Token | 2018 |
Token ID | 2864 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
tera | +0.018 |
river | +0.016 |
ograp | +0.014 |
wcsstore | +0.014 |
ppo | +0.014 |
Neg logit contributions | |
alities | -0.014 |
Reviewed | -0.013 |
ities | -0.013 |
Collider | -0.013 |
romeda | -0.013 |
Token | S |
Token ID | 311 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
tera | +0.085 |
river | +0.077 |
ograp | +0.068 |
wcsstore | +0.067 |
ppo | +0.066 |
Neg logit contributions | |
alities | -0.065 |
ities | -0.064 |
Reviewed | -0.064 |
Collider | -0.062 |
romeda | -0.061 |
Token | arg |
Token ID | 853 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
tera | +0.122 |
river | +0.112 |
ograp | +0.101 |
wcsstore | +0.099 |
ppo | +0.098 |
Neg logit contributions | |
alities | -0.068 |
ities | -0.067 |
Reviewed | -0.066 |
Collider | -0.064 |
romeda | -0.063 |
Token | ent |
Token ID | 298 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
alities | +0.079 |
ities | +0.078 |
Reviewed | +0.077 |
Collider | +0.075 |
romeda | +0.074 |
Neg logit contributions | |
tera | -0.111 |
river | -0.100 |
ograp | -0.090 |
wcsstore | -0.088 |
ppo | -0.087 |
Token | Sh |
Token ID | 911 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
tera | +0.013 |
river | +0.012 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.010 |
Neg logit contributions | |
alities | -0.009 |
Reviewed | -0.009 |
ities | -0.009 |
Collider | -0.008 |
romeda | -0.008 |
Token | river |
Token ID | 38291 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
tera | +0.003 |
river | +0.000 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.004 |
Neg logit contributions | |
alities | -0.049 |
ities | -0.049 |
Reviewed | -0.049 |
Collider | -0.048 |
romeda | -0.048 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
tera | +0.408 |
river | +0.370 |
ograp | +0.325 |
wcsstore | +0.320 |
ppo | +0.314 |
Neg logit contributions | |
alities | -0.335 |
ities | -0.331 |
Reviewed | -0.331 |
Collider | -0.322 |
romeda | -0.318 |
Token | for |
Token ID | 329 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
tera | +0.049 |
river | +0.045 |
ograp | +0.040 |
wcsstore | +0.039 |
ppo | +0.039 |
Neg logit contributions | |
alities | -0.036 |
Reviewed | -0.035 |
ities | -0.035 |
Collider | -0.034 |
romeda | -0.034 |
Token | Dist |
Token ID | 4307 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | inguished |
Token ID | 46709 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
tera | +0.145 |
river | +0.132 |
ograp | +0.119 |
wcsstore | +0.118 |
ppo | +0.116 |
Neg logit contributions | |
alities | -0.081 |
ities | -0.081 |
Reviewed | -0.080 |
Collider | -0.077 |
romeda | -0.076 |
Token | Human |
Token ID | 5524 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
alities | +0.080 |
Reviewed | +0.079 |
ities | +0.078 |
Collider | +0.076 |
romeda | +0.075 |
Neg logit contributions | |
tera | -0.095 |
river | -0.086 |
ograp | -0.075 |
wcsstore | -0.074 |
ppo | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
alities | +0.138 |
ities | +0.136 |
Reviewed | +0.136 |
Collider | +0.132 |
romeda | +0.130 |
Neg logit contributions | |
tera | -0.170 |
river | -0.154 |
ograp | -0.136 |
wcsstore | -0.134 |
ppo | -0.131 |
Token | Read |
Token ID | 4149 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
tera | +0.006 |
river | +0.005 |
ograp | +0.005 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.005 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -3.06e-04 |
Pos logit contributions | |
alities | +0.035 |
ities | +0.034 |
Reviewed | +0.034 |
Collider | +0.033 |
romeda | +0.033 |
Neg logit contributions | |
tera | -0.042 |
river | -0.038 |
ograp | -0.034 |
wcsstore | -0.033 |
ppo | -0.032 |
Token | 2018 |
Token ID | 2864 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | Sh |
Token ID | 911 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
tera | +0.088 |
river | +0.080 |
ograp | +0.072 |
wcsstore | +0.071 |
ppo | +0.070 |
Neg logit contributions | |
alities | -0.054 |
ities | -0.053 |
Reviewed | -0.053 |
Collider | -0.051 |
romeda | -0.050 |
Token | river |
Token ID | 38291 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
tera | +0.003 |
river | +0.000 |
ograp | -0.002 |
wcsstore | -0.003 |
ppo | -0.003 |
Neg logit contributions | |
alities | -0.044 |
ities | -0.044 |
Reviewed | -0.043 |
Collider | -0.043 |
romeda | -0.043 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
tera | +0.414 |
river | +0.374 |
ograp | +0.331 |
wcsstore | +0.326 |
ppo | +0.320 |
Neg logit contributions | |
alities | -0.324 |
ities | -0.320 |
Reviewed | -0.320 |
Collider | -0.311 |
romeda | -0.307 |
Token | announcement |
Token ID | 8009 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
tera | +0.057 |
river | +0.052 |
ograp | +0.047 |
wcsstore | +0.046 |
ppo | +0.046 |
Neg logit contributions | |
alities | -0.030 |
ities | -0.030 |
Reviewed | -0.030 |
Collider | -0.029 |
romeda | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-04 |
Pos logit contributions | |
alities | +0.024 |
ities | +0.024 |
Reviewed | +0.024 |
Collider | +0.023 |
romeda | +0.023 |
Neg logit contributions | |
tera | -0.032 |
river | -0.029 |
ograp | -0.026 |
wcsstore | -0.025 |
ppo | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | an |
Token ID | 281 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
tera | +0.062 |
river | +0.057 |
ograp | +0.050 |
wcsstore | +0.050 |
ppo | +0.049 |
Neg logit contributions | |
alities | -0.041 |
ities | -0.040 |
Reviewed | -0.040 |
Collider | -0.039 |
romeda | -0.038 |
Token | individual |
Token ID | 1981 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
alities | +0.044 |
ities | +0.043 |
Reviewed | +0.043 |
Collider | +0.042 |
romeda | +0.042 |
Neg logit contributions | |
tera | -0.031 |
river | -0.027 |
ograp | -0.023 |
wcsstore | -0.022 |
ppo | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +2.18e-04 |
Pos logit contributions | |
tera | +0.113 |
river | +0.103 |
ograp | +0.091 |
wcsstore | +0.090 |
ppo | +0.088 |
Neg logit contributions | |
alities | -0.086 |
ities | -0.085 |
Reviewed | -0.085 |
Collider | -0.083 |
romeda | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
tera | +0.000 |
river | +0.000 |
ograp | +0.000 |
wcsstore | +0.000 |
ppo | +0.000 |
Neg logit contributions | |
alities | -0.000 |
ities | -0.000 |
Reviewed | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | Sh |
Token ID | 911 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
alities | +0.003 |
ities | +0.003 |
Reviewed | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | river |
Token ID | 38291 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
tera | +0.003 |
river | +0.000 |
ograp | -0.002 |
wcsstore | -0.003 |
ppo | -0.003 |
Neg logit contributions | |
alities | -0.046 |
ities | -0.046 |
Reviewed | -0.046 |
Collider | -0.045 |
romeda | -0.045 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
tera | +0.405 |
river | +0.367 |
ograp | +0.323 |
wcsstore | +0.317 |
ppo | +0.311 |
Neg logit contributions | |
alities | -0.330 |
Reviewed | -0.326 |
ities | -0.326 |
Collider | -0.317 |
romeda | -0.313 |
Token | , |
Token ID | 11 |
Feature activation | -5.87e-05 |
Pos logit contributions | |
tera | +0.050 |
river | +0.045 |
ograp | +0.040 |
wcsstore | +0.039 |
ppo | +0.039 |
Neg logit contributions | |
alities | -0.038 |
ities | -0.037 |
Reviewed | -0.037 |
Collider | -0.036 |
romeda | -0.036 |
Token | please |
Token ID | 3387 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | download |
Token ID | 4321 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
tera | +0.107 |
river | +0.094 |
ograp | +0.079 |
wcsstore | +0.078 |
ppo | +0.076 |
Neg logit contributions | |
alities | -0.138 |
ities | -0.136 |
Reviewed | -0.136 |
Collider | -0.133 |
romeda | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
tera | +0.121 |
river | +0.110 |
ograp | +0.098 |
wcsstore | +0.097 |
ppo | +0.095 |
Neg logit contributions | |
alities | -0.078 |
ities | -0.077 |
Reviewed | -0.076 |
Collider | -0.074 |
romeda | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
tera | +0.004 |
river | +0.004 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | S |
Token ID | 50 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | arg |
Token ID | 853 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
tera | +0.040 |
river | +0.036 |
ograp | +0.032 |
wcsstore | +0.031 |
ppo | +0.031 |
Neg logit contributions | |
alities | -0.036 |
ities | -0.036 |
Reviewed | -0.036 |
Collider | -0.035 |
romeda | -0.034 |
Token | ent |
Token ID | 298 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
alities | +0.087 |
Reviewed | +0.086 |
ities | +0.086 |
Collider | +0.084 |
romeda | +0.082 |
Neg logit contributions | |
tera | -0.107 |
river | -0.096 |
ograp | -0.085 |
wcsstore | -0.084 |
ppo | -0.082 |
Token | Sh |
Token ID | 911 |
Feature activation | +9.23e-02 |
Pos logit contributions | |
tera | +0.008 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | river |
Token ID | 38291 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
tera | +0.024 |
river | +0.022 |
ograp | +0.019 |
wcsstore | +0.018 |
ppo | +0.018 |
Neg logit contributions | |
alities | -0.021 |
Reviewed | -0.021 |
ities | -0.021 |
Collider | -0.020 |
romeda | -0.020 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
tera | +0.408 |
river | +0.370 |
ograp | +0.326 |
wcsstore | +0.319 |
ppo | +0.315 |
Neg logit contributions | |
alities | -0.324 |
Reviewed | -0.320 |
ities | -0.318 |
Collider | -0.311 |
romeda | -0.306 |
Token | for |
Token ID | 329 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
tera | +0.044 |
river | +0.040 |
ograp | +0.035 |
wcsstore | +0.035 |
ppo | +0.034 |
Neg logit contributions | |
alities | -0.034 |
Reviewed | -0.033 |
ities | -0.033 |
Collider | -0.033 |
romeda | -0.032 |
Token | Dist |
Token ID | 4307 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.006 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | inguished |
Token ID | 46709 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
tera | +0.139 |
river | +0.127 |
ograp | +0.114 |
wcsstore | +0.113 |
ppo | +0.111 |
Neg logit contributions | |
alities | -0.081 |
ities | -0.080 |
Reviewed | -0.079 |
Collider | -0.077 |
romeda | -0.075 |
Token | Human |
Token ID | 5524 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
alities | +0.082 |
Reviewed | +0.081 |
ities | +0.081 |
Collider | +0.079 |
romeda | +0.078 |
Neg logit contributions | |
tera | -0.099 |
river | -0.090 |
ograp | -0.079 |
wcsstore | -0.078 |
ppo | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | -5.87e-05 |
Pos logit contributions | |
tera | +0.050 |
river | +0.045 |
ograp | +0.040 |
wcsstore | +0.039 |
ppo | +0.039 |
Neg logit contributions | |
alities | -0.038 |
ities | -0.037 |
Reviewed | -0.037 |
Collider | -0.036 |
romeda | -0.036 |
Token | please |
Token ID | 3387 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | download |
Token ID | 4321 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
tera | +0.107 |
river | +0.094 |
ograp | +0.079 |
wcsstore | +0.078 |
ppo | +0.076 |
Neg logit contributions | |
alities | -0.138 |
ities | -0.136 |
Reviewed | -0.136 |
Collider | -0.133 |
romeda | -0.131 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
tera | +0.121 |
river | +0.110 |
ograp | +0.098 |
wcsstore | +0.097 |
ppo | +0.095 |
Neg logit contributions | |
alities | -0.078 |
ities | -0.077 |
Reviewed | -0.076 |
Collider | -0.074 |
romeda | -0.073 |
Token | Sh |
Token ID | 911 |
Feature activation | +9.57e-02 |
Pos logit contributions | |
alities | +0.003 |
ities | +0.003 |
Reviewed | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | river |
Token ID | 38291 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
tera | +0.003 |
river | +0.000 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.003 |
Neg logit contributions | |
alities | -0.044 |
ities | -0.043 |
Reviewed | -0.043 |
Collider | -0.042 |
romeda | -0.042 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
tera | +0.406 |
river | +0.367 |
ograp | +0.324 |
wcsstore | +0.319 |
ppo | +0.314 |
Neg logit contributions | |
alities | -0.324 |
ities | -0.320 |
Reviewed | -0.319 |
Collider | -0.310 |
romeda | -0.306 |
Token | nomination |
Token ID | 11872 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
tera | +0.058 |
river | +0.053 |
ograp | +0.048 |
wcsstore | +0.048 |
ppo | +0.047 |
Neg logit contributions | |
alities | -0.029 |
ities | -0.029 |
Reviewed | -0.029 |
Collider | -0.028 |
romeda | -0.027 |
Token | packet |
Token ID | 19638 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
alities | +0.010 |
ities | +0.010 |
Reviewed | +0.010 |
Collider | +0.010 |
romeda | +0.010 |
Neg logit contributions | |
tera | -0.014 |
river | -0.013 |
ograp | -0.011 |
wcsstore | -0.011 |
ppo | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
tera | +0.007 |
river | +0.007 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.005 |
ities | -0.005 |
Reviewed | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | submit |
Token ID | 9199 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
tera | +0.004 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.004 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
alities | +0.022 |
ities | +0.022 |
Reviewed | +0.022 |
Collider | +0.021 |
romeda | +0.021 |
Neg logit contributions | |
tera | -0.029 |
river | -0.026 |
ograp | -0.023 |
wcsstore | -0.023 |
ppo | -0.022 |
Token | S |
Token ID | 311 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.005 |
river | -0.005 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | arg |
Token ID | 853 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
tera | +0.116 |
river | +0.106 |
ograp | +0.095 |
wcsstore | +0.094 |
ppo | +0.092 |
Neg logit contributions | |
alities | -0.069 |
Reviewed | -0.068 |
ities | -0.068 |
Collider | -0.066 |
romeda | -0.064 |
Token | ent |
Token ID | 298 |
Feature activation | +2.38e-03 |
Pos logit contributions | |
alities | +0.089 |
ities | +0.088 |
Reviewed | +0.087 |
Collider | +0.085 |
romeda | +0.084 |
Neg logit contributions | |
tera | -0.122 |
river | -0.110 |
ograp | -0.098 |
wcsstore | -0.097 |
ppo | -0.095 |
Token | Sh |
Token ID | 911 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.000 |
Reviewed | -0.000 |
ities | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | river |
Token ID | 38291 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
tera | +0.003 |
river | +0.000 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Neg logit contributions | |
alities | -0.044 |
ities | -0.044 |
Reviewed | -0.044 |
Collider | -0.044 |
romeda | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
tera | +0.399 |
river | +0.362 |
ograp | +0.318 |
wcsstore | +0.311 |
ppo | +0.308 |
Neg logit contributions | |
alities | -0.322 |
Reviewed | -0.319 |
ities | -0.317 |
Collider | -0.309 |
romeda | -0.305 |
Token | in |
Token ID | 287 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
tera | +0.000 |
river | +0.000 |
ograp | +0.000 |
wcsstore | +0.000 |
ppo | +0.000 |
Neg logit contributions | |
alities | -0.000 |
ities | -0.000 |
Reviewed | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | founding |
Token ID | 16636 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.006 |
ities | -0.006 |
Reviewed | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
tera | +0.063 |
river | +0.057 |
ograp | +0.051 |
wcsstore | +0.050 |
ppo | +0.049 |
Neg logit contributions | |
alities | -0.043 |
ities | -0.043 |
Reviewed | -0.042 |
Collider | -0.041 |
romeda | -0.040 |
Token | developing |
Token ID | 5922 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
alities | +0.002 |
Reviewed | +0.002 |
ities | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | S |
Token ID | 311 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
tera | +0.014 |
river | +0.013 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.011 |
Neg logit contributions | |
alities | -0.011 |
Reviewed | -0.011 |
ities | -0.011 |
Collider | -0.011 |
romeda | -0.011 |
Token | arg |
Token ID | 853 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
tera | +0.121 |
river | +0.110 |
ograp | +0.099 |
wcsstore | +0.098 |
ppo | +0.097 |
Neg logit contributions | |
alities | -0.068 |
ities | -0.066 |
Reviewed | -0.066 |
Collider | -0.064 |
romeda | -0.063 |
Token | ent |
Token ID | 298 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
alities | +0.092 |
ities | +0.090 |
Reviewed | +0.089 |
Collider | +0.087 |
romeda | +0.086 |
Neg logit contributions | |
tera | -0.127 |
river | -0.115 |
ograp | -0.103 |
wcsstore | -0.101 |
ppo | -0.100 |
Token | Sh |
Token ID | 911 |
Feature activation | +8.69e-02 |
Pos logit contributions | |
tera | +0.000 |
river | +0.000 |
ograp | +0.000 |
wcsstore | +0.000 |
ppo | +0.000 |
Neg logit contributions | |
alities | -0.000 |
Reviewed | -0.000 |
ities | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | river |
Token ID | 38291 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
tera | +0.002 |
river | +0.000 |
ograp | -0.002 |
wcsstore | -0.003 |
ppo | -0.003 |
Neg logit contributions | |
alities | -0.040 |
ities | -0.040 |
Reviewed | -0.040 |
Collider | -0.039 |
romeda | -0.039 |
Token | Award |
Token ID | 11289 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
tera | +0.389 |
river | +0.353 |
ograp | +0.309 |
wcsstore | +0.303 |
ppo | +0.297 |
Neg logit contributions | |
alities | -0.325 |
Reviewed | -0.323 |
ities | -0.321 |
Collider | -0.312 |
romeda | -0.309 |
Token | for |
Token ID | 329 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
tera | +0.040 |
river | +0.036 |
ograp | +0.032 |
wcsstore | +0.031 |
ppo | +0.031 |
Neg logit contributions | |
alities | -0.032 |
Reviewed | -0.032 |
ities | -0.032 |
Collider | -0.031 |
romeda | -0.030 |
Token | Dist |
Token ID | 4307 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
alities | +0.009 |
ities | +0.009 |
Reviewed | +0.009 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.007 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | inguished |
Token ID | 46709 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
tera | +0.131 |
river | +0.119 |
ograp | +0.108 |
wcsstore | +0.107 |
ppo | +0.105 |
Neg logit contributions | |
alities | -0.074 |
ities | -0.073 |
Reviewed | -0.072 |
Collider | -0.069 |
romeda | -0.069 |
Token | Human |
Token ID | 5524 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
alities | +0.085 |
Reviewed | +0.084 |
ities | +0.084 |
Collider | +0.082 |
romeda | +0.081 |
Neg logit contributions | |
tera | -0.101 |
river | -0.091 |
ograp | -0.080 |
wcsstore | -0.079 |
ppo | -0.077 |
Token | Mill |
Token ID | 9212 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.006 |
ities | -0.006 |
Reviewed | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | Rd |
Token ID | 20769 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
tera | +0.140 |
river | +0.128 |
ograp | +0.114 |
wcsstore | +0.113 |
ppo | +0.111 |
Neg logit contributions | |
alities | -0.091 |
ities | -0.090 |
Reviewed | -0.089 |
Collider | -0.087 |
romeda | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
tera | +0.028 |
river | +0.025 |
ograp | +0.022 |
wcsstore | +0.021 |
ppo | +0.021 |
Neg logit contributions | |
alities | -0.027 |
ities | -0.027 |
Reviewed | -0.027 |
Collider | -0.026 |
romeda | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
tera | +0.010 |
river | +0.009 |
ograp | +0.008 |
wcsstore | +0.008 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.008 |
ities | -0.008 |
Reviewed | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | Et |
Token ID | 17906 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
tera | +0.024 |
river | +0.022 |
ograp | +0.020 |
wcsstore | +0.019 |
ppo | +0.019 |
Neg logit contributions | |
alities | -0.017 |
Reviewed | -0.017 |
ities | -0.017 |
Collider | -0.017 |
romeda | -0.016 |
Token | obic |
Token ID | 20803 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
alities | +0.257 |
ities | +0.255 |
Reviewed | +0.254 |
Collider | +0.250 |
romeda | +0.250 |
Neg logit contributions | |
tera | -0.044 |
river | -0.027 |
ograp | -0.010 |
wcsstore | -0.008 |
ppo | -0.006 |
Token | oke |
Token ID | 2088 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
tera | +0.516 |
river | +0.485 |
ograp | +0.447 |
obic | +0.444 |
ppo | +0.438 |
Neg logit contributions | |
alities | -0.149 |
Reviewed | -0.143 |
Collider | -0.141 |
romeda | -0.140 |
ities | -0.138 |
Token | � |
Token ID | 447 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
alities | +0.158 |
Reviewed | +0.156 |
ities | +0.154 |
Collider | +0.151 |
romeda | +0.149 |
Neg logit contributions | |
tera | -0.204 |
river | -0.185 |
ograp | -0.163 |
wcsstore | -0.160 |
ppo | -0.159 |
Token | � |
Token ID | 247 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
tera | +0.011 |
river | +0.010 |
ograp | +0.009 |
wcsstore | +0.009 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.010 |
ities | -0.010 |
Reviewed | -0.010 |
Collider | -0.010 |
romeda | -0.009 |
Token | s |
Token ID | 82 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
tera | +0.006 |
river | +0.005 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.004 |
Reviewed | -0.004 |
ities | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | Mark |
Token ID | 2940 |
Feature activation | +2.46e-04 |
Pos logit contributions | |
tera | +0.010 |
river | +0.009 |
ograp | +0.008 |
wcsstore | +0.008 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.007 |
Reviewed | -0.007 |
ities | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | pling |
Token ID | 11347 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
alities | +0.030 |
Reviewed | +0.030 |
ities | +0.030 |
Collider | +0.030 |
romeda | +0.029 |
Neg logit contributions | |
tera | -0.013 |
river | -0.010 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.007 |
Token | subway |
Token ID | 19612 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
tera | +0.203 |
river | +0.185 |
ograp | +0.164 |
ppo | +0.160 |
wcsstore | +0.160 |
Neg logit contributions | |
alities | -0.136 |
Reviewed | -0.133 |
ities | -0.133 |
Collider | -0.129 |
romeda | -0.128 |
Token | station |
Token ID | 4429 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
alities | +0.017 |
Reviewed | +0.016 |
ities | +0.016 |
Collider | +0.016 |
romeda | +0.015 |
Neg logit contributions | |
tera | -0.042 |
river | -0.039 |
ograp | -0.035 |
wcsstore | -0.035 |
ppo | -0.035 |
Token | in |
Token ID | 287 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
alities | +0.100 |
Reviewed | +0.098 |
ities | +0.098 |
Collider | +0.096 |
romeda | +0.094 |
Neg logit contributions | |
tera | -0.120 |
river | -0.109 |
ograp | -0.095 |
wcsstore | -0.093 |
ppo | -0.092 |
Token | Et |
Token ID | 17906 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.007 |
Reviewed | -0.007 |
ities | -0.007 |
Collider | -0.006 |
romeda | -0.006 |
Token | obic |
Token ID | 20803 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
alities | +0.263 |
ities | +0.262 |
Reviewed | +0.260 |
romeda | +0.257 |
Collider | +0.256 |
Neg logit contributions | |
tera | -0.048 |
river | -0.032 |
ograp | -0.014 |
wcsstore | -0.011 |
ppo | -0.010 |
Token | oke |
Token ID | 2088 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
tera | +0.507 |
river | +0.475 |
ograp | +0.438 |
obic | +0.434 |
ppo | +0.429 |
Neg logit contributions | |
alities | -0.143 |
Reviewed | -0.138 |
Collider | -0.136 |
ities | -0.134 |
romeda | -0.133 |
Token | . |
Token ID | 13 |
Feature activation | +8.44e-03 |
Pos logit contributions | |
alities | +0.180 |
Reviewed | +0.177 |
ities | +0.176 |
Collider | +0.173 |
romeda | +0.170 |
Neg logit contributions | |
tera | -0.206 |
river | -0.187 |
ograp | -0.162 |
obic | -0.158 |
ppo | -0.158 |
Token |
|
Token ID | 198 |
Feature activation | +9.13e-03 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -6.57e-03 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | Police |
Token ID | 9039 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | over |
Token ID | 625 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
alities | +0.034 |
ities | +0.034 |
Reviewed | +0.034 |
Collider | +0.033 |
romeda | +0.032 |
Neg logit contributions | |
tera | -0.043 |
river | -0.039 |
ograp | -0.035 |
wcsstore | -0.034 |
ppo | -0.034 |
Token | growth |
Token ID | 27922 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
alities | +0.040 |
ities | +0.040 |
Reviewed | +0.039 |
Collider | +0.039 |
romeda | +0.038 |
Neg logit contributions | |
tera | -0.032 |
river | -0.028 |
ograp | -0.024 |
wcsstore | -0.023 |
ppo | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
tera | +0.172 |
river | +0.155 |
ograp | +0.137 |
wcsstore | +0.135 |
ppo | +0.133 |
Neg logit contributions | |
alities | -0.141 |
ities | -0.139 |
Reviewed | -0.139 |
Collider | -0.135 |
romeda | -0.133 |
Token | an |
Token ID | 281 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | aer |
Token ID | 25534 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
alities | +0.035 |
ities | +0.034 |
Reviewed | +0.034 |
Collider | +0.033 |
romeda | +0.033 |
Neg logit contributions | |
tera | -0.046 |
river | -0.042 |
ograp | -0.037 |
wcsstore | -0.037 |
ppo | -0.036 |
Token | obic |
Token ID | 20803 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
alities | +0.009 |
ities | +0.009 |
Reviewed | +0.009 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.002 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | pathogens |
Token ID | 38366 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
tera | +0.469 |
river | +0.434 |
ograp | +0.396 |
wcsstore | +0.391 |
ppo | +0.387 |
Neg logit contributions | |
alities | -0.177 |
Reviewed | -0.173 |
ities | -0.172 |
Collider | -0.166 |
romeda | -0.162 |
Token | ( |
Token ID | 357 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
alities | +0.020 |
ities | +0.020 |
Reviewed | +0.020 |
Collider | +0.020 |
romeda | +0.019 |
Neg logit contributions | |
tera | -0.026 |
river | -0.023 |
ograp | -0.021 |
wcsstore | -0.020 |
ppo | -0.020 |
Token | Prev |
Token ID | 36854 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | ot |
Token ID | 313 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
alities | +0.115 |
Reviewed | +0.114 |
ities | +0.114 |
Collider | +0.111 |
romeda | +0.110 |
Neg logit contributions | |
tera | -0.117 |
river | -0.105 |
ograp | -0.090 |
wcsstore | -0.088 |
ppo | -0.088 |
Token | ella |
Token ID | 12627 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
alities | +0.008 |
Reviewed | +0.008 |
ities | +0.008 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.022 |
river | -0.021 |
ograp | -0.019 |
wcsstore | -0.019 |
ppo | -0.018 |
Token | credit |
Token ID | 3884 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.007 |
ities | -0.007 |
Reviewed | -0.007 |
Collider | -0.007 |
romeda | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
tera | +0.023 |
river | +0.021 |
ograp | +0.019 |
wcsstore | +0.018 |
ppo | +0.018 |
Neg logit contributions | |
alities | -0.019 |
Reviewed | -0.018 |
ities | -0.018 |
Collider | -0.018 |
romeda | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.006 |
ities | -0.006 |
Reviewed | -0.006 |
Collider | -0.005 |
romeda | -0.005 |
Token | hack |
Token ID | 8156 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
alities | +0.039 |
ities | +0.039 |
Reviewed | +0.039 |
Collider | +0.038 |
romeda | +0.037 |
Neg logit contributions | |
tera | -0.054 |
river | -0.049 |
ograp | -0.044 |
wcsstore | -0.043 |
ppo | -0.042 |
Token | Crowd |
Token ID | 29452 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.007 |
Reviewed | -0.007 |
ities | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | strike |
Token ID | 33069 |
Feature activation | +9.91e-02 |
Pos logit contributions | |
tera | +0.329 |
river | +0.296 |
ograp | +0.257 |
wcsstore | +0.253 |
ppo | +0.248 |
Neg logit contributions | |
alities | -0.309 |
ities | -0.305 |
Reviewed | -0.304 |
Collider | -0.297 |
romeda | -0.292 |
Token | stood |
Token ID | 6204 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
tera | +0.028 |
river | +0.025 |
ograp | +0.023 |
wcsstore | +0.022 |
ppo | +0.022 |
Neg logit contributions | |
alities | -0.020 |
ities | -0.020 |
Reviewed | -0.020 |
Collider | -0.019 |
romeda | -0.019 |
Token | by |
Token ID | 416 |
Feature activation | -7.89e-04 |
Pos logit contributions | |
alities | +0.056 |
Reviewed | +0.055 |
ities | +0.055 |
Collider | +0.054 |
romeda | +0.053 |
Neg logit contributions | |
tera | -0.075 |
river | -0.069 |
ograp | -0.060 |
wcsstore | -0.060 |
ppo | -0.059 |
Token | its |
Token ID | 663 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
alities | +0.000 |
Reviewed | +0.000 |
ities | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | analysis |
Token ID | 3781 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
alities | +0.010 |
Reviewed | +0.010 |
ities | +0.010 |
Collider | +0.009 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.013 |
river | -0.012 |
ograp | -0.011 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | ). |
Token ID | 737 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
alities | +0.048 |
ities | +0.047 |
Reviewed | +0.047 |
Collider | +0.045 |
romeda | +0.045 |
Neg logit contributions | |
tera | -0.082 |
river | -0.075 |
ograp | -0.067 |
wcsstore | -0.066 |
ppo | -0.065 |
Token | S |
Token ID | 311 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
alities | +0.049 |
ities | +0.049 |
Reviewed | +0.049 |
Collider | +0.047 |
romeda | +0.047 |
Neg logit contributions | |
tera | -0.057 |
river | -0.051 |
ograp | -0.045 |
wcsstore | -0.044 |
ppo | -0.044 |
Token | NS |
Token ID | 8035 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
tera | +0.124 |
river | +0.113 |
ograp | +0.102 |
wcsstore | +0.101 |
ppo | +0.100 |
Neg logit contributions | |
alities | -0.066 |
ities | -0.066 |
Reviewed | -0.065 |
Collider | -0.062 |
romeda | -0.061 |
Token | is |
Token ID | 318 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
alities | +0.054 |
ities | +0.054 |
Reviewed | +0.053 |
Collider | +0.052 |
romeda | +0.051 |
Neg logit contributions | |
tera | -0.074 |
river | -0.067 |
ograp | -0.060 |
wcsstore | -0.059 |
ppo | -0.058 |
Token | bas |
Token ID | 1615 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | cially |
Token ID | 2131 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
alities | +0.100 |
ities | +0.099 |
Reviewed | +0.098 |
Collider | +0.096 |
romeda | +0.095 |
Neg logit contributions | |
tera | -0.103 |
river | -0.092 |
ograp | -0.080 |
wcsstore | -0.079 |
ppo | -0.077 |
Token | a |
Token ID | 257 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
tera | +0.376 |
river | +0.343 |
ograp | +0.304 |
wcsstore | +0.299 |
ppo | +0.296 |
Neg logit contributions | |
alities | -0.259 |
Reviewed | -0.255 |
ities | -0.255 |
Collider | -0.248 |
romeda | -0.243 |
Token | notification |
Token ID | 14483 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
tera | +0.006 |
river | +0.006 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.005 |
Reviewed | -0.005 |
ities | -0.005 |
Collider | -0.004 |
romeda | -0.004 |
Token | service |
Token ID | 2139 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
tera | +0.028 |
river | +0.026 |
ograp | +0.023 |
wcsstore | +0.022 |
ppo | +0.022 |
Neg logit contributions | |
alities | -0.021 |
Reviewed | -0.021 |
ities | -0.021 |
Collider | -0.020 |
romeda | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
alities | +0.028 |
ities | +0.027 |
Reviewed | +0.027 |
Collider | +0.027 |
romeda | +0.026 |
Neg logit contributions | |
tera | -0.035 |
river | -0.032 |
ograp | -0.028 |
wcsstore | -0.028 |
ppo | -0.027 |
Token | AWS |
Token ID | 30865 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
tera | +0.033 |
river | +0.030 |
ograp | +0.027 |
wcsstore | +0.026 |
ppo | +0.026 |
Neg logit contributions | |
alities | -0.026 |
Reviewed | -0.026 |
ities | -0.026 |
Collider | -0.025 |
romeda | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
tera | +0.005 |
river | +0.004 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | Other |
Token ID | 6395 |
Feature activation | -6.78e-02 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.005 |
river | -0.005 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | security |
Token ID | 2324 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
alities | +0.015 |
ities | +0.014 |
Reviewed | +0.014 |
Collider | +0.014 |
romeda | +0.014 |
Neg logit contributions | |
tera | -0.018 |
river | -0.017 |
ograp | -0.015 |
wcsstore | -0.015 |
ppo | -0.014 |
Token | firms |
Token ID | 9611 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
alities | +0.033 |
ities | +0.032 |
Reviewed | +0.032 |
Collider | +0.032 |
romeda | +0.031 |
Neg logit contributions | |
tera | -0.038 |
river | -0.035 |
ograp | -0.030 |
wcsstore | -0.030 |
ppo | -0.029 |
Token | backed |
Token ID | 9763 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
alities | +0.026 |
ities | +0.025 |
Reviewed | +0.025 |
Collider | +0.025 |
romeda | +0.024 |
Neg logit contributions | |
tera | -0.035 |
river | -0.032 |
ograp | -0.028 |
wcsstore | -0.028 |
ppo | -0.028 |
Token | Crowd |
Token ID | 29452 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
alities | +0.053 |
ities | +0.053 |
Reviewed | +0.052 |
Collider | +0.051 |
romeda | +0.050 |
Neg logit contributions | |
tera | -0.062 |
river | -0.056 |
ograp | -0.049 |
wcsstore | -0.048 |
ppo | -0.048 |
Token | strike |
Token ID | 33069 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
tera | +0.321 |
river | +0.288 |
ograp | +0.250 |
wcsstore | +0.246 |
ppo | +0.241 |
Neg logit contributions | |
alities | -0.311 |
ities | -0.307 |
Reviewed | -0.306 |
Collider | -0.300 |
romeda | -0.295 |
Token | 's |
Token ID | 338 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
tera | +0.023 |
river | +0.021 |
ograp | +0.018 |
wcsstore | +0.018 |
ppo | +0.018 |
Neg logit contributions | |
alities | -0.018 |
ities | -0.018 |
Reviewed | -0.018 |
Collider | -0.017 |
romeda | -0.017 |
Token | assessment |
Token ID | 8922 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.008 |
Reviewed | -0.008 |
ities | -0.008 |
Collider | -0.007 |
romeda | -0.007 |
Token | up |
Token ID | 510 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
tera | +0.147 |
river | +0.133 |
ograp | +0.117 |
wcsstore | +0.115 |
ppo | +0.113 |
Neg logit contributions | |
alities | -0.118 |
Reviewed | -0.117 |
ities | -0.117 |
Collider | -0.114 |
romeda | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | ont |
Token ID | 756 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
alities | +0.090 |
ities | +0.089 |
Reviewed | +0.089 |
Collider | +0.087 |
romeda | +0.086 |
Neg logit contributions | |
tera | -0.078 |
river | -0.069 |
ograp | -0.059 |
wcsstore | -0.058 |
ppo | -0.057 |
Token | region |
Token ID | 3814 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
tera | +0.016 |
river | +0.014 |
ograp | +0.012 |
wcsstore | +0.012 |
ppo | +0.012 |
Neg logit contributions | |
alities | -0.013 |
Reviewed | -0.013 |
ities | -0.013 |
Collider | -0.013 |
romeda | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
tera | +0.020 |
river | +0.018 |
ograp | +0.015 |
wcsstore | +0.015 |
ppo | +0.015 |
Neg logit contributions | |
alities | -0.017 |
Reviewed | -0.017 |
ities | -0.017 |
Collider | -0.017 |
romeda | -0.016 |
Token | And |
Token ID | 843 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
alities | +0.007 |
ities | +0.007 |
Reviewed | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.008 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token | cru |
Token ID | 4630 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
tera | +0.007 |
river | +0.006 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.005 |
Reviewed | -0.005 |
ities | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | cially |
Token ID | 2131 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
alities | +0.140 |
ities | +0.139 |
Reviewed | +0.139 |
Collider | +0.137 |
romeda | +0.136 |
Neg logit contributions | |
tera | -0.027 |
river | -0.018 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
tera | +0.354 |
river | +0.320 |
ograp | +0.281 |
wcsstore | +0.276 |
ppo | +0.274 |
Neg logit contributions | |
alities | -0.276 |
Reviewed | -0.273 |
ities | -0.272 |
Collider | -0.266 |
romeda | -0.261 |
Token | even |
Token ID | 772 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
tera | +0.116 |
river | +0.106 |
ograp | +0.093 |
wcsstore | +0.091 |
ppo | +0.090 |
Neg logit contributions | |
alities | -0.088 |
Reviewed | -0.088 |
ities | -0.086 |
Collider | -0.085 |
romeda | -0.082 |
Token | sea |
Token ID | 5417 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
tera | +0.019 |
river | +0.017 |
ograp | +0.015 |
wcsstore | +0.015 |
ppo | +0.015 |
Neg logit contributions | |
alities | -0.012 |
Reviewed | -0.012 |
ities | -0.012 |
Collider | -0.012 |
romeda | -0.011 |
Token | itself |
Token ID | 2346 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | well |
Token ID | 880 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
alities | +0.027 |
Reviewed | +0.026 |
ities | +0.026 |
Collider | +0.026 |
romeda | +0.025 |
Neg logit contributions | |
tera | -0.032 |
river | -0.029 |
ograp | -0.025 |
wcsstore | -0.025 |
ppo | -0.025 |
Token | ,' |
Token ID | 4032 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
tera | +0.112 |
river | +0.102 |
ograp | +0.091 |
wcsstore | +0.089 |
ppo | +0.088 |
Neg logit contributions | |
alities | -0.079 |
ities | -0.078 |
Reviewed | -0.078 |
Collider | -0.075 |
romeda | -0.074 |
Token | said |
Token ID | 531 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
alities | +0.030 |
ities | +0.030 |
Reviewed | +0.030 |
Collider | +0.029 |
romeda | +0.029 |
Neg logit contributions | |
tera | -0.032 |
river | -0.029 |
ograp | -0.025 |
wcsstore | -0.024 |
ppo | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -7.79e-03 |
Pos logit contributions | |
tera | +0.015 |
river | +0.014 |
ograp | +0.012 |
wcsstore | +0.012 |
ppo | +0.012 |
Neg logit contributions | |
alities | -0.012 |
Reviewed | -0.012 |
ities | -0.011 |
Collider | -0.011 |
romeda | -0.011 |
Token | initial |
Token ID | 4238 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
alities | +0.002 |
Reviewed | +0.002 |
ities | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | Crowd |
Token ID | 29452 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
alities | +0.073 |
Reviewed | +0.072 |
ities | +0.072 |
Collider | +0.070 |
romeda | +0.069 |
Neg logit contributions | |
tera | -0.066 |
river | -0.058 |
ograp | -0.050 |
wcsstore | -0.049 |
ppo | -0.048 |
Token | strike |
Token ID | 33069 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
tera | +0.313 |
river | +0.280 |
ograp | +0.242 |
wcsstore | +0.238 |
ppo | +0.233 |
Neg logit contributions | |
alities | -0.310 |
ities | -0.305 |
Reviewed | -0.305 |
Collider | -0.298 |
romeda | -0.294 |
Token | assessment |
Token ID | 8922 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
tera | +0.020 |
river | +0.018 |
ograp | +0.016 |
wcsstore | +0.015 |
ppo | +0.015 |
Neg logit contributions | |
alities | -0.018 |
ities | -0.018 |
Reviewed | -0.018 |
Collider | -0.018 |
romeda | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
tera | +0.134 |
river | +0.121 |
ograp | +0.107 |
wcsstore | +0.104 |
ppo | +0.103 |
Neg logit contributions | |
alities | -0.113 |
ities | -0.111 |
Reviewed | -0.111 |
Collider | -0.108 |
romeda | -0.107 |
Token |
|
Token ID | 198 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.001 |
romeda | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
alities | +0.008 |
ities | +0.007 |
Reviewed | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.009 |
river | -0.008 |
ograp | -0.007 |
wcsstore | -0.007 |
ppo | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
tera | +0.038 |
river | +0.034 |
ograp | +0.030 |
wcsstore | +0.030 |
ppo | +0.029 |
Neg logit contributions | |
alities | -0.031 |
Reviewed | -0.031 |
ities | -0.031 |
Collider | -0.030 |
romeda | -0.029 |
Token | were |
Token ID | 547 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
alities | +0.023 |
Reviewed | +0.023 |
ities | +0.023 |
Collider | +0.022 |
romeda | +0.022 |
Neg logit contributions | |
tera | -0.035 |
river | -0.032 |
ograp | -0.028 |
wcsstore | -0.028 |
ppo | -0.027 |
Token | -- |
Token ID | 1377 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
alities | +0.006 |
Reviewed | +0.006 |
ities | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.007 |
river | -0.006 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.009 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.009 |
wcsstore | -0.009 |
ppo | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
tera | +0.010 |
river | +0.009 |
ograp | +0.008 |
wcsstore | +0.008 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.009 |
ities | -0.009 |
Reviewed | -0.009 |
Collider | -0.008 |
romeda | -0.008 |
Token | RF |
Token ID | 32754 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
tera | +0.005 |
river | +0.004 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.013 |
ities | -0.013 |
Reviewed | -0.013 |
Collider | -0.013 |
romeda | -0.013 |
Token | : |
Token ID | 25 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
tera | +0.363 |
river | +0.330 |
ograp | +0.293 |
wcsstore | +0.290 |
ppo | +0.285 |
Neg logit contributions | |
alities | -0.256 |
Reviewed | -0.252 |
ities | -0.252 |
Collider | -0.245 |
romeda | -0.241 |
Token | You |
Token ID | 921 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
tera | +0.007 |
river | +0.006 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.005 |
Token | know |
Token ID | 760 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
alities | +0.028 |
ities | +0.028 |
Reviewed | +0.028 |
Collider | +0.027 |
romeda | +0.026 |
Neg logit contributions | |
tera | -0.040 |
river | -0.036 |
ograp | -0.032 |
wcsstore | -0.032 |
ppo | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
tera | +0.004 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
Reviewed | -0.003 |
ities | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
tera | +0.021 |
river | +0.019 |
ograp | +0.017 |
wcsstore | +0.017 |
ppo | +0.016 |
Neg logit contributions | |
alities | -0.016 |
Reviewed | -0.016 |
ities | -0.016 |
Collider | -0.015 |
romeda | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | However |
Token ID | 4864 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
alities | +0.003 |
ities | +0.003 |
Reviewed | +0.003 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
alities | +0.009 |
ities | +0.009 |
Reviewed | +0.009 |
Collider | +0.009 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.010 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | Crowd |
Token ID | 29452 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | strike |
Token ID | 33069 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
tera | +0.354 |
river | +0.324 |
ograp | +0.286 |
wcsstore | +0.278 |
ppo | +0.275 |
Neg logit contributions | |
alities | -0.262 |
ities | -0.257 |
Reviewed | -0.256 |
Collider | -0.248 |
romeda | -0.245 |
Token | , |
Token ID | 11 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
tera | +0.024 |
river | +0.021 |
ograp | +0.019 |
wcsstore | +0.019 |
ppo | +0.018 |
Neg logit contributions | |
alities | -0.017 |
ities | -0.017 |
Reviewed | -0.017 |
Collider | -0.017 |
romeda | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -8.00e-03 |
Pos logit contributions | |
tera | +0.006 |
river | +0.006 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.004 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | DNC |
Token ID | 17824 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
tera | +0.132 |
river | +0.121 |
ograp | +0.108 |
wcsstore | +0.106 |
ppo | +0.104 |
Neg logit contributions | |
alities | -0.088 |
Reviewed | -0.086 |
ities | -0.086 |
Collider | -0.083 |
romeda | -0.082 |
Token | the |
Token ID | 262 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
alities | +0.005 |
Reviewed | +0.005 |
ities | +0.005 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | forensic |
Token ID | 23953 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
alities | +0.007 |
Reviewed | +0.007 |
ities | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | evidence |
Token ID | 2370 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
tera | +0.050 |
river | +0.045 |
ograp | +0.039 |
wcsstore | +0.039 |
ppo | +0.038 |
Neg logit contributions | |
alities | -0.045 |
ities | -0.044 |
Reviewed | -0.044 |
Collider | -0.043 |
romeda | -0.042 |
Token | found |
Token ID | 1043 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
tera | +0.012 |
river | +0.011 |
ograp | +0.009 |
wcsstore | +0.009 |
ppo | +0.009 |
Neg logit contributions | |
alities | -0.009 |
ities | -0.009 |
Reviewed | -0.009 |
Collider | -0.009 |
romeda | -0.009 |
Token | by |
Token ID | 416 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
alities | +0.013 |
Reviewed | +0.013 |
ities | +0.013 |
Collider | +0.012 |
romeda | +0.012 |
Neg logit contributions | |
tera | -0.016 |
river | -0.015 |
ograp | -0.013 |
wcsstore | -0.013 |
ppo | -0.013 |
Token | Crowd |
Token ID | 29452 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
alities | +0.014 |
ities | +0.014 |
Reviewed | +0.014 |
Collider | +0.014 |
romeda | +0.013 |
Neg logit contributions | |
tera | -0.017 |
river | -0.015 |
ograp | -0.014 |
wcsstore | -0.013 |
ppo | -0.013 |
Token | strike |
Token ID | 33069 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
tera | +0.312 |
river | +0.280 |
ograp | +0.243 |
wcsstore | +0.239 |
ppo | +0.235 |
Neg logit contributions | |
alities | -0.301 |
ities | -0.298 |
Reviewed | -0.297 |
Collider | -0.290 |
romeda | -0.286 |
Token | that |
Token ID | 326 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
tera | +0.017 |
river | +0.015 |
ograp | +0.013 |
wcsstore | +0.013 |
ppo | +0.013 |
Neg logit contributions | |
alities | -0.012 |
ities | -0.012 |
Reviewed | -0.012 |
Collider | -0.012 |
romeda | -0.012 |
Token | fingers |
Token ID | 9353 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
tera | +0.014 |
river | +0.013 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.011 |
Neg logit contributions | |
alities | -0.011 |
ities | -0.011 |
Reviewed | -0.011 |
Collider | -0.010 |
romeda | -0.010 |
Token | two |
Token ID | 734 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
tera | +0.014 |
river | +0.013 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.011 |
Neg logit contributions | |
alities | -0.010 |
ities | -0.010 |
Reviewed | -0.010 |
Collider | -0.009 |
romeda | -0.009 |
Token | groups |
Token ID | 2628 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
tera | +0.042 |
river | +0.038 |
ograp | +0.034 |
wcsstore | +0.033 |
ppo | +0.033 |
Neg logit contributions | |
alities | -0.032 |
Reviewed | -0.031 |
ities | -0.031 |
Collider | -0.030 |
romeda | -0.030 |
Token | powerful |
Token ID | 3665 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
tera | +0.007 |
river | +0.006 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.006 |
Neg logit contributions | |
Reviewed | -0.005 |
alities | -0.005 |
ities | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | Nor |
Token ID | 5414 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
Reviewed | +0.020 |
alities | +0.020 |
ities | +0.020 |
Collider | +0.019 |
romeda | +0.019 |
Neg logit contributions | |
tera | -0.030 |
river | -0.027 |
ograp | -0.024 |
wcsstore | -0.024 |
ppo | -0.023 |
Token | � |
Token ID | 447 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
tera | +0.015 |
river | +0.013 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.011 |
Neg logit contributions | |
alities | -0.013 |
ities | -0.013 |
Reviewed | -0.012 |
Collider | -0.012 |
romeda | -0.012 |
Token | � |
Token ID | 247 |
Feature activation | +6.64e-03 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | e |
Token ID | 68 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | asters |
Token ID | 7060 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
tera | +0.024 |
river | +0.022 |
ograp | +0.019 |
wcsstore | +0.019 |
ppo | +0.019 |
Neg logit contributions | |
alities | -0.020 |
Reviewed | -0.020 |
ities | -0.020 |
Collider | -0.019 |
romeda | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
tera | +0.329 |
river | +0.299 |
ograp | +0.261 |
wcsstore | +0.257 |
ppo | +0.253 |
Neg logit contributions | |
alities | -0.279 |
Reviewed | -0.275 |
ities | -0.273 |
Collider | -0.266 |
romeda | -0.264 |
Token | make |
Token ID | 787 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
tera | +0.030 |
river | +0.028 |
ograp | +0.024 |
wcsstore | +0.024 |
ppo | +0.024 |
Neg logit contributions | |
alities | -0.023 |
Reviewed | -0.022 |
ities | -0.022 |
Collider | -0.022 |
romeda | -0.021 |
Token | driving |
Token ID | 5059 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
tera | +0.052 |
river | +0.048 |
ograp | +0.042 |
wcsstore | +0.041 |
ppo | +0.041 |
Neg logit contributions | |
alities | -0.041 |
Reviewed | -0.040 |
ities | -0.040 |
Collider | -0.039 |
romeda | -0.038 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
tera | +0.093 |
river | +0.085 |
ograp | +0.075 |
wcsstore | +0.074 |
ppo | +0.073 |
Neg logit contributions | |
alities | -0.067 |
ities | -0.066 |
Reviewed | -0.066 |
Collider | -0.064 |
romeda | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | arse |
Token ID | 17208 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
alities | +0.045 |
Reviewed | +0.045 |
ities | +0.045 |
Collider | +0.044 |
romeda | +0.043 |
Neg logit contributions | |
tera | -0.087 |
river | -0.080 |
ograp | -0.072 |
ppo | -0.071 |
wcsstore | -0.070 |
Token | with |
Token ID | 351 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
alities | +0.068 |
Reviewed | +0.067 |
ities | +0.067 |
Collider | +0.065 |
romeda | +0.064 |
Neg logit contributions | |
tera | -0.088 |
river | -0.080 |
ograp | -0.071 |
wcsstore | -0.069 |
ppo | -0.068 |
Token | these |
Token ID | 777 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | guys |
Token ID | 3730 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
alities | +0.021 |
Reviewed | +0.021 |
ities | +0.021 |
Collider | +0.020 |
romeda | +0.020 |
Neg logit contributions | |
tera | -0.025 |
river | -0.023 |
ograp | -0.020 |
wcsstore | -0.020 |
ppo | -0.019 |
Token | [ |
Token ID | 685 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
tera | +0.039 |
river | +0.035 |
ograp | +0.031 |
wcsstore | +0.030 |
ppo | +0.030 |
Neg logit contributions | |
alities | -0.030 |
Reviewed | -0.030 |
ities | -0.030 |
Collider | -0.029 |
romeda | -0.029 |
Token | RF |
Token ID | 32754 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
alities | +0.008 |
ities | +0.008 |
Reviewed | +0.008 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | laughs |
Token ID | 22051 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
tera | +0.339 |
river | +0.305 |
ograp | +0.272 |
wcsstore | +0.265 |
ppo | +0.263 |
Neg logit contributions | |
alities | -0.257 |
Reviewed | -0.253 |
ities | -0.251 |
Collider | -0.244 |
romeda | -0.242 |
Token | ], |
Token ID | 4357 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
tera | +0.053 |
river | +0.048 |
ograp | +0.043 |
wcsstore | +0.041 |
ppo | +0.041 |
Neg logit contributions | |
alities | -0.044 |
Reviewed | -0.043 |
ities | -0.043 |
Collider | -0.042 |
romeda | -0.042 |
Token | Robert |
Token ID | 5199 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
alities | +0.083 |
Reviewed | +0.082 |
ities | +0.081 |
Collider | +0.079 |
romeda | +0.078 |
Neg logit contributions | |
tera | -0.110 |
river | -0.100 |
ograp | -0.089 |
wcsstore | -0.087 |
ppo | -0.086 |
Token | had |
Token ID | 550 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
alities | +0.042 |
Reviewed | +0.042 |
ities | +0.041 |
Collider | +0.040 |
romeda | +0.040 |
Neg logit contributions | |
tera | -0.057 |
river | -0.052 |
ograp | -0.046 |
ppo | -0.045 |
wcsstore | -0.045 |
Token | been |
Token ID | 587 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
alities | +0.016 |
Reviewed | +0.015 |
ities | +0.015 |
Collider | +0.015 |
romeda | +0.015 |
Neg logit contributions | |
tera | -0.019 |
river | -0.018 |
ograp | -0.015 |
wcsstore | -0.015 |
ppo | -0.015 |
Token | get |
Token ID | 651 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
alities | +0.034 |
ities | +0.033 |
Reviewed | +0.033 |
Collider | +0.032 |
romeda | +0.032 |
Neg logit contributions | |
tera | -0.043 |
river | -0.039 |
ograp | -0.034 |
wcsstore | -0.034 |
ppo | -0.033 |
Token | from |
Token ID | 422 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
alities | +0.028 |
Reviewed | +0.028 |
ities | +0.028 |
Collider | +0.027 |
romeda | +0.026 |
Neg logit contributions | |
tera | -0.035 |
river | -0.032 |
ograp | -0.028 |
wcsstore | -0.028 |
ppo | -0.027 |
Token | this |
Token ID | 428 |
Feature activation | +9.76e-03 |
Pos logit contributions | |
tera | +0.034 |
river | +0.031 |
ograp | +0.027 |
wcsstore | +0.027 |
ppo | +0.027 |
Neg logit contributions | |
alities | -0.026 |
ities | -0.025 |
Reviewed | -0.025 |
Collider | -0.025 |
romeda | -0.024 |
Token | sub |
Token ID | 850 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
tera | +0.003 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | wo |
Token ID | 21638 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
alities | +0.061 |
ities | +0.060 |
Reviewed | +0.059 |
Collider | +0.058 |
romeda | +0.057 |
Neg logit contributions | |
tera | -0.070 |
river | -0.063 |
ograp | -0.055 |
wcsstore | -0.054 |
ppo | -0.053 |
Token | ofer |
Token ID | 30288 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
tera | +0.057 |
river | +0.054 |
ograp | +0.050 |
ppo | +0.050 |
wcsstore | +0.049 |
Neg logit contributions | |
alities | -0.005 |
Reviewed | -0.005 |
ities | -0.004 |
Collider | -0.004 |
romeda | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-04 |
Pos logit contributions | |
alities | +0.338 |
ities | +0.333 |
Reviewed | +0.332 |
Collider | +0.324 |
romeda | +0.319 |
Neg logit contributions | |
tera | -0.420 |
river | -0.379 |
ograp | -0.335 |
wcsstore | -0.328 |
ppo | -0.324 |
Token | I |
Token ID | 314 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | have |
Token ID | 423 |
Feature activation | -8.93e-04 |
Pos logit contributions | |
tera | +0.004 |
river | +0.004 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | this |
Token ID | 428 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | sub |
Token ID | 850 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
tera | +0.005 |
river | +0.005 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | I |
Token ID | 314 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | have |
Token ID | 423 |
Feature activation | -8.93e-04 |
Pos logit contributions | |
tera | +0.004 |
river | +0.004 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | this |
Token ID | 428 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | sub |
Token ID | 850 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
tera | +0.005 |
river | +0.005 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | wo |
Token ID | 21638 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
alities | +0.060 |
ities | +0.059 |
Reviewed | +0.059 |
Collider | +0.057 |
romeda | +0.056 |
Neg logit contributions | |
tera | -0.077 |
river | -0.070 |
ograp | -0.062 |
wcsstore | -0.060 |
ppo | -0.060 |
Token | ofer |
Token ID | 30288 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
tera | +0.063 |
river | +0.060 |
ograp | +0.055 |
ppo | +0.055 |
wcsstore | +0.054 |
Neg logit contributions | |
alities | -0.005 |
Reviewed | -0.004 |
ities | -0.004 |
Collider | -0.004 |
romeda | -0.003 |
Token | paired |
Token ID | 20312 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
alities | +0.322 |
ities | +0.317 |
Reviewed | +0.317 |
Collider | +0.308 |
romeda | +0.302 |
Neg logit contributions | |
tera | -0.425 |
river | -0.386 |
ograp | -0.341 |
wcsstore | -0.334 |
ppo | -0.330 |
Token | up |
Token ID | 510 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
tera | +0.043 |
river | +0.039 |
ograp | +0.034 |
wcsstore | +0.034 |
ppo | +0.033 |
Neg logit contributions | |
alities | -0.031 |
Reviewed | -0.031 |
ities | -0.031 |
Collider | -0.030 |
romeda | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | Martin |
Token ID | 5780 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
alities | +0.007 |
ities | +0.007 |
Reviewed | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.007 |
Token | Log |
Token ID | 5972 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
tera | +0.018 |
river | +0.016 |
ograp | +0.014 |
wcsstore | +0.014 |
ppo | +0.014 |
Neg logit contributions | |
alities | -0.012 |
ities | -0.012 |
Reviewed | -0.012 |
Collider | -0.012 |
romeda | -0.011 |
Token | time |
Token ID | 640 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
tera | +0.038 |
river | +0.034 |
ograp | +0.030 |
wcsstore | +0.029 |
ppo | +0.029 |
Neg logit contributions | |
alities | -0.034 |
ities | -0.033 |
Reviewed | -0.033 |
Collider | -0.032 |
romeda | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
tera | +0.023 |
river | +0.021 |
ograp | +0.018 |
wcsstore | +0.018 |
ppo | +0.018 |
Neg logit contributions | |
alities | -0.017 |
Reviewed | -0.017 |
ities | -0.017 |
Collider | -0.017 |
romeda | -0.016 |
Token | this |
Token ID | 428 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | sub |
Token ID | 850 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
tera | +0.007 |
river | +0.006 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.005 |
ities | -0.005 |
Reviewed | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | wo |
Token ID | 21638 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
alities | +0.055 |
ities | +0.054 |
Reviewed | +0.054 |
Collider | +0.053 |
romeda | +0.052 |
Neg logit contributions | |
tera | -0.069 |
river | -0.062 |
ograp | -0.055 |
wcsstore | -0.054 |
ppo | -0.053 |
Token | ofer |
Token ID | 30288 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
tera | +0.054 |
river | +0.051 |
ograp | +0.048 |
ppo | +0.047 |
obic | +0.047 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.005 |
ities | -0.005 |
Collider | -0.004 |
romeda | -0.004 |
Token | is |
Token ID | 318 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
alities | +0.320 |
ities | +0.316 |
Reviewed | +0.315 |
Collider | +0.307 |
romeda | +0.302 |
Neg logit contributions | |
tera | -0.423 |
river | -0.383 |
ograp | -0.340 |
wcsstore | -0.335 |
ppo | -0.329 |
Token | worth |
Token ID | 2861 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
tera | +0.005 |
river | +0.005 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
Reviewed | -0.004 |
ities | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | every |
Token ID | 790 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
alities | +0.089 |
ities | +0.088 |
Reviewed | +0.088 |
Collider | +0.086 |
romeda | +0.084 |
Neg logit contributions | |
tera | -0.098 |
river | -0.087 |
ograp | -0.076 |
wcsstore | -0.076 |
ppo | -0.074 |
Token | penny |
Token ID | 26369 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
tera | +0.055 |
river | +0.050 |
ograp | +0.044 |
wcsstore | +0.043 |
ppo | +0.042 |
Neg logit contributions | |
alities | -0.043 |
ities | -0.043 |
Reviewed | -0.043 |
Collider | -0.042 |
romeda | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -4.17e-03 |
Pos logit contributions | |
tera | +0.064 |
river | +0.058 |
ograp | +0.051 |
wcsstore | +0.050 |
ppo | +0.049 |
Neg logit contributions | |
alities | -0.054 |
ities | -0.053 |
Reviewed | -0.053 |
Collider | -0.052 |
romeda | -0.051 |
Token | activated |
Token ID | 13906 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
tera | +0.042 |
river | +0.038 |
ograp | +0.034 |
wcsstore | +0.033 |
ppo | +0.033 |
Neg logit contributions | |
alities | -0.029 |
ities | -0.028 |
Reviewed | -0.028 |
Collider | -0.027 |
romeda | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
alities | +0.042 |
ities | +0.042 |
Reviewed | +0.042 |
Collider | +0.040 |
romeda | +0.040 |
Neg logit contributions | |
tera | -0.052 |
river | -0.047 |
ograp | -0.041 |
wcsstore | -0.041 |
ppo | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +4.68e-02 |
Pos logit contributions | |
tera | +0.006 |
river | +0.006 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.005 |
ities | -0.005 |
Reviewed | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -6.44e-04 |
Pos logit contributions | |
tera | +0.012 |
river | +0.011 |
ograp | +0.010 |
wcsstore | +0.010 |
ppo | +0.010 |
Neg logit contributions | |
alities | -0.010 |
ities | -0.010 |
Reviewed | -0.010 |
Collider | -0.010 |
romeda | -0.010 |
Token | Krist |
Token ID | 40756 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | ofer |
Token ID | 30288 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
tera | +0.026 |
river | +0.023 |
ograp | +0.021 |
wcsstore | +0.020 |
ppo | +0.020 |
Neg logit contributions | |
alities | -0.019 |
Reviewed | -0.019 |
ities | -0.018 |
Collider | -0.018 |
romeda | -0.018 |
Token | B |
Token ID | 347 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
alities | +0.303 |
Reviewed | +0.299 |
ities | +0.298 |
Collider | +0.290 |
romeda | +0.285 |
Neg logit contributions | |
tera | -0.440 |
river | -0.400 |
ograp | -0.356 |
wcsstore | -0.351 |
ppo | -0.346 |
Token | ouch |
Token ID | 7673 |
Feature activation | +8.54e-03 |
Pos logit contributions | |
alities | +0.017 |
Reviewed | +0.017 |
ities | +0.016 |
Collider | +0.016 |
romeda | +0.016 |
Neg logit contributions | |
tera | -0.017 |
river | -0.016 |
ograp | -0.014 |
wcsstore | -0.013 |
ppo | -0.013 |
Token | ard |
Token ID | 446 |
Feature activation | -9.19e-02 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -4.11e-03 |
Pos logit contributions | |
alities | +0.019 |
ities | +0.019 |
Reviewed | +0.019 |
Collider | +0.019 |
romeda | +0.018 |
Neg logit contributions | |
tera | -0.025 |
river | -0.023 |
ograp | -0.020 |
wcsstore | -0.020 |
ppo | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
alities | +0.031 |
ities | +0.030 |
Reviewed | +0.030 |
Collider | +0.029 |
romeda | +0.029 |
Neg logit contributions | |
tera | -0.032 |
river | -0.029 |
ograp | -0.025 |
wcsstore | -0.025 |
ppo | -0.024 |
Token | The |
Token ID | 383 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
tera | +0.031 |
river | +0.028 |
ograp | +0.024 |
wcsstore | +0.024 |
ppo | +0.024 |
Neg logit contributions | |
alities | -0.029 |
ities | -0.029 |
Reviewed | -0.029 |
Collider | -0.028 |
romeda | -0.027 |
Token | best |
Token ID | 1266 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
tera | +0.030 |
river | +0.027 |
ograp | +0.024 |
wcsstore | +0.023 |
ppo | +0.023 |
Neg logit contributions | |
alities | -0.023 |
ities | -0.023 |
Reviewed | -0.023 |
Collider | -0.022 |
romeda | -0.022 |
Token | sub |
Token ID | 850 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
alities | +0.016 |
ities | +0.015 |
Reviewed | +0.015 |
Collider | +0.015 |
romeda | +0.015 |
Neg logit contributions | |
tera | -0.020 |
river | -0.018 |
ograp | -0.016 |
wcsstore | -0.016 |
ppo | -0.016 |
Token | wo |
Token ID | 21638 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
alities | +0.059 |
ities | +0.058 |
Reviewed | +0.058 |
Collider | +0.057 |
romeda | +0.056 |
Neg logit contributions | |
tera | -0.069 |
river | -0.062 |
ograp | -0.054 |
wcsstore | -0.053 |
ppo | -0.052 |
Token | ofer |
Token ID | 30288 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
tera | +0.053 |
river | +0.050 |
ograp | +0.047 |
ppo | +0.047 |
obic | +0.046 |
Neg logit contributions | |
alities | -0.007 |
Reviewed | -0.006 |
Collider | -0.006 |
ities | -0.005 |
romeda | -0.005 |
Token | ever |
Token ID | 1683 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
alities | +0.338 |
ities | +0.333 |
Reviewed | +0.332 |
Collider | +0.323 |
romeda | +0.319 |
Neg logit contributions | |
tera | -0.405 |
river | -0.366 |
ograp | -0.321 |
wcsstore | -0.316 |
ppo | -0.312 |
Token | !!! |
Token ID | 10185 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
tera | +0.117 |
river | +0.106 |
ograp | +0.093 |
wcsstore | +0.091 |
ppo | +0.090 |
Neg logit contributions | |
alities | -0.097 |
ities | -0.096 |
Reviewed | -0.096 |
Collider | -0.093 |
romeda | -0.092 |
Token | So |
Token ID | 1406 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
alities | +0.114 |
ities | +0.113 |
Reviewed | +0.112 |
Collider | +0.109 |
romeda | +0.108 |
Neg logit contributions | |
tera | -0.131 |
river | -0.117 |
ograp | -0.103 |
wcsstore | -0.101 |
ppo | -0.100 |
Token | I |
Token ID | 314 |
Feature activation | -7.76e-03 |
Pos logit contributions | |
alities | +0.035 |
ities | +0.034 |
Reviewed | +0.034 |
Collider | +0.033 |
romeda | +0.033 |
Neg logit contributions | |
tera | -0.050 |
river | -0.046 |
ograp | -0.041 |
ppo | -0.040 |
wcsstore | -0.040 |
Token | bought |
Token ID | 5839 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | legend |
Token ID | 8177 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
alities | +0.000 |
Reviewed | +0.000 |
ities | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | ," |
Token ID | 553 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
tera | +0.156 |
river | +0.141 |
ograp | +0.126 |
wcsstore | +0.121 |
obic | +0.120 |
Neg logit contributions | |
alities | -0.128 |
Reviewed | -0.127 |
ities | -0.126 |
Collider | -0.124 |
romeda | -0.120 |
Token | U |
Token ID | 471 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
alities | +0.019 |
ities | +0.019 |
Reviewed | +0.019 |
Collider | +0.018 |
romeda | +0.018 |
Neg logit contributions | |
tera | -0.026 |
river | -0.024 |
ograp | -0.021 |
wcsstore | -0.021 |
ppo | -0.021 |
Token | men |
Token ID | 3653 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
alities | +0.032 |
Reviewed | +0.032 |
ities | +0.032 |
Collider | +0.031 |
romeda | +0.030 |
Neg logit contributions | |
tera | -0.039 |
river | -0.035 |
ograp | -0.031 |
wcsstore | -0.030 |
ppo | -0.030 |
Token | h |
Token ID | 71 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
alities | +0.125 |
Reviewed | +0.124 |
ities | +0.123 |
Collider | +0.120 |
romeda | +0.118 |
Neg logit contributions | |
tera | -0.154 |
river | -0.139 |
ograp | -0.122 |
wcsstore | -0.120 |
ppo | -0.119 |
Token | ofer |
Token ID | 30288 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
alities | +0.047 |
Reviewed | +0.047 |
ities | +0.046 |
Collider | +0.046 |
romeda | +0.044 |
Neg logit contributions | |
tera | -0.062 |
river | -0.056 |
ograp | -0.050 |
ppo | -0.049 |
wcsstore | -0.048 |
Token | says |
Token ID | 1139 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
alities | +0.319 |
ities | +0.315 |
Reviewed | +0.315 |
Collider | +0.306 |
romeda | +0.301 |
Neg logit contributions | |
tera | -0.423 |
river | -0.383 |
ograp | -0.339 |
wcsstore | -0.334 |
ppo | -0.329 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
tera | +0.008 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.007 |
ities | -0.007 |
Reviewed | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | old |
Token ID | 727 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
tera | +0.051 |
river | +0.046 |
ograp | +0.040 |
wcsstore | +0.039 |
ppo | +0.039 |
Neg logit contributions | |
Reviewed | -0.042 |
alities | -0.042 |
Collider | -0.042 |
ities | -0.041 |
romeda | -0.040 |
Token | K |
Token ID | 509 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
alities | +0.080 |
ities | +0.079 |
Reviewed | +0.078 |
Collider | +0.076 |
romeda | +0.075 |
Neg logit contributions | |
tera | -0.110 |
river | -0.100 |
ograp | -0.089 |
wcsstore | -0.088 |
ppo | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
alities | +0.032 |
ities | +0.031 |
Reviewed | +0.031 |
Collider | +0.030 |
romeda | +0.030 |
Neg logit contributions | |
tera | -0.039 |
river | -0.035 |
ograp | -0.031 |
wcsstore | -0.031 |
ppo | -0.030 |
Token | H |
Token ID | 367 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
tera | +0.005 |
river | +0.005 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | och |
Token ID | 5374 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
tera | +0.023 |
river | +0.021 |
ograp | +0.018 |
wcsstore | +0.018 |
ppo | +0.018 |
Neg logit contributions | |
alities | -0.020 |
Reviewed | -0.019 |
ities | -0.019 |
Collider | -0.019 |
romeda | -0.019 |
Token | schild |
Token ID | 35058 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.003 |
ppo | +0.003 |
wcsstore | +0.003 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | Foundation |
Token ID | 5693 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
alities | +0.295 |
ities | +0.290 |
Reviewed | +0.290 |
Collider | +0.282 |
romeda | +0.278 |
Neg logit contributions | |
tera | -0.375 |
river | -0.339 |
ograp | -0.299 |
wcsstore | -0.294 |
ppo | -0.290 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e-03 |
Pos logit contributions | |
tera | +0.137 |
river | +0.124 |
ograp | +0.109 |
wcsstore | +0.107 |
ppo | +0.105 |
Neg logit contributions | |
alities | -0.114 |
ities | -0.112 |
Reviewed | -0.112 |
Collider | -0.109 |
romeda | -0.108 |
Token |
|
Token ID | 198 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | Joy |
Token ID | 41338 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | ce |
Token ID | 344 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
alities | +0.027 |
ities | +0.027 |
Reviewed | +0.027 |
Collider | +0.026 |
romeda | +0.025 |
Neg logit contributions | |
tera | -0.049 |
river | -0.045 |
ograp | -0.040 |
wcsstore | -0.040 |
ppo | -0.039 |
Token | people |
Token ID | 661 |
Feature activation | -2.31e-04 |
Pos logit contributions | |
tera | +0.018 |
river | +0.016 |
ograp | +0.014 |
wcsstore | +0.014 |
ppo | +0.014 |
Neg logit contributions | |
alities | -0.013 |
Reviewed | -0.012 |
ities | -0.012 |
Collider | -0.012 |
romeda | -0.012 |
Token | would |
Token ID | 561 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | be |
Token ID | 307 |
Feature activation | +1.61e-04 |
Pos logit contributions | |
tera | +0.012 |
river | +0.011 |
ograp | +0.010 |
wcsstore | +0.010 |
ppo | +0.009 |
Neg logit contributions | |
alities | -0.009 |
ities | -0.009 |
Reviewed | -0.009 |
Collider | -0.008 |
romeda | -0.008 |
Token | cum |
Token ID | 10973 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
tera | +0.000 |
river | +0.000 |
ograp | +0.000 |
wcsstore | +0.000 |
ppo | +0.000 |
Neg logit contributions | |
alities | -0.000 |
Reviewed | -0.000 |
ities | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | ul |
Token ID | 377 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
tera | +0.062 |
river | +0.056 |
ograp | +0.050 |
wcsstore | +0.048 |
ppo | +0.048 |
Neg logit contributions | |
alities | -0.045 |
Reviewed | -0.044 |
ities | -0.044 |
Collider | -0.043 |
romeda | -0.042 |
Token | atively |
Token ID | 9404 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
alities | +0.012 |
Reviewed | +0.011 |
ities | +0.011 |
Collider | +0.010 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.118 |
river | -0.111 |
ograp | -0.103 |
wcsstore | -0.102 |
ppo | -0.101 |
Token | sharing |
Token ID | 7373 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
alities | +0.265 |
Reviewed | +0.261 |
ities | +0.261 |
Collider | +0.254 |
romeda | +0.249 |
Neg logit contributions | |
tera | -0.396 |
river | -0.361 |
ograp | -0.322 |
wcsstore | -0.317 |
ppo | -0.313 |
Token | 1 |
Token ID | 352 |
Feature activation | -9.99e-02 |
Pos logit contributions | |
alities | +0.035 |
Reviewed | +0.035 |
ities | +0.035 |
Collider | +0.034 |
romeda | +0.033 |
Neg logit contributions | |
tera | -0.046 |
river | -0.042 |
ograp | -0.037 |
wcsstore | -0.037 |
ppo | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
alities | +0.021 |
ities | +0.021 |
Reviewed | +0.021 |
Collider | +0.020 |
romeda | +0.020 |
Neg logit contributions | |
tera | -0.028 |
river | -0.025 |
ograp | -0.022 |
wcsstore | -0.022 |
ppo | -0.021 |
Token | 024 |
Token ID | 40839 |
Feature activation | +6.56e-02 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | times |
Token ID | 1661 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
tera | +0.018 |
river | +0.016 |
ograp | +0.014 |
wcsstore | +0.014 |
ppo | +0.014 |
Neg logit contributions | |
alities | -0.014 |
ities | -0.014 |
Reviewed | -0.014 |
Collider | -0.014 |
romeda | -0.013 |
Token | manga |
Token ID | 15911 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | series |
Token ID | 2168 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
alities | +0.004 |
Reviewed | +0.004 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | have |
Token ID | 423 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
tera | +0.036 |
river | +0.033 |
ograp | +0.029 |
wcsstore | +0.029 |
ppo | +0.029 |
Neg logit contributions | |
alities | -0.024 |
Reviewed | -0.024 |
ities | -0.024 |
Collider | -0.023 |
romeda | -0.023 |
Token | cum |
Token ID | 10973 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.004 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | ul |
Token ID | 377 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
tera | +0.068 |
river | +0.062 |
ograp | +0.056 |
wcsstore | +0.054 |
ppo | +0.054 |
Neg logit contributions | |
alities | -0.042 |
ities | -0.041 |
Reviewed | -0.041 |
Collider | -0.040 |
romeda | -0.039 |
Token | atively |
Token ID | 9404 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
alities | +0.013 |
Reviewed | +0.012 |
ities | +0.012 |
Collider | +0.011 |
romeda | +0.010 |
Neg logit contributions | |
tera | -0.133 |
river | -0.125 |
ograp | -0.117 |
wcsstore | -0.116 |
ppo | -0.114 |
Token | sold |
Token ID | 2702 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
alities | +0.265 |
Reviewed | +0.261 |
ities | +0.260 |
Collider | +0.253 |
romeda | +0.249 |
Neg logit contributions | |
tera | -0.395 |
river | -0.360 |
ograp | -0.321 |
wcsstore | -0.316 |
ppo | -0.311 |
Token | over |
Token ID | 625 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
alities | +0.009 |
ities | +0.009 |
Reviewed | +0.009 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.013 |
river | -0.012 |
ograp | -0.011 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | 22 |
Token ID | 2534 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
alities | +0.029 |
ities | +0.029 |
Reviewed | +0.029 |
Collider | +0.028 |
romeda | +0.028 |
Neg logit contributions | |
tera | -0.040 |
river | -0.036 |
ograp | -0.032 |
wcsstore | -0.032 |
ppo | -0.031 |
Token | million |
Token ID | 1510 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
tera | +0.076 |
river | +0.068 |
ograp | +0.060 |
wcsstore | +0.059 |
ppo | +0.058 |
Neg logit contributions | |
alities | -0.065 |
ities | -0.064 |
Reviewed | -0.064 |
Collider | -0.062 |
romeda | -0.061 |
Token | copies |
Token ID | 9088 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
tera | +0.043 |
river | +0.038 |
ograp | +0.032 |
wcsstore | +0.032 |
ppo | +0.031 |
Neg logit contributions | |
alities | -0.048 |
ities | -0.047 |
Reviewed | -0.047 |
Collider | -0.046 |
romeda | -0.046 |
Token | recommended |
Token ID | 7151 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
alities | +0.003 |
ities | +0.003 |
Reviewed | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
alities | +0.028 |
ities | +0.027 |
Reviewed | +0.027 |
Collider | +0.027 |
romeda | +0.026 |
Neg logit contributions | |
tera | -0.035 |
river | -0.032 |
ograp | -0.028 |
wcsstore | -0.028 |
ppo | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
tera | +0.008 |
river | +0.007 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.007 |
ities | -0.007 |
Reviewed | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | even |
Token ID | 772 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | tent |
Token ID | 11105 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
tera | +0.123 |
river | +0.112 |
ograp | +0.098 |
wcsstore | +0.096 |
ppo | +0.095 |
Neg logit contributions | |
alities | -0.101 |
Reviewed | -0.100 |
ities | -0.100 |
Collider | -0.097 |
romeda | -0.095 |
Token | atively |
Token ID | 9404 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
alities | +0.015 |
ities | +0.014 |
Reviewed | +0.014 |
Collider | +0.012 |
romeda | +0.011 |
Neg logit contributions | |
tera | -0.151 |
river | -0.142 |
ograp | -0.133 |
wcsstore | -0.131 |
ppo | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
alities | +0.314 |
Reviewed | +0.309 |
ities | +0.309 |
Collider | +0.301 |
romeda | +0.297 |
Neg logit contributions | |
tera | -0.339 |
river | -0.304 |
ograp | -0.266 |
wcsstore | -0.261 |
ppo | -0.256 |
Token | or |
Token ID | 393 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.007 |
ities | -0.007 |
Reviewed | -0.007 |
Collider | -0.006 |
romeda | -0.006 |
Token | even |
Token ID | 772 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
tera | +0.014 |
river | +0.012 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.010 |
Neg logit contributions | |
alities | -0.012 |
Reviewed | -0.012 |
ities | -0.012 |
Collider | -0.011 |
romeda | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
tera | +0.127 |
river | +0.115 |
ograp | +0.102 |
wcsstore | +0.100 |
ppo | +0.099 |
Neg logit contributions | |
alities | -0.095 |
Reviewed | -0.094 |
ities | -0.094 |
Collider | -0.091 |
romeda | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
tera | +0.017 |
river | +0.015 |
ograp | +0.013 |
wcsstore | +0.013 |
ppo | +0.013 |
Neg logit contributions | |
alities | -0.012 |
Reviewed | -0.012 |
ities | -0.012 |
Collider | -0.012 |
romeda | -0.012 |
Token | Laser |
Token ID | 23222 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
alities | +0.004 |
Reviewed | +0.004 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.004 |
river | -0.004 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | Inter |
Token ID | 4225 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
tera | +0.004 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.004 |
ities | -0.004 |
Reviewed | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | fer |
Token ID | 2232 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
tera | +0.121 |
river | +0.110 |
ograp | +0.098 |
wcsstore | +0.096 |
ppo | +0.095 |
Neg logit contributions | |
alities | -0.087 |
ities | -0.086 |
Reviewed | -0.086 |
Collider | -0.083 |
romeda | -0.082 |
Token | ometer |
Token ID | 15635 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
tera | +0.006 |
river | +0.005 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.010 |
ities | -0.010 |
Reviewed | -0.010 |
Collider | -0.010 |
romeda | -0.010 |
Token | Grav |
Token ID | 32599 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
tera | +0.108 |
river | +0.098 |
ograp | +0.087 |
wcsstore | +0.086 |
ppo | +0.084 |
Neg logit contributions | |
alities | -0.074 |
ities | -0.073 |
Reviewed | -0.073 |
Collider | -0.070 |
romeda | -0.069 |
Token | itational |
Token ID | 22181 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Reviewed | +0.003 |
alities | +0.003 |
ities | +0.002 |
romeda | +0.002 |
Collider | +0.002 |
Neg logit contributions | |
tera | -0.033 |
river | -0.031 |
ograp | -0.029 |
onica | -0.029 |
wcsstore | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
alities | +0.281 |
Reviewed | +0.274 |
ities | +0.271 |
Collider | +0.260 |
romeda | +0.259 |
Neg logit contributions | |
tera | -0.372 |
river | -0.338 |
ograp | -0.298 |
ppo | -0.290 |
wcsstore | -0.288 |
Token | wave |
Token ID | 19204 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
ppo | -0.003 |
wcsstore | -0.003 |
Token | Observatory |
Token ID | 25758 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
alities | +0.010 |
ities | +0.010 |
Reviewed | +0.010 |
Collider | +0.010 |
romeda | +0.010 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | ( |
Token ID | 357 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
tera | +0.050 |
river | +0.045 |
ograp | +0.040 |
wcsstore | +0.039 |
ppo | +0.039 |
Neg logit contributions | |
alities | -0.040 |
Reviewed | -0.040 |
ities | -0.040 |
Collider | -0.039 |
romeda | -0.038 |
Token | L |
Token ID | 43 |
Feature activation | +9.50e-02 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
tera | +0.042 |
river | +0.038 |
ograp | +0.033 |
wcsstore | +0.033 |
ppo | +0.032 |
Neg logit contributions | |
alities | -0.031 |
ities | -0.030 |
Reviewed | -0.030 |
Collider | -0.030 |
romeda | -0.029 |
Token | fundamental |
Token ID | 7531 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
alities | +0.011 |
ities | +0.011 |
Reviewed | +0.011 |
Collider | +0.011 |
romeda | +0.011 |
Neg logit contributions | |
tera | -0.016 |
river | -0.014 |
ograp | -0.013 |
wcsstore | -0.012 |
ppo | -0.012 |
Token | measurement |
Token ID | 15558 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
alities | +0.080 |
Reviewed | +0.079 |
ities | +0.079 |
Collider | +0.077 |
romeda | +0.076 |
Neg logit contributions | |
tera | -0.115 |
river | -0.105 |
ograp | -0.093 |
wcsstore | -0.092 |
ppo | -0.090 |
Token | ambig |
Token ID | 18203 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
alities | +0.075 |
ities | +0.074 |
Reviewed | +0.073 |
Collider | +0.071 |
romeda | +0.070 |
Neg logit contributions | |
tera | -0.103 |
river | -0.093 |
ograp | -0.083 |
wcsstore | -0.082 |
ppo | -0.080 |
Token | u |
Token ID | 84 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Reviewed | +0.002 |
alities | +0.002 |
Collider | +0.002 |
ities | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | ities |
Token ID | 871 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Reviewed | +0.005 |
Collider | +0.003 |
alities | +0.003 |
romeda | +0.002 |
hears | +0.001 |
Neg logit contributions | |
tera | -0.104 |
river | -0.098 |
ograp | -0.092 |
wcsstore | -0.090 |
ppo | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
alities | +0.279 |
Reviewed | +0.276 |
ities | +0.275 |
Collider | +0.268 |
romeda | +0.264 |
Neg logit contributions | |
tera | -0.360 |
river | -0.325 |
ograp | -0.287 |
wcsstore | -0.283 |
ppo | -0.279 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
alities | +0.003 |
ities | +0.003 |
Reviewed | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | Although |
Token ID | 7003 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
tera | +0.028 |
river | +0.026 |
ograp | +0.023 |
wcsstore | +0.022 |
ppo | +0.022 |
Neg logit contributions | |
alities | -0.021 |
Reviewed | -0.021 |
ities | -0.021 |
Collider | -0.020 |
romeda | -0.020 |
Token | Priv |
Token ID | 9243 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | ile |
Token ID | 576 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
tera | +0.014 |
river | +0.012 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.011 |
Neg logit contributions | |
alities | -0.011 |
Reviewed | -0.011 |
ities | -0.011 |
Collider | -0.011 |
romeda | -0.011 |
Token | ges |
Token ID | 3212 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
alities | +0.016 |
ities | +0.016 |
Reviewed | +0.016 |
Collider | +0.015 |
romeda | +0.015 |
Neg logit contributions | |
tera | -0.022 |
river | -0.020 |
ograp | -0.017 |
wcsstore | -0.017 |
ppo | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
alities | +0.029 |
ities | +0.028 |
Reviewed | +0.028 |
Collider | +0.027 |
romeda | +0.027 |
Neg logit contributions | |
tera | -0.040 |
river | -0.036 |
ograp | -0.032 |
wcsstore | -0.032 |
ppo | -0.031 |
Token | Immun |
Token ID | 25445 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
alities | +0.006 |
ities | +0.006 |
Reviewed | +0.006 |
Collider | +0.006 |
romeda | +0.006 |
Neg logit contributions | |
tera | -0.007 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token | ities |
Token ID | 871 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
tera | +0.073 |
river | +0.069 |
ograp | +0.065 |
wcsstore | +0.064 |
ppo | +0.064 |
Neg logit contributions | |
alities | -0.000 |
Reviewed | -0.000 |
ities | -0.000 |
Collider | +0.001 |
romeda | +0.001 |
Token | of |
Token ID | 286 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
alities | +0.273 |
ities | +0.269 |
Reviewed | +0.266 |
Collider | +0.260 |
romeda | +0.256 |
Neg logit contributions | |
tera | -0.368 |
river | -0.333 |
ograp | -0.296 |
wcsstore | -0.292 |
ppo | -0.286 |
Token | Citizens |
Token ID | 18029 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.004 |
river | -0.004 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
tera | +0.081 |
river | +0.073 |
ograp | +0.065 |
wcsstore | +0.064 |
ppo | +0.063 |
Neg logit contributions | |
alities | -0.064 |
ities | -0.063 |
Reviewed | -0.063 |
Collider | -0.061 |
romeda | -0.060 |
Token | the |
Token ID | 262 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
tera | +0.010 |
river | +0.009 |
ograp | +0.008 |
wcsstore | +0.008 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.007 |
ities | -0.007 |
Reviewed | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | several |
Token ID | 1811 |
Feature activation | +9.96e-02 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.007 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token | � |
Token ID | 228 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
tera | +0.122 |
river | +0.109 |
ograp | +0.093 |
wcsstore | +0.091 |
ppo | +0.090 |
Neg logit contributions | |
alities | -0.130 |
Reviewed | -0.129 |
ities | -0.129 |
Collider | -0.126 |
romeda | -0.124 |
Token | ς |
Token ID | 35558 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
tera | +0.035 |
river | +0.032 |
ograp | +0.028 |
wcsstore | +0.028 |
ppo | +0.028 |
Neg logit contributions | |
alities | -0.021 |
ities | -0.020 |
Reviewed | -0.020 |
Collider | -0.020 |
romeda | -0.019 |
Token | ( |
Token ID | 357 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
alities | +0.165 |
ities | +0.162 |
Reviewed | +0.162 |
Collider | +0.158 |
romeda | +0.155 |
Neg logit contributions | |
tera | -0.212 |
river | -0.192 |
ograp | -0.170 |
wcsstore | -0.167 |
ppo | -0.164 |
Token | Ant |
Token ID | 13217 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
alities | +0.008 |
ities | +0.007 |
Reviewed | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.007 |
Token | iqu |
Token ID | 1557 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
tera | +0.048 |
river | +0.043 |
ograp | +0.037 |
wcsstore | +0.036 |
ppo | +0.036 |
Neg logit contributions | |
alities | -0.053 |
ities | -0.053 |
Reviewed | -0.053 |
Collider | -0.051 |
romeda | -0.051 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
tera | +0.125 |
river | +0.116 |
ograp | +0.106 |
wcsstore | +0.105 |
ppo | +0.103 |
Neg logit contributions | |
alities | -0.048 |
ities | -0.047 |
Reviewed | -0.047 |
Collider | -0.045 |
romeda | -0.044 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
alities | +0.268 |
ities | +0.264 |
Reviewed | +0.264 |
Collider | +0.256 |
romeda | +0.252 |
Neg logit contributions | |
tera | -0.368 |
river | -0.334 |
ograp | -0.297 |
wcsstore | -0.292 |
ppo | -0.288 |
Token | the |
Token ID | 262 |
Feature activation | -5.46e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | Jews |
Token ID | 6771 |
Feature activation | +7.04e-02 |
Pos logit contributions | |
alities | +0.011 |
ities | +0.011 |
Reviewed | +0.011 |
Collider | +0.011 |
romeda | +0.010 |
Neg logit contributions | |
tera | -0.016 |
river | -0.014 |
ograp | -0.013 |
wcsstore | -0.012 |
ppo | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
tera | +0.021 |
river | +0.019 |
ograp | +0.017 |
wcsstore | +0.016 |
ppo | +0.016 |
Neg logit contributions | |
alities | -0.014 |
ities | -0.014 |
Reviewed | -0.014 |
Collider | -0.013 |
romeda | -0.013 |
Token | : |
Token ID | 25 |
Feature activation | -7.24e-02 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | few |
Token ID | 1178 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
tera | +0.005 |
river | +0.005 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
Reviewed | -0.004 |
ities | -0.004 |
Collider | -0.003 |
romeda | -0.003 |
Token | other |
Token ID | 584 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
alities | +0.031 |
ities | +0.030 |
Reviewed | +0.030 |
Collider | +0.029 |
romeda | +0.029 |
Neg logit contributions | |
tera | -0.039 |
river | -0.035 |
ograp | -0.031 |
wcsstore | -0.031 |
ppo | -0.030 |
Token | fr |
Token ID | 1216 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
alities | +0.015 |
Reviewed | +0.014 |
ities | +0.014 |
Collider | +0.014 |
romeda | +0.014 |
Neg logit contributions | |
tera | -0.018 |
river | -0.016 |
ograp | -0.014 |
wcsstore | -0.014 |
ppo | -0.014 |
Token | atern |
Token ID | 9205 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
tera | +0.129 |
river | +0.116 |
ograp | +0.102 |
wcsstore | +0.100 |
ppo | +0.098 |
Neg logit contributions | |
alities | -0.114 |
Reviewed | -0.113 |
ities | -0.112 |
Collider | -0.110 |
romeda | -0.108 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Reviewed | +0.000 |
alities | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
ities | +0.000 |
Neg logit contributions | |
tera | -0.014 |
river | -0.013 |
ograp | -0.012 |
wcsstore | -0.012 |
ppo | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
alities | +0.272 |
Reviewed | +0.268 |
ities | +0.267 |
Collider | +0.260 |
romeda | +0.256 |
Neg logit contributions | |
tera | -0.363 |
river | -0.329 |
ograp | -0.291 |
wcsstore | -0.287 |
ppo | -0.283 |
Token | also |
Token ID | 635 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
alities | +0.014 |
Reviewed | +0.014 |
ities | +0.014 |
Collider | +0.014 |
romeda | +0.014 |
Neg logit contributions | |
tera | -0.019 |
river | -0.017 |
ograp | -0.015 |
wcsstore | -0.015 |
ppo | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
alities | +0.005 |
Reviewed | +0.005 |
ities | +0.005 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
tera | +0.012 |
river | +0.011 |
ograp | +0.009 |
wcsstore | +0.009 |
ppo | +0.009 |
Neg logit contributions | |
alities | -0.008 |
ities | -0.008 |
Reviewed | -0.008 |
Collider | -0.008 |
romeda | -0.007 |
Token | similar |
Token ID | 2092 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
tera | +0.043 |
river | +0.039 |
ograp | +0.035 |
wcsstore | +0.035 |
ppo | +0.034 |
Neg logit contributions | |
alities | -0.030 |
Reviewed | -0.030 |
ities | -0.029 |
Collider | -0.029 |
romeda | -0.028 |
Token | anthrop |
Token ID | 17911 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
tera | +0.004 |
river | +0.004 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
Reviewed | -0.003 |
ities | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | omorphic |
Token ID | 46374 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
tera | +0.105 |
river | +0.091 |
ograp | +0.075 |
wcsstore | +0.074 |
ppo | +0.072 |
Neg logit contributions | |
alities | -0.154 |
ities | -0.153 |
Reviewed | -0.152 |
Collider | -0.149 |
romeda | -0.147 |
Token | div |
Token ID | 2659 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
tera | +0.142 |
river | +0.128 |
ograp | +0.114 |
wcsstore | +0.113 |
ppo | +0.111 |
Neg logit contributions | |
alities | -0.100 |
Reviewed | -0.100 |
ities | -0.099 |
Collider | -0.097 |
romeda | -0.095 |
Token | in |
Token ID | 259 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
tera | +0.179 |
river | +0.161 |
ograp | +0.143 |
wcsstore | +0.140 |
ppo | +0.138 |
Neg logit contributions | |
alities | -0.138 |
Reviewed | -0.137 |
ities | -0.136 |
Collider | -0.134 |
romeda | -0.131 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.003 |
Reviewed | +0.002 |
Collider | -0.000 |
romeda | -0.001 |
Neg logit contributions | |
tera | -0.169 |
river | -0.160 |
ograp | -0.150 |
wcsstore | -0.149 |
ppo | -0.148 |
Token | became |
Token ID | 2627 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
alities | +0.267 |
Reviewed | +0.264 |
ities | +0.263 |
Collider | +0.257 |
romeda | +0.252 |
Neg logit contributions | |
tera | -0.367 |
river | -0.333 |
ograp | -0.296 |
wcsstore | -0.291 |
ppo | -0.287 |
Token | unacceptable |
Token ID | 18010 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
tera | +0.031 |
river | +0.028 |
ograp | +0.025 |
wcsstore | +0.025 |
ppo | +0.024 |
Neg logit contributions | |
alities | -0.021 |
Reviewed | -0.021 |
ities | -0.021 |
Collider | -0.020 |
romeda | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
tera | +0.052 |
river | +0.047 |
ograp | +0.041 |
wcsstore | +0.040 |
ppo | +0.040 |
Neg logit contributions | |
alities | -0.041 |
Reviewed | -0.041 |
ities | -0.040 |
Collider | -0.040 |
romeda | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | rising |
Token ID | 7396 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.008 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
alities | +0.022 |
Reviewed | +0.022 |
ities | +0.022 |
romeda | +0.021 |
Collider | +0.021 |
Neg logit contributions | |
tera | -0.027 |
river | -0.024 |
ograp | -0.021 |
ppo | -0.021 |
wcsstore | -0.021 |
Token | Budget |
Token ID | 15401 |
Feature activation | -3.52e-02 |
Pos logit contributions | |
alities | +0.005 |
Reviewed | +0.005 |
ities | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.007 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
alities | +0.008 |
Reviewed | +0.007 |
ities | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
ppo | -0.007 |
wcsstore | -0.007 |
Token | Policy |
Token ID | 7820 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
alities | +0.008 |
ities | +0.008 |
Reviewed | +0.008 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.008 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token | Prior |
Token ID | 14481 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
tera | +0.038 |
river | +0.035 |
ograp | +0.030 |
ppo | +0.030 |
wcsstore | +0.030 |
Neg logit contributions | |
alities | -0.022 |
Reviewed | -0.022 |
ities | -0.021 |
Collider | -0.021 |
romeda | -0.020 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
romeda | +0.007 |
Reviewed | +0.007 |
Collider | +0.006 |
alities | +0.005 |
rogens | +0.005 |
Neg logit contributions | |
tera | -0.143 |
river | -0.134 |
ograp | -0.125 |
wcsstore | -0.124 |
ppo | -0.123 |
Token | ( |
Token ID | 357 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
alities | +0.277 |
Reviewed | +0.273 |
ities | +0.272 |
Collider | +0.265 |
romeda | +0.261 |
Neg logit contributions | |
tera | -0.357 |
river | -0.323 |
ograp | -0.285 |
wcsstore | -0.281 |
ppo | -0.277 |
Token | CB |
Token ID | 23199 |
Feature activation | +7.59e-03 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | PP |
Token ID | 10246 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | ) |
Token ID | 8 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
alities | +0.036 |
ities | +0.035 |
Reviewed | +0.035 |
Collider | +0.034 |
romeda | +0.033 |
Neg logit contributions | |
tera | -0.064 |
river | -0.059 |
ograp | -0.053 |
wcsstore | -0.052 |
ppo | -0.052 |
Token | offered |
Token ID | 4438 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.009 |
wcsstore | -0.009 |
ppo | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -4.95e-03 |
Pos logit contributions | |
alities | +0.050 |
ities | +0.049 |
Reviewed | +0.049 |
Collider | +0.048 |
romeda | +0.047 |
Neg logit contributions | |
tera | -0.068 |
river | -0.061 |
ograp | -0.054 |
wcsstore | -0.054 |
ppo | -0.053 |
Token | women |
Token ID | 1466 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
tera | +0.031 |
river | +0.028 |
ograp | +0.025 |
wcsstore | +0.025 |
ppo | +0.024 |
Neg logit contributions | |
alities | -0.023 |
Reviewed | -0.023 |
ities | -0.023 |
Collider | -0.022 |
romeda | -0.022 |
Token | all |
Token ID | 477 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | ethnic |
Token ID | 9450 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
tera | +0.007 |
river | +0.007 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
tera | +0.049 |
river | +0.046 |
ograp | +0.043 |
wcsstore | +0.042 |
ppo | +0.042 |
Neg logit contributions | |
Reviewed | -0.005 |
alities | -0.005 |
Collider | -0.004 |
romeda | -0.004 |
ities | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +6.06e-03 |
Pos logit contributions | |
alities | +0.276 |
Reviewed | +0.274 |
ities | +0.271 |
Collider | +0.266 |
romeda | +0.262 |
Neg logit contributions | |
tera | -0.357 |
river | -0.324 |
ograp | -0.285 |
wcsstore | -0.281 |
ppo | -0.277 |
Token | This |
Token ID | 770 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | seems |
Token ID | 2331 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
tera | +0.043 |
river | +0.039 |
ograp | +0.035 |
wcsstore | +0.034 |
ppo | +0.034 |
Neg logit contributions | |
alities | -0.032 |
Reviewed | -0.032 |
ities | -0.032 |
Collider | -0.031 |
romeda | -0.030 |
Token | clear |
Token ID | 1598 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
alities | +0.013 |
Reviewed | +0.013 |
ities | +0.013 |
Collider | +0.013 |
romeda | +0.013 |
Neg logit contributions | |
tera | -0.016 |
river | -0.015 |
ograp | -0.013 |
wcsstore | -0.013 |
ppo | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -9.76e-03 |
Pos logit contributions | |
tera | +0.031 |
river | +0.028 |
ograp | +0.024 |
wcsstore | +0.024 |
ppo | +0.023 |
Neg logit contributions | |
alities | -0.026 |
Reviewed | -0.026 |
ities | -0.026 |
Collider | -0.025 |
romeda | -0.025 |
Token | fronts |
Token ID | 29324 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.000 |
Reviewed | -0.000 |
ities | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
alities | +0.177 |
Reviewed | +0.175 |
ities | +0.175 |
Collider | +0.170 |
romeda | +0.167 |
Neg logit contributions | |
tera | -0.239 |
river | -0.217 |
ograp | -0.192 |
wcsstore | -0.190 |
ppo | -0.187 |
Token | � |
Token ID | 564 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.004 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | � |
Token ID | 246 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | un |
Token ID | 403 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
tera | +0.074 |
river | +0.067 |
ograp | +0.059 |
wcsstore | +0.058 |
ppo | +0.057 |
Neg logit contributions | |
alities | -0.058 |
ities | -0.057 |
Reviewed | -0.057 |
Collider | -0.056 |
romeda | -0.055 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
alities | +0.013 |
Reviewed | +0.013 |
ities | +0.013 |
Collider | +0.013 |
romeda | +0.012 |
Neg logit contributions | |
tera | -0.015 |
river | -0.014 |
ograp | -0.012 |
wcsstore | -0.012 |
ppo | -0.012 |
Token | � |
Token ID | 447 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
alities | +0.276 |
ities | +0.272 |
Reviewed | +0.271 |
Collider | +0.264 |
romeda | +0.260 |
Neg logit contributions | |
tera | -0.358 |
river | -0.324 |
ograp | -0.287 |
wcsstore | -0.283 |
ppo | -0.278 |
Token | � |
Token ID | 247 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -7.04e-03 |
Pos logit contributions | |
alities | +0.008 |
Reviewed | +0.008 |
ities | +0.008 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.011 |
river | -0.010 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | bourgeois |
Token ID | 19749 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.003 |
Token | atern |
Token ID | 9205 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
tera | +0.125 |
river | +0.113 |
ograp | +0.099 |
wcsstore | +0.097 |
ppo | +0.096 |
Neg logit contributions | |
alities | -0.111 |
Reviewed | -0.110 |
ities | -0.109 |
Collider | -0.107 |
romeda | -0.105 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Reviewed | +0.000 |
alities | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
ities | +0.000 |
Neg logit contributions | |
tera | -0.017 |
river | -0.016 |
ograp | -0.015 |
wcsstore | -0.015 |
ppo | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -8.64e-03 |
Pos logit contributions | |
alities | +0.240 |
Reviewed | +0.236 |
ities | +0.235 |
Collider | +0.229 |
romeda | +0.225 |
Neg logit contributions | |
tera | -0.392 |
river | -0.359 |
ograp | -0.321 |
wcsstore | -0.317 |
ppo | -0.313 |
Token | sor |
Token ID | 25655 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | or |
Token ID | 273 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
Reviewed | +0.071 |
alities | +0.071 |
Collider | +0.070 |
ities | +0.069 |
romeda | +0.068 |
Neg logit contributions | |
tera | -0.075 |
river | -0.068 |
ograp | -0.059 |
wcsstore | -0.057 |
ppo | -0.057 |
Token | ities |
Token ID | 871 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Reviewed | +0.001 |
alities | +0.001 |
Collider | +0.001 |
romeda | +0.000 |
ities | +0.000 |
Neg logit contributions | |
tera | -0.046 |
river | -0.043 |
ograp | -0.040 |
wcsstore | -0.040 |
ppo | -0.039 |
Token | on |
Token ID | 319 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
alities | +0.229 |
Reviewed | +0.226 |
ities | +0.224 |
Collider | +0.218 |
romeda | +0.214 |
Neg logit contributions | |
tera | -0.404 |
river | -0.370 |
ograp | -0.333 |
wcsstore | -0.328 |
ppo | -0.324 |
Token | campus |
Token ID | 7611 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
alities | +0.011 |
ities | +0.011 |
Reviewed | +0.011 |
Collider | +0.011 |
romeda | +0.011 |
Neg logit contributions | |
tera | -0.018 |
river | -0.016 |
ograp | -0.015 |
wcsstore | -0.015 |
ppo | -0.014 |
Token | ), |
Token ID | 828 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
tera | +0.012 |
river | +0.011 |
ograp | +0.010 |
wcsstore | +0.010 |
ppo | +0.009 |
Neg logit contributions | |
alities | -0.007 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -2.85e-03 |
Pos logit contributions | |
alities | +0.071 |
Reviewed | +0.070 |
ities | +0.070 |
Collider | +0.068 |
romeda | +0.067 |
Neg logit contributions | |
tera | -0.099 |
river | -0.090 |
ograp | -0.080 |
wcsstore | -0.079 |
ppo | -0.077 |
Token | in |
Token ID | 287 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | t |
Token ID | 83 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
alities | +0.004 |
Reviewed | +0.004 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
alities | +0.008 |
Reviewed | +0.007 |
ities | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
tera | +0.036 |
river | +0.033 |
ograp | +0.029 |
wcsstore | +0.028 |
ppo | +0.028 |
Neg logit contributions | |
alities | -0.028 |
Reviewed | -0.028 |
ities | -0.027 |
Collider | -0.027 |
romeda | -0.026 |
Token | harder |
Token ID | 7069 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
tera | +0.033 |
river | +0.030 |
ograp | +0.027 |
wcsstore | +0.026 |
ppo | +0.026 |
Neg logit contributions | |
alities | -0.024 |
Reviewed | -0.024 |
ities | -0.024 |
Collider | -0.023 |
romeda | -0.023 |
Token | on |
Token ID | 319 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
tera | +0.005 |
river | +0.004 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
Reviewed | -0.004 |
ities | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | yourself |
Token ID | 3511 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
alities | +0.028 |
ities | +0.028 |
Reviewed | +0.028 |
Collider | +0.028 |
romeda | +0.027 |
Neg logit contributions | |
tera | -0.014 |
river | -0.011 |
ograp | -0.009 |
wcsstore | -0.009 |
ppo | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
tera | +0.216 |
river | +0.195 |
ograp | +0.173 |
wcsstore | +0.170 |
ppo | +0.167 |
Neg logit contributions | |
alities | -0.170 |
Reviewed | -0.167 |
ities | -0.167 |
Collider | -0.163 |
romeda | -0.160 |
Token | I |
Token ID | 314 |
Feature activation | +6.10e-03 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | � |
Token ID | 447 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | � |
Token ID | 247 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.000 |
wcsstore | +0.000 |
ppo | +0.000 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | ve |
Token ID | 303 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
tera | +0.002 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | dips |
Token ID | 48904 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
tera | +0.091 |
river | +0.083 |
ograp | +0.073 |
wcsstore | +0.073 |
ppo | +0.071 |
Neg logit contributions | |
alities | -0.066 |
ities | -0.065 |
Reviewed | -0.064 |
Collider | -0.063 |
romeda | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
tera | +0.015 |
river | +0.014 |
ograp | +0.012 |
wcsstore | +0.012 |
ppo | +0.012 |
Neg logit contributions | |
alities | -0.011 |
ities | -0.011 |
Reviewed | -0.011 |
Collider | -0.011 |
romeda | -0.011 |
Token | helped |
Token ID | 4193 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
tera | +0.004 |
river | +0.004 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | T |
Token ID | 309 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
alities | +0.040 |
ities | +0.040 |
Reviewed | +0.039 |
Collider | +0.039 |
romeda | +0.038 |
Neg logit contributions | |
tera | -0.053 |
river | -0.048 |
ograp | -0.043 |
wcsstore | -0.042 |
ppo | -0.041 |
Token | read |
Token ID | 961 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
tera | +0.006 |
river | +0.006 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.005 |
ities | -0.005 |
Reviewed | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | well |
Token ID | 4053 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
tera | +0.009 |
river | +0.007 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.024 |
ities | -0.024 |
Reviewed | -0.024 |
Collider | -0.024 |
romeda | -0.024 |
Token | negate |
Token ID | 44328 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
tera | +0.216 |
river | +0.195 |
ograp | +0.172 |
wcsstore | +0.169 |
ppo | +0.166 |
Neg logit contributions | |
alities | -0.178 |
ities | -0.176 |
Reviewed | -0.175 |
Collider | -0.171 |
romeda | -0.168 |
Token | his |
Token ID | 465 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
tera | +0.057 |
river | +0.052 |
ograp | +0.046 |
wcsstore | +0.045 |
ppo | +0.045 |
Neg logit contributions | |
alities | -0.042 |
ities | -0.041 |
Reviewed | -0.041 |
Collider | -0.040 |
romeda | -0.039 |
Token | lack |
Token ID | 3092 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
tera | +0.004 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
Reviewed | -0.003 |
ities | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
alities | +0.082 |
ities | +0.081 |
Reviewed | +0.080 |
Collider | +0.078 |
romeda | +0.077 |
Neg logit contributions | |
tera | -0.105 |
river | -0.095 |
ograp | -0.084 |
wcsstore | -0.082 |
ppo | -0.081 |
Token | speed |
Token ID | 2866 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
alities | +0.006 |
ities | +0.006 |
Reviewed | +0.006 |
Collider | +0.006 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.007 |
river | -0.006 |
ograp | -0.006 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
alities | +0.021 |
ities | +0.021 |
Reviewed | +0.020 |
Collider | +0.020 |
romeda | +0.020 |
Neg logit contributions | |
tera | -0.029 |
river | -0.026 |
ograp | -0.023 |
wcsstore | -0.023 |
ppo | -0.023 |
Token | joystick |
Token ID | 49485 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
tera | +0.008 |
river | +0.007 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | with |
Token ID | 351 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
tera | +0.066 |
river | +0.060 |
ograp | +0.053 |
wcsstore | +0.052 |
ppo | +0.051 |
Neg logit contributions | |
alities | -0.051 |
ities | -0.050 |
Reviewed | -0.050 |
Collider | -0.048 |
romeda | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.007 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token | right |
Token ID | 826 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | hand |
Token ID | 1021 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
tera | +0.025 |
river | +0.022 |
ograp | +0.018 |
wcsstore | +0.017 |
ppo | +0.017 |
Neg logit contributions | |
alities | -0.039 |
ities | -0.039 |
Reviewed | -0.039 |
Collider | -0.038 |
romeda | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
tera | +0.236 |
river | +0.214 |
ograp | +0.190 |
wcsstore | +0.187 |
ppo | +0.184 |
Neg logit contributions | |
alities | -0.181 |
Reviewed | -0.178 |
ities | -0.178 |
Collider | -0.173 |
romeda | -0.171 |
Token | obtain |
Token ID | 7330 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.004 |
river | -0.004 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
tera | +0.021 |
river | +0.019 |
ograp | +0.017 |
wcsstore | +0.016 |
ppo | +0.016 |
Neg logit contributions | |
alities | -0.015 |
ities | -0.015 |
Reviewed | -0.015 |
Collider | -0.014 |
romeda | -0.014 |
Token | reward |
Token ID | 6721 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | ( |
Token ID | 357 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
tera | +0.035 |
river | +0.032 |
ograp | +0.028 |
wcsstore | +0.028 |
ppo | +0.027 |
Neg logit contributions | |
alities | -0.028 |
ities | -0.028 |
Reviewed | -0.028 |
Collider | -0.027 |
romeda | -0.027 |
Token | parts |
Token ID | 3354 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
tera | +0.005 |
river | +0.005 |
ograp | +0.004 |
wcsstore | +0.004 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.004 |
Reviewed | -0.004 |
ities | -0.004 |
Collider | -0.004 |
romeda | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
tera | +0.214 |
river | +0.193 |
ograp | +0.170 |
wcsstore | +0.167 |
ppo | +0.164 |
Neg logit contributions | |
alities | -0.177 |
Reviewed | -0.175 |
ities | -0.175 |
Collider | -0.170 |
romeda | -0.168 |
Token | ( |
Token ID | 357 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
alities | +0.005 |
Reviewed | +0.005 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | part |
Token ID | 3911 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
alities | +0.004 |
Reviewed | +0.004 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
tera | +0.003 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | parts |
Token ID | 3354 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
tera | +0.008 |
river | +0.007 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.015 |
Reviewed | -0.015 |
ities | -0.015 |
Collider | -0.015 |
romeda | -0.015 |
Token | ) |
Token ID | 8 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
tera | +0.241 |
river | +0.219 |
ograp | +0.195 |
wcsstore | +0.191 |
ppo | +0.189 |
Neg logit contributions | |
alities | -0.163 |
Reviewed | -0.161 |
ities | -0.160 |
Collider | -0.155 |
romeda | -0.154 |
Token | return |
Token ID | 1441 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | ob |
Token ID | 909 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
tera | +0.075 |
river | +0.066 |
ograp | +0.056 |
wcsstore | +0.055 |
ppo | +0.054 |
Neg logit contributions | |
alities | -0.088 |
Reviewed | -0.088 |
ities | -0.087 |
Collider | -0.085 |
romeda | -0.085 |
Token | b |
Token ID | 65 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
alities | +0.032 |
Reviewed | +0.031 |
ities | +0.031 |
Collider | +0.030 |
romeda | +0.029 |
Neg logit contributions | |
tera | -0.056 |
river | -0.051 |
ograp | -0.046 |
wcsstore | -0.045 |
ppo | -0.045 |
Token | _ |
Token ID | 62 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
alities | +0.050 |
ities | +0.049 |
Reviewed | +0.049 |
Collider | +0.048 |
romeda | +0.047 |
Neg logit contributions | |
tera | -0.060 |
river | -0.054 |
ograp | -0.048 |
wcsstore | -0.047 |
ppo | -0.046 |
Token | � |
Token ID | 447 |
Feature activation | -6.04e-03 |
Pos logit contributions | |
alities | +0.030 |
ities | +0.029 |
Reviewed | +0.029 |
Collider | +0.029 |
romeda | +0.028 |
Neg logit contributions | |
tera | -0.039 |
river | -0.035 |
ograp | -0.031 |
wcsstore | -0.031 |
ppo | -0.030 |
Token | � |
Token ID | 247 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | ll |
Token ID | 297 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
tera | +0.004 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | see |
Token ID | 766 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
alities | +0.038 |
ities | +0.037 |
Reviewed | +0.037 |
Collider | +0.036 |
romeda | +0.035 |
Neg logit contributions | |
tera | -0.049 |
river | -0.045 |
ograp | -0.040 |
wcsstore | -0.039 |
ppo | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
tera | +0.044 |
river | +0.040 |
ograp | +0.035 |
wcsstore | +0.035 |
ppo | +0.034 |
Neg logit contributions | |
alities | -0.033 |
ities | -0.032 |
Reviewed | -0.032 |
Collider | -0.031 |
romeda | -0.031 |
Token | Arena |
Token ID | 10937 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +9.50e-03 |
Pos logit contributions | |
tera | +0.219 |
river | +0.198 |
ograp | +0.174 |
wcsstore | +0.171 |
ppo | +0.169 |
Neg logit contributions | |
alities | -0.169 |
ities | -0.167 |
Reviewed | -0.166 |
Collider | -0.161 |
romeda | -0.159 |
Token | Keep |
Token ID | 9175 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
tera | +0.089 |
river | +0.080 |
ograp | +0.071 |
wcsstore | +0.070 |
ppo | +0.069 |
Neg logit contributions | |
alities | -0.069 |
ities | -0.068 |
Reviewed | -0.068 |
Collider | -0.066 |
romeda | -0.065 |
Token | mind |
Token ID | 2000 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
tera | +0.019 |
river | +0.018 |
ograp | +0.016 |
wcsstore | +0.016 |
ppo | +0.016 |
Neg logit contributions | |
alities | -0.008 |
ities | -0.008 |
Reviewed | -0.008 |
Collider | -0.008 |
romeda | -0.008 |
Token | this |
Token ID | 428 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
alities | +0.077 |
ities | +0.076 |
Reviewed | +0.076 |
Collider | +0.074 |
romeda | +0.073 |
Neg logit contributions | |
tera | -0.097 |
river | -0.088 |
ograp | -0.078 |
wcsstore | -0.077 |
ppo | -0.075 |
Token | with |
Token ID | 351 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
tera | +0.078 |
river | +0.071 |
ograp | +0.062 |
wcsstore | +0.061 |
ppo | +0.061 |
Neg logit contributions | |
alities | -0.059 |
Reviewed | -0.058 |
ities | -0.058 |
Collider | -0.057 |
romeda | -0.056 |
Token | corruption |
Token ID | 9253 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
alities | +0.010 |
Reviewed | +0.010 |
ities | +0.010 |
Collider | +0.010 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.014 |
river | -0.013 |
ograp | -0.011 |
wcsstore | -0.011 |
ppo | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
alities | +0.053 |
ities | +0.053 |
Reviewed | +0.053 |
Collider | +0.051 |
romeda | +0.050 |
Neg logit contributions | |
tera | -0.071 |
river | -0.064 |
ograp | -0.057 |
wcsstore | -0.056 |
ppo | -0.055 |
Token | organised |
Token ID | 20325 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Reviewed | +0.005 |
alities | +0.005 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.007 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | crime |
Token ID | 4065 |
Feature activation | +8.77e-02 |
Pos logit contributions | |
Reviewed | +0.077 |
alities | +0.076 |
Collider | +0.075 |
ities | +0.075 |
romeda | +0.073 |
Neg logit contributions | |
tera | -0.103 |
river | -0.094 |
ograp | -0.082 |
wcsstore | -0.081 |
ppo | -0.080 |
Token | in |
Token ID | 287 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
tera | +0.024 |
river | +0.022 |
ograp | +0.019 |
wcsstore | +0.019 |
ppo | +0.018 |
Neg logit contributions | |
alities | -0.019 |
Reviewed | -0.019 |
ities | -0.019 |
Collider | -0.018 |
romeda | -0.018 |
Token | these |
Token ID | 777 |
Feature activation | -9.48e-02 |
Pos logit contributions | |
tera | +0.007 |
river | +0.006 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.005 |
ities | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | countries |
Token ID | 2678 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
alities | +0.023 |
Reviewed | +0.022 |
ities | +0.022 |
Collider | +0.022 |
romeda | +0.022 |
Neg logit contributions | |
tera | -0.024 |
river | -0.021 |
ograp | -0.018 |
wcsstore | -0.018 |
ppo | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
tera | +0.007 |
river | +0.006 |
ograp | +0.006 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.005 |
Reviewed | -0.005 |
ities | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | Now |
Token ID | 2735 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
alities | +0.006 |
ities | +0.006 |
Reviewed | +0.006 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.006 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
alities | +0.008 |
ities | +0.008 |
Reviewed | +0.008 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.011 |
river | -0.010 |
ograp | -0.008 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | killed |
Token ID | 2923 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
alities | +0.016 |
Reviewed | +0.016 |
ities | +0.016 |
Collider | +0.016 |
romeda | +0.015 |
Neg logit contributions | |
tera | -0.025 |
river | -0.022 |
ograp | -0.020 |
wcsstore | -0.020 |
ppo | -0.019 |
Token | by |
Token ID | 416 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | machine |
Token ID | 4572 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
alities | +0.008 |
Reviewed | +0.008 |
ities | +0.008 |
Collider | +0.008 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.010 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | guns |
Token ID | 6541 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
alities | +0.049 |
ities | +0.048 |
Reviewed | +0.048 |
Collider | +0.047 |
romeda | +0.046 |
Neg logit contributions | |
tera | -0.064 |
river | -0.058 |
ograp | -0.051 |
wcsstore | -0.050 |
ppo | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
tera | +0.018 |
river | +0.016 |
ograp | +0.014 |
wcsstore | +0.014 |
ppo | +0.014 |
Neg logit contributions | |
alities | -0.015 |
ities | -0.014 |
Reviewed | -0.014 |
Collider | -0.014 |
romeda | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
alities | +0.006 |
ities | +0.006 |
Reviewed | +0.006 |
Collider | +0.006 |
romeda | +0.006 |
Neg logit contributions | |
tera | -0.008 |
river | -0.007 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +4.58e-03 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | Its |
Token ID | 20459 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | source |
Token ID | 2723 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
alities | +0.026 |
Reviewed | +0.026 |
ities | +0.026 |
Collider | +0.025 |
romeda | +0.025 |
Neg logit contributions | |
tera | -0.034 |
river | -0.031 |
ograp | -0.027 |
wcsstore | -0.027 |
ppo | -0.026 |
Token | said |
Token ID | 531 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
alities | +0.007 |
Reviewed | +0.007 |
ities | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.009 |
river | -0.008 |
ograp | -0.007 |
wcsstore | -0.007 |
ppo | -0.007 |
Token | : |
Token ID | 25 |
Feature activation | -5.53e-02 |
Pos logit contributions | |
tera | +0.015 |
river | +0.014 |
ograp | +0.012 |
wcsstore | +0.012 |
ppo | +0.012 |
Neg logit contributions | |
alities | -0.012 |
Reviewed | -0.012 |
ities | -0.012 |
Collider | -0.011 |
romeda | -0.011 |
Token | State |
Token ID | 1812 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
alities | +0.010 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.009 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.010 |
wcsstore | -0.009 |
ppo | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
alities | +0.015 |
Reviewed | +0.015 |
ities | +0.015 |
Collider | +0.015 |
romeda | +0.015 |
Neg logit contributions | |
tera | -0.019 |
river | -0.018 |
ograp | -0.015 |
wcsstore | -0.015 |
ppo | -0.015 |
Token | territory |
Token ID | 7674 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
tera | +0.007 |
river | +0.006 |
ograp | +0.006 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +7.03e-03 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | possession |
Token ID | 7797 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
alities | +0.056 |
ities | +0.055 |
Reviewed | +0.055 |
Collider | +0.054 |
romeda | +0.053 |
Neg logit contributions | |
tera | -0.074 |
river | -0.067 |
ograp | -0.059 |
wcsstore | -0.058 |
ppo | -0.057 |
Token | or |
Token ID | 393 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
tera | +0.007 |
river | +0.007 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.005 |
Token | tribe |
Token ID | 14893 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
tera | +0.013 |
river | +0.012 |
ograp | +0.011 |
wcsstore | +0.011 |
ppo | +0.011 |
Neg logit contributions | |
alities | -0.006 |
Reviewed | -0.006 |
ities | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +7.38e-03 |
Pos logit contributions | |
alities | +0.040 |
Reviewed | +0.039 |
ities | +0.039 |
Collider | +0.038 |
romeda | +0.038 |
Neg logit contributions | |
tera | -0.050 |
river | -0.045 |
ograp | -0.040 |
wcsstore | -0.039 |
ppo | -0.038 |
Token | or |
Token ID | 393 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
tera | +0.002 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
tera | +0.016 |
river | +0.015 |
ograp | +0.013 |
wcsstore | +0.013 |
ppo | +0.013 |
Neg logit contributions | |
alities | -0.012 |
Reviewed | -0.012 |
ities | -0.012 |
Collider | -0.012 |
romeda | -0.012 |
Token | attention |
Token ID | 3241 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.009 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.010 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
tera | +0.058 |
river | +0.053 |
ograp | +0.046 |
wcsstore | +0.046 |
ppo | +0.045 |
Neg logit contributions | |
alities | -0.049 |
Reviewed | -0.048 |
ities | -0.048 |
Collider | -0.047 |
romeda | -0.047 |
Token | McLaren |
Token ID | 33017 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.004 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | as |
Token ID | 355 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
tera | +0.046 |
river | +0.041 |
ograp | +0.036 |
wcsstore | +0.036 |
ppo | +0.035 |
Neg logit contributions | |
alities | -0.036 |
ities | -0.036 |
Reviewed | -0.035 |
Collider | -0.035 |
romeda | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
alities | +0.023 |
ities | +0.023 |
Reviewed | +0.023 |
Collider | +0.022 |
romeda | +0.022 |
Neg logit contributions | |
tera | -0.032 |
river | -0.029 |
ograp | -0.026 |
wcsstore | -0.026 |
ppo | -0.025 |
Token | child |
Token ID | 1200 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
tera | +0.062 |
river | +0.056 |
ograp | +0.049 |
wcsstore | +0.048 |
ppo | +0.047 |
Neg logit contributions | |
alities | -0.055 |
Reviewed | -0.054 |
ities | -0.054 |
Collider | -0.052 |
romeda | -0.052 |
Token | " |
Token ID | 366 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.006 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | You |
Token ID | 1639 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | might |
Token ID | 1244 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
alities | +0.042 |
ities | +0.041 |
Reviewed | +0.041 |
Collider | +0.040 |
romeda | +0.039 |
Neg logit contributions | |
tera | -0.053 |
river | -0.048 |
ograp | -0.042 |
wcsstore | -0.042 |
ppo | -0.041 |
Token | drive |
Token ID | 3708 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
tera | +0.077 |
river | +0.069 |
ograp | +0.061 |
wcsstore | +0.061 |
ppo | +0.060 |
Neg logit contributions | |
alities | -0.059 |
Reviewed | -0.059 |
ities | -0.058 |
Collider | -0.057 |
romeda | -0.056 |
Token | I |
Token ID | 40 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
tera | +0.011 |
river | +0.010 |
ograp | +0.009 |
wcsstore | +0.009 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.010 |
ities | -0.009 |
Reviewed | -0.009 |
Collider | -0.009 |
romeda | -0.009 |
Token | love |
Token ID | 1842 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
tera | +0.036 |
river | +0.033 |
ograp | +0.029 |
wcsstore | +0.028 |
ppo | +0.028 |
Neg logit contributions | |
alities | -0.028 |
ities | -0.028 |
Reviewed | -0.028 |
Collider | -0.027 |
romeda | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
tera | +0.040 |
river | +0.036 |
ograp | +0.032 |
wcsstore | +0.031 |
ppo | +0.031 |
Neg logit contributions | |
alities | -0.029 |
Reviewed | -0.029 |
ities | -0.029 |
Collider | -0.028 |
romeda | -0.028 |
Token | beach |
Token ID | 10481 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
tera | +0.000 |
river | +0.000 |
ograp | +0.000 |
wcsstore | +0.000 |
ppo | +0.000 |
Neg logit contributions | |
alities | -0.000 |
Reviewed | -0.000 |
ities | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | too |
Token ID | 1165 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
alities | +0.013 |
ities | +0.013 |
Reviewed | +0.013 |
Collider | +0.012 |
romeda | +0.012 |
Neg logit contributions | |
tera | -0.017 |
river | -0.015 |
ograp | -0.014 |
wcsstore | -0.013 |
ppo | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
tera | +0.059 |
river | +0.054 |
ograp | +0.048 |
wcsstore | +0.047 |
ppo | +0.046 |
Neg logit contributions | |
alities | -0.041 |
Reviewed | -0.041 |
ities | -0.041 |
Collider | -0.039 |
romeda | -0.039 |
Token | That |
Token ID | 1320 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | � |
Token ID | 447 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
tera | +0.018 |
river | +0.016 |
ograp | +0.014 |
wcsstore | +0.014 |
ppo | +0.014 |
Neg logit contributions | |
alities | -0.013 |
ities | -0.013 |
Reviewed | -0.013 |
Collider | -0.013 |
romeda | -0.013 |
Token | � |
Token ID | 247 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | s |
Token ID | 82 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | why |
Token ID | 1521 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
alities | +0.002 |
Reviewed | +0.002 |
ities | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.002 |
river | -0.002 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | ing |
Token ID | 278 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
tera | +0.012 |
river | +0.011 |
ograp | +0.010 |
wcsstore | +0.010 |
ppo | +0.009 |
Neg logit contributions | |
alities | -0.008 |
ities | -0.008 |
Reviewed | -0.008 |
Collider | -0.008 |
romeda | -0.008 |
Token | Up |
Token ID | 3205 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
alities | +0.011 |
ities | +0.011 |
Reviewed | +0.011 |
Collider | +0.010 |
romeda | +0.010 |
Neg logit contributions | |
tera | -0.014 |
river | -0.012 |
ograp | -0.011 |
wcsstore | -0.011 |
ppo | -0.011 |
Token | � |
Token ID | 447 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
ities | -0.003 |
Reviewed | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | � |
Token ID | 251 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.009 |
ities | -0.009 |
Reviewed | -0.009 |
Collider | -0.009 |
romeda | -0.009 |
Token | by |
Token ID | 416 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
ities | -0.001 |
Reviewed | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | state |
Token ID | 1181 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
alities | +0.003 |
ities | +0.003 |
Reviewed | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +6.09e-02 |
Pos logit contributions | |
alities | +0.012 |
Reviewed | +0.012 |
ities | +0.012 |
Collider | +0.011 |
romeda | +0.011 |
Neg logit contributions | |
tera | -0.016 |
river | -0.014 |
ograp | -0.013 |
wcsstore | -0.012 |
ppo | -0.012 |
Token | including |
Token ID | 1390 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
tera | +0.017 |
river | +0.016 |
ograp | +0.014 |
wcsstore | +0.014 |
ppo | +0.014 |
Neg logit contributions | |
alities | -0.012 |
Reviewed | -0.012 |
ities | -0.012 |
Collider | -0.012 |
romeda | -0.011 |
Token | things |
Token ID | 1243 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.011 |
river | -0.010 |
ograp | -0.009 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | like |
Token ID | 588 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
tera | +0.065 |
river | +0.059 |
ograp | +0.053 |
wcsstore | +0.052 |
ppo | +0.051 |
Neg logit contributions | |
alities | -0.045 |
Reviewed | -0.044 |
ities | -0.044 |
Collider | -0.042 |
romeda | -0.042 |
Token | trolls |
Token ID | 24727 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.009 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.013 |
river | -0.011 |
ograp | -0.010 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | therapy |
Token ID | 9102 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
alities | +0.065 |
ities | +0.064 |
Reviewed | +0.064 |
Collider | +0.063 |
romeda | +0.062 |
Neg logit contributions | |
tera | -0.087 |
river | -0.079 |
ograp | -0.070 |
wcsstore | -0.069 |
ppo | -0.068 |
Token | could |
Token ID | 714 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
alities | +0.033 |
ities | +0.033 |
Reviewed | +0.032 |
Collider | +0.032 |
romeda | +0.031 |
Neg logit contributions | |
tera | -0.044 |
river | -0.039 |
ograp | -0.035 |
wcsstore | -0.034 |
ppo | -0.034 |
Token | help |
Token ID | 1037 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
alities | +0.060 |
ities | +0.060 |
Reviewed | +0.059 |
Collider | +0.058 |
romeda | +0.057 |
Neg logit contributions | |
tera | -0.075 |
river | -0.068 |
ograp | -0.060 |
wcsstore | -0.059 |
ppo | -0.058 |
Token | get |
Token ID | 651 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
tera | +0.090 |
river | +0.081 |
ograp | +0.072 |
wcsstore | +0.070 |
ppo | +0.070 |
Neg logit contributions | |
alities | -0.072 |
ities | -0.071 |
Reviewed | -0.071 |
Collider | -0.069 |
romeda | -0.068 |
Token | to |
Token ID | 284 |
Feature activation | -5.83e-03 |
Pos logit contributions | |
alities | +0.031 |
ities | +0.030 |
Reviewed | +0.030 |
Collider | +0.029 |
romeda | +0.029 |
Neg logit contributions | |
tera | -0.040 |
river | -0.037 |
ograp | -0.032 |
wcsstore | -0.032 |
ppo | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | root |
Token ID | 6808 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
alities | +0.008 |
Reviewed | +0.008 |
ities | +0.008 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.011 |
river | -0.010 |
ograp | -0.009 |
wcsstore | -0.008 |
ppo | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
alities | +0.057 |
ities | +0.056 |
Reviewed | +0.056 |
Collider | +0.054 |
romeda | +0.053 |
Neg logit contributions | |
tera | -0.079 |
river | -0.072 |
ograp | -0.064 |
wcsstore | -0.063 |
ppo | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
alities | +0.003 |
Reviewed | +0.003 |
ities | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | problem |
Token ID | 1917 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
alities | +0.006 |
Reviewed | +0.006 |
ities | +0.006 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.007 |
river | -0.006 |
ograp | -0.006 |
wcsstore | -0.006 |
ppo | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
alities | +0.022 |
Reviewed | +0.022 |
ities | +0.021 |
Collider | +0.021 |
romeda | +0.021 |
Neg logit contributions | |
tera | -0.028 |
river | -0.025 |
ograp | -0.022 |
wcsstore | -0.022 |
ppo | -0.021 |
Token | � |
Token ID | 447 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
tera | +0.107 |
river | +0.097 |
ograp | +0.086 |
wcsstore | +0.084 |
ppo | +0.084 |
Neg logit contributions | |
alities | -0.082 |
Reviewed | -0.081 |
ities | -0.080 |
Collider | -0.078 |
romeda | -0.077 |
Token | � |
Token ID | 247 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
tera | +0.006 |
river | +0.005 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.005 |
Neg logit contributions | |
alities | -0.006 |
ities | -0.006 |
Reviewed | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | s |
Token ID | 82 |
Feature activation | +2.70e-03 |
Pos logit contributions | |
tera | +0.009 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.007 |
Neg logit contributions | |
alities | -0.007 |
Reviewed | -0.007 |
ities | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | what |
Token ID | 644 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.010 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | need |
Token ID | 761 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
alities | +0.025 |
ities | +0.025 |
Reviewed | +0.025 |
Collider | +0.024 |
romeda | +0.024 |
Neg logit contributions | |
tera | -0.034 |
river | -0.030 |
ograp | -0.027 |
wcsstore | -0.027 |
ppo | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.005 |
river | -0.005 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | know |
Token ID | 760 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
tera | +0.007 |
river | +0.007 |
ograp | +0.006 |
wcsstore | +0.006 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.005 |
ities | -0.005 |
Reviewed | -0.005 |
Collider | -0.005 |
romeda | -0.005 |
Token | about |
Token ID | 546 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
alities | +0.004 |
Reviewed | +0.004 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.005 |
river | -0.005 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
alities | +0.001 |
ities | +0.001 |
Reviewed | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | Nike |
Token ID | 23817 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
alities | +0.005 |
Reviewed | +0.005 |
ities | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | throttle |
Token ID | 29976 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
tera | +0.002 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
alities | +0.069 |
ities | +0.068 |
Reviewed | +0.067 |
Collider | +0.066 |
romeda | +0.065 |
Neg logit contributions | |
tera | -0.092 |
river | -0.083 |
ograp | -0.074 |
wcsstore | -0.073 |
ppo | -0.071 |
Token | reached |
Token ID | 4251 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
tera | +0.004 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | down |
Token ID | 866 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
tera | +0.015 |
river | +0.014 |
ograp | +0.012 |
wcsstore | +0.012 |
ppo | +0.012 |
Neg logit contributions | |
alities | -0.013 |
Reviewed | -0.013 |
ities | -0.013 |
Collider | -0.012 |
romeda | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
tera | +0.092 |
river | +0.083 |
ograp | +0.073 |
wcsstore | +0.072 |
ppo | +0.071 |
Neg logit contributions | |
alities | -0.074 |
Reviewed | -0.073 |
ities | -0.072 |
Collider | -0.071 |
romeda | -0.070 |
Token | take |
Token ID | 1011 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
tera | +0.006 |
river | +0.005 |
ograp | +0.005 |
wcsstore | +0.005 |
ppo | +0.004 |
Neg logit contributions | |
alities | -0.005 |
Reviewed | -0.005 |
ities | -0.005 |
Collider | -0.004 |
romeda | -0.004 |
Token | control |
Token ID | 1630 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
alities | +0.004 |
ities | +0.004 |
Reviewed | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.005 |
river | -0.004 |
ograp | -0.004 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +9.89e-03 |
Pos logit contributions | |
alities | +0.015 |
ities | +0.015 |
Reviewed | +0.015 |
Collider | +0.014 |
romeda | +0.014 |
Neg logit contributions | |
tera | -0.018 |
river | -0.017 |
ograp | -0.015 |
wcsstore | -0.014 |
ppo | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
ities | -0.002 |
Reviewed | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | stick |
Token ID | 4859 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.002 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | ; |
Token ID | 26 |
Feature activation | +6.05e-02 |
Pos logit contributions | |
tera | +0.082 |
river | +0.075 |
ograp | +0.065 |
wcsstore | +0.064 |
ppo | +0.063 |
Neg logit contributions | |
alities | -0.068 |
Reviewed | -0.068 |
ities | -0.067 |
Collider | -0.066 |
romeda | -0.065 |
Token | physicians |
Token ID | 17206 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
alities | +0.018 |
ities | +0.018 |
Reviewed | +0.017 |
Collider | +0.017 |
romeda | +0.017 |
Neg logit contributions | |
tera | -0.024 |
river | -0.022 |
ograp | -0.020 |
wcsstore | -0.019 |
ppo | -0.019 |
Token | had |
Token ID | 550 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
tera | +0.050 |
river | +0.045 |
ograp | +0.040 |
wcsstore | +0.040 |
ppo | +0.039 |
Neg logit contributions | |
alities | -0.033 |
ities | -0.032 |
Reviewed | -0.032 |
Collider | -0.031 |
romeda | -0.031 |
Token | poor |
Token ID | 3595 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
alities | +0.011 |
ities | +0.011 |
Reviewed | +0.011 |
Collider | +0.011 |
romeda | +0.010 |
Neg logit contributions | |
tera | -0.015 |
river | -0.013 |
ograp | -0.012 |
wcsstore | -0.012 |
ppo | -0.011 |
Token | medical |
Token ID | 3315 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
alities | +0.024 |
Reviewed | +0.024 |
ities | +0.024 |
Collider | +0.023 |
romeda | +0.023 |
Neg logit contributions | |
tera | -0.032 |
river | -0.029 |
ograp | -0.025 |
wcsstore | -0.025 |
ppo | -0.024 |
Token | training |
Token ID | 3047 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.001 |
wcsstore | +0.001 |
ppo | +0.001 |
Neg logit contributions | |
alities | -0.001 |
Reviewed | -0.001 |
ities | -0.001 |
Collider | -0.001 |
romeda | -0.001 |
Token | before |
Token ID | 878 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
alities | +0.041 |
ities | +0.040 |
Reviewed | +0.040 |
Collider | +0.038 |
romeda | +0.038 |
Neg logit contributions | |
tera | -0.052 |
river | -0.047 |
ograp | -0.042 |
wcsstore | -0.041 |
ppo | -0.040 |
Token | entering |
Token ID | 8218 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
alities | +0.022 |
ities | +0.021 |
Reviewed | +0.021 |
Collider | +0.021 |
romeda | +0.021 |
Neg logit contributions | |
tera | -0.030 |
river | -0.027 |
ograp | -0.024 |
wcsstore | -0.024 |
ppo | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
tera | +0.048 |
river | +0.044 |
ograp | +0.038 |
wcsstore | +0.038 |
ppo | +0.037 |
Neg logit contributions | |
alities | -0.033 |
Reviewed | -0.033 |
ities | -0.032 |
Collider | -0.032 |
romeda | -0.031 |
Token | field |
Token ID | 2214 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
alities | +0.004 |
Reviewed | +0.004 |
ities | +0.004 |
Collider | +0.004 |
romeda | +0.004 |
Neg logit contributions | |
tera | -0.007 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
alities | +0.029 |
Reviewed | +0.028 |
ities | +0.028 |
Collider | +0.028 |
romeda | +0.027 |
Neg logit contributions | |
tera | -0.033 |
river | -0.030 |
ograp | -0.026 |
wcsstore | -0.026 |
ppo | -0.025 |
Token | Others |
Token ID | 12691 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | focused |
Token ID | 5670 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.008 |
ities | +0.008 |
Collider | +0.008 |
romeda | +0.008 |
Neg logit contributions | |
tera | -0.012 |
river | -0.011 |
ograp | -0.010 |
wcsstore | -0.010 |
ppo | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | -6.52e-02 |
Pos logit contributions | |
alities | +0.033 |
Reviewed | +0.033 |
ities | +0.032 |
Collider | +0.031 |
romeda | +0.031 |
Neg logit contributions | |
tera | -0.044 |
river | -0.040 |
ograp | -0.036 |
wcsstore | -0.035 |
ppo | -0.035 |
Token | Robin |
Token ID | 12325 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
alities | +0.014 |
Reviewed | +0.013 |
ities | +0.013 |
Collider | +0.013 |
romeda | +0.013 |
Neg logit contributions | |
tera | -0.018 |
river | -0.017 |
ograp | -0.015 |
wcsstore | -0.014 |
ppo | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -3.66e-03 |
Pos logit contributions | |
tera | +0.004 |
river | +0.004 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.003 |
Reviewed | -0.003 |
ities | -0.003 |
Collider | -0.003 |
romeda | -0.003 |
Token | Cyborg |
Token ID | 46114 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
alities | +0.001 |
Reviewed | +0.001 |
ities | +0.001 |
Collider | +0.001 |
romeda | +0.001 |
Neg logit contributions | |
tera | -0.001 |
river | -0.001 |
ograp | -0.001 |
wcsstore | -0.001 |
ppo | -0.001 |
Token | ... |
Token ID | 986 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
tera | +0.166 |
river | +0.151 |
ograp | +0.134 |
wcsstore | +0.131 |
ppo | +0.130 |
Neg logit contributions | |
alities | -0.128 |
Reviewed | -0.127 |
ities | -0.125 |
Collider | -0.122 |
romeda | -0.120 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
alities | +0.249 |
ities | +0.246 |
Reviewed | +0.245 |
Collider | +0.238 |
romeda | +0.234 |
Neg logit contributions | |
tera | -0.342 |
river | -0.310 |
ograp | -0.275 |
wcsstore | -0.271 |
ppo | -0.267 |
Token | the |
Token ID | 262 |
Feature activation | -1.68e-03 |
Pos logit contributions | |
alities | +0.002 |
Reviewed | +0.002 |
ities | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.003 |
wcsstore | -0.003 |
ppo | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
alities | +0.000 |
Reviewed | +0.000 |
ities | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | rel |
Token ID | 823 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
alities | +0.039 |
Reviewed | +0.038 |
ities | +0.038 |
Collider | +0.037 |
romeda | +0.036 |
Neg logit contributions | |
tera | -0.054 |
river | -0.049 |
ograp | -0.043 |
wcsstore | -0.043 |
ppo | -0.042 |
Token | atable |
Token ID | 21156 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
alities | +0.022 |
Reviewed | +0.021 |
ities | +0.021 |
Collider | +0.021 |
romeda | +0.020 |
Neg logit contributions | |
tera | -0.044 |
river | -0.041 |
ograp | -0.037 |
wcsstore | -0.036 |
ppo | -0.036 |
Token | Richard |
Token ID | 6219 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
alities | +0.083 |
Reviewed | +0.082 |
ities | +0.081 |
Collider | +0.079 |
romeda | +0.078 |
Neg logit contributions | |
tera | -0.113 |
river | -0.103 |
ograp | -0.091 |
wcsstore | -0.089 |
ppo | -0.088 |
Token | Dawkins |
Token ID | 38922 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
tera | +0.008 |
river | +0.008 |
ograp | +0.007 |
wcsstore | +0.007 |
ppo | +0.006 |
Neg logit contributions | |
alities | -0.006 |
ities | -0.006 |
Reviewed | -0.006 |
Collider | -0.006 |
romeda | -0.006 |
Token | off |
Token ID | 572 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
tera | +0.189 |
river | +0.171 |
ograp | +0.151 |
wcsstore | +0.147 |
ppo | +0.146 |
Neg logit contributions | |
alities | -0.152 |
Reviewed | -0.150 |
ities | -0.149 |
Collider | -0.146 |
romeda | -0.144 |
Token | his |
Token ID | 465 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
tera | +0.114 |
river | +0.104 |
ograp | +0.092 |
wcsstore | +0.090 |
ppo | +0.089 |
Neg logit contributions | |
alities | -0.080 |
ities | -0.079 |
Reviewed | -0.079 |
Collider | -0.076 |
romeda | -0.076 |
Token | church |
Token ID | 4928 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
tera | +0.003 |
river | +0.002 |
ograp | +0.002 |
wcsstore | +0.002 |
ppo | +0.002 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
romeda | -0.002 |
Collider | -0.002 |
Token | grounds |
Token ID | 9384 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
alities | +0.007 |
Reviewed | +0.007 |
ities | +0.007 |
Collider | +0.007 |
romeda | +0.007 |
Neg logit contributions | |
tera | -0.010 |
river | -0.009 |
ograp | -0.008 |
wcsstore | -0.007 |
ppo | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
alities | +0.185 |
Reviewed | +0.182 |
ities | +0.182 |
Collider | +0.177 |
romeda | +0.175 |
Neg logit contributions | |
tera | -0.229 |
river | -0.207 |
ograp | -0.182 |
wcsstore | -0.178 |
ppo | -0.177 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
alities | +0.003 |
ities | +0.003 |
Reviewed | +0.003 |
Collider | +0.003 |
romeda | +0.003 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
alities | +0.005 |
ities | +0.005 |
Reviewed | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.006 |
river | -0.005 |
ograp | -0.005 |
wcsstore | -0.004 |
ppo | -0.004 |
Token | About |
Token ID | 8585 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
alities | +0.002 |
ities | +0.002 |
Reviewed | +0.002 |
Collider | +0.002 |
romeda | +0.002 |
Neg logit contributions | |
tera | -0.003 |
river | -0.003 |
ograp | -0.002 |
wcsstore | -0.002 |
ppo | -0.002 |
Token | former |
Token ID | 1966 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
tera | +0.069 |
river | +0.062 |
ograp | +0.055 |
wcsstore | +0.054 |
ppo | +0.053 |
Neg logit contributions | |
alities | -0.052 |
ities | -0.051 |
Reviewed | -0.051 |
Collider | -0.049 |
romeda | -0.049 |
Token | � |
Token ID | 134 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
alities | +0.033 |
Reviewed | +0.033 |
ities | +0.033 |
Collider | +0.032 |
romeda | +0.031 |
Neg logit contributions | |
tera | -0.045 |
river | -0.040 |
ograp | -0.036 |
wcsstore | -0.035 |
ppo | -0.035 |
Token | � |
Token ID | 119 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
alities | +0.033 |
ities | +0.032 |
Reviewed | +0.032 |
Collider | +0.031 |
romeda | +0.031 |
Neg logit contributions | |
tera | -0.042 |
river | -0.037 |
ograp | -0.033 |
wcsstore | -0.033 |
ppo | -0.032 |
Token | u |
Token ID | 84 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
alities | +0.040 |
Reviewed | +0.039 |
ities | +0.039 |
Collider | +0.038 |
romeda | +0.038 |
Neg logit contributions | |
tera | -0.053 |
river | -0.048 |
ograp | -0.042 |
wcsstore | -0.042 |
ppo | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
alities | +0.045 |
Reviewed | +0.045 |
ities | +0.044 |
Collider | +0.043 |
romeda | +0.043 |
Neg logit contributions | |
tera | -0.061 |
river | -0.055 |
ograp | -0.049 |
wcsstore | -0.048 |
ppo | -0.048 |
Token | E |
Token ID | 412 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
alities | +0.000 |
ities | +0.000 |
Reviewed | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | pen |
Token ID | 3112 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
alities | +0.073 |
Reviewed | +0.073 |
ities | +0.072 |
Collider | +0.070 |
romeda | +0.069 |
Neg logit contributions | |
tera | -0.123 |
river | -0.113 |
ograp | -0.101 |
wcsstore | -0.100 |
ppo | -0.099 |
Token | a |
Token ID | 64 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
alities | +0.213 |
ities | +0.211 |
Reviewed | +0.210 |
Collider | +0.205 |
romeda | +0.202 |
Neg logit contributions | |
tera | -0.269 |
river | -0.243 |
ograp | -0.214 |
wcsstore | -0.211 |
ppo | -0.208 |
Token | mo |
Token ID | 6941 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
alities | +0.040 |
Reviewed | +0.040 |
ities | +0.040 |
Collider | +0.039 |
romeda | +0.038 |
Neg logit contributions | |
tera | -0.058 |
river | -0.052 |
ograp | -0.047 |
wcsstore | -0.046 |
ppo | -0.045 |
Token | ek |
Token ID | 988 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
tera | +0.090 |
river | +0.081 |
ograp | +0.072 |
wcsstore | +0.071 |
ppo | +0.070 |
Neg logit contributions | |
alities | -0.065 |
Reviewed | -0.064 |
ities | -0.064 |
Collider | -0.063 |
romeda | -0.062 |
Token | ahi |
Token ID | 32810 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
tera | +0.044 |
river | +0.040 |
ograp | +0.035 |
wcsstore | +0.035 |
ppo | +0.034 |
Neg logit contributions | |
alities | -0.036 |
Reviewed | -0.035 |
ities | -0.035 |
Collider | -0.035 |
romeda | -0.034 |
Token | |
Token ID | 220 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
alities | +0.075 |
Reviewed | +0.074 |
ities | +0.074 |
Collider | +0.072 |
romeda | +0.070 |
Neg logit contributions | |
tera | -0.107 |
river | -0.097 |
ograp | -0.087 |
wcsstore | -0.085 |
ppo | -0.084 |
Token | as |
Token ID | 355 |
Feature activation | -7.95e-02 |
Pos logit contributions | |
tera | +0.010 |
river | +0.009 |
ograp | +0.008 |
wcsstore | +0.008 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.007 |
ities | -0.007 |
Reviewed | -0.007 |
Collider | -0.007 |
romeda | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
alities | +0.016 |
Reviewed | +0.016 |
ities | +0.016 |
Collider | +0.015 |
romeda | +0.015 |
Neg logit contributions | |
tera | -0.023 |
river | -0.021 |
ograp | -0.018 |
wcsstore | -0.018 |
ppo | -0.018 |
Token | combination |
Token ID | 6087 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
tera | +0.003 |
river | +0.003 |
ograp | +0.003 |
wcsstore | +0.003 |
ppo | +0.003 |
Neg logit contributions | |
alities | -0.002 |
Reviewed | -0.002 |
ities | -0.002 |
Collider | -0.002 |
romeda | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -7.06e-04 |
Pos logit contributions | |
tera | +0.139 |
river | +0.126 |
ograp | +0.111 |
wcsstore | +0.109 |
ppo | +0.107 |
Neg logit contributions | |
alities | -0.115 |
ities | -0.113 |
Reviewed | -0.113 |
Collider | -0.110 |
romeda | -0.109 |
Token | byte |
Token ID | 18022 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
alities | +0.000 |
Reviewed | +0.000 |
ities | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | size |
Token ID | 2546 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
alities | +0.094 |
ities | +0.093 |
Reviewed | +0.092 |
Collider | +0.089 |
romeda | +0.087 |
Neg logit contributions | |
tera | -0.142 |
river | -0.129 |
ograp | -0.115 |
wcsstore | -0.114 |
ppo | -0.112 |
Token | and |
Token ID | 290 |
Feature activation | -5.30e-04 |
Pos logit contributions | |
alities | +0.161 |
ities | +0.159 |
Reviewed | +0.157 |
Collider | +0.154 |
romeda | +0.150 |
Neg logit contributions | |
tera | -0.227 |
river | -0.206 |
ograp | -0.183 |
wcsstore | -0.181 |
ppo | -0.177 |
Token | object |
Token ID | 2134 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
alities | +0.000 |
Reviewed | +0.000 |
ities | +0.000 |
Collider | +0.000 |
romeda | +0.000 |
Neg logit contributions | |
tera | -0.000 |
river | -0.000 |
ograp | -0.000 |
wcsstore | -0.000 |
ppo | -0.000 |
Token | pointers |
Token ID | 32007 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
alities | +0.009 |
Reviewed | +0.009 |
ities | +0.009 |
Collider | +0.009 |
romeda | +0.009 |
Neg logit contributions | |
tera | -0.024 |
river | -0.022 |
ograp | -0.020 |
wcsstore | -0.020 |
ppo | -0.020 |
Token | ). |
Token ID | 737 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
alities | +0.040 |
Reviewed | +0.040 |
ities | +0.039 |
Collider | +0.038 |
romeda | +0.038 |
Neg logit contributions | |
tera | -0.069 |
river | -0.063 |
ograp | -0.057 |
wcsstore | -0.056 |
ppo | -0.055 |
Token | You |
Token ID | 921 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
alities | +0.048 |
Reviewed | +0.047 |
ities | +0.047 |
Collider | +0.046 |
romeda | +0.045 |
Neg logit contributions | |
tera | -0.054 |
river | -0.049 |
ograp | -0.043 |
wcsstore | -0.042 |
ppo | -0.041 |
Token | tests |
Token ID | 5254 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
alities | +0.045 |
Reviewed | +0.045 |
ities | +0.045 |
Collider | +0.044 |
romeda | +0.043 |
Neg logit contributions | |
tera | -0.053 |
river | -0.048 |
ograp | -0.043 |
wcsstore | -0.042 |
ppo | -0.041 |
Token | undertaken |
Token ID | 21846 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
tera | +0.010 |
river | +0.010 |
ograp | +0.008 |
wcsstore | +0.008 |
ppo | +0.008 |
Neg logit contributions | |
alities | -0.008 |
Reviewed | -0.008 |
ities | -0.008 |
Collider | -0.008 |
romeda | -0.008 |
Token | after |
Token ID | 706 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
alities | +0.058 |
Reviewed | +0.058 |
ities | +0.057 |
Collider | +0.056 |
romeda | +0.055 |
Neg logit contributions | |
tera | -0.079 |
river | -0.072 |
ograp | -0.064 |
wcsstore | -0.063 |
ppo | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
tera | +0.033 |
river | +0.030 |
ograp | +0.026 |
wcsstore | +0.026 |
ppo | +0.025 |
Neg logit contributions | |
alities | -0.024 |
Reviewed | -0.023 |
ities | -0.023 |
Collider | -0.023 |
romeda | -0.023 |
Token | Gren |
Token ID | 19674 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
alities | +0.005 |
Reviewed | +0.005 |
ities | +0.004 |
romeda | +0.004 |
Collider | +0.004 |
Neg logit contributions | |
tera | -0.007 |
river | -0.006 |
ograp | -0.005 |
wcsstore | -0.005 |
ppo | -0.005 |
Token | fell |
Token ID | 23299 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
alities | +0.005 |
Reviewed | +0.005 |
ities | +0.005 |
Collider | +0.005 |
romeda | +0.005 |
Neg logit contributions | |
tera | -0.030 |
river | -0.028 |
ograp | -0.026 |
wcsstore | -0.025 |
ppo | -0.025 |
Token | Tower |
Token ID | 8765 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
alities | +0.209 |
ities | +0.206 |
Reviewed | +0.206 |
Collider | +0.201 |
romeda | +0.197 |
Neg logit contributions | |
tera | -0.254 |
river | -0.229 |
ograp | -0.203 |
wcsstore | -0.199 |
ppo | -0.196 |
Token | fire |
Token ID | 2046 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
tera | +0.028 |
river | +0.026 |
ograp | +0.023 |
wcsstore | +0.023 |
ppo | +0.022 |
Neg logit contributions | |
alities | -0.017 |
Reviewed | -0.017 |
ities | -0.017 |
romeda | -0.016 |
Collider | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
alities | +0.043 |
ities | +0.043 |
Reviewed | +0.042 |
Collider | +0.041 |
romeda | +0.041 |
Neg logit contributions | |
tera | -0.054 |
river | -0.049 |
ograp | -0.043 |
wcsstore | -0.042 |
ppo | -0.041 |
Token | according |
Token ID | 1864 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
tera | +0.001 |
river | +0.001 |
ograp | +0.000 |
wcsstore | +0.000 |
ppo | +0.000 |
Neg logit contributions | |
alities | -0.000 |
Reviewed | -0.000 |
ities | -0.000 |
Collider | -0.000 |
romeda | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
alities | +0.020 |
Reviewed | +0.020 |
ities | +0.020 |
Collider | +0.019 |
romeda | +0.019 |
Neg logit contributions | |
tera | -0.023 |
river | -0.021 |
ograp | -0.018 |
wcsstore | -0.018 |
ppo | -0.018 |