Token |
|
Token ID | 198 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
blance | +0.022 |
uments | +0.020 |
arthed | +0.020 |
ondon | +0.019 |
nesota | +0.018 |
Neg logit contributions | |
ogens | -0.016 |
Debor | -0.015 |
BUR | -0.015 |
osit | -0.014 |
supervision | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | +7.87e-02 |
Pos logit contributions | |
blance | +0.020 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.015 |
Debor | -0.014 |
BUR | -0.014 |
osit | -0.014 |
supervision | -0.013 |
Token | T |
Token ID | 309 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
blance | +0.030 |
uments | +0.028 |
arthed | +0.028 |
ondon | +0.026 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.024 |
Debor | -0.022 |
BUR | -0.022 |
osit | -0.021 |
supervision | -0.021 |
Token | iki |
Token ID | 5580 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
blance | +0.122 |
uments | +0.115 |
arthed | +0.113 |
ondon | +0.108 |
nesota | +0.102 |
Neg logit contributions | |
ogens | -0.097 |
Debor | -0.091 |
BUR | -0.088 |
osit | -0.086 |
supervision | -0.084 |
Token | Tw |
Token ID | 1815 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ogens | +0.063 |
Debor | +0.059 |
BUR | +0.057 |
osit | +0.056 |
supervision | +0.055 |
Neg logit contributions | |
blance | -0.074 |
uments | -0.069 |
arthed | -0.068 |
ondon | -0.065 |
nesota | -0.062 |
Token | irl |
Token ID | 1901 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
blance | +0.102 |
arthed | +0.094 |
uments | +0.094 |
ondon | +0.087 |
nesota | +0.082 |
Neg logit contributions | |
ogens | -0.122 |
Debor | -0.113 |
BUR | -0.111 |
osit | -0.111 |
iated | -0.108 |
Token | thrill |
Token ID | 28576 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
blance | +0.417 |
uments | +0.392 |
arthed | +0.388 |
ondon | +0.370 |
nesota | +0.352 |
Neg logit contributions | |
ogens | -0.326 |
Debor | -0.302 |
BUR | -0.294 |
osit | -0.286 |
supervision | -0.281 |
Token | ride |
Token ID | 6594 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
blance | +0.087 |
uments | +0.083 |
arthed | +0.082 |
ondon | +0.078 |
nesota | +0.075 |
Neg logit contributions | |
ogens | -0.053 |
Debor | -0.049 |
BUR | -0.048 |
osit | -0.046 |
supervision | -0.045 |
Token | at |
Token ID | 379 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.008 |
arthed | +0.008 |
ondon | +0.008 |
nesota | +0.007 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | California |
Token ID | 3442 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.011 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.011 |
BUR | -0.010 |
osit | -0.010 |
supervision | -0.010 |
Token | 's |
Token ID | 338 |
Feature activation | -5.48e-03 |
Pos logit contributions | |
blance | +0.061 |
uments | +0.057 |
arthed | +0.056 |
ondon | +0.053 |
nesota | +0.050 |
Neg logit contributions | |
ogens | -0.062 |
Debor | -0.059 |
BUR | -0.057 |
osit | -0.056 |
supervision | -0.055 |
Token | More |
Token ID | 3125 |
Feature activation | +8.07e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | Advanced |
Token ID | 13435 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
blance | +0.030 |
uments | +0.028 |
arthed | +0.028 |
ondon | +0.026 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.025 |
Debor | -0.024 |
BUR | -0.023 |
osit | -0.022 |
supervision | -0.022 |
Token | Ruby |
Token ID | 10888 |
Feature activation | +9.68e-02 |
Pos logit contributions | |
blance | +0.159 |
uments | +0.149 |
arthed | +0.148 |
ondon | +0.140 |
nesota | +0.133 |
Neg logit contributions | |
ogens | -0.143 |
Debor | -0.134 |
BUR | -0.131 |
osit | -0.127 |
supervision | -0.125 |
Token | Method |
Token ID | 11789 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
blance | +0.036 |
uments | +0.033 |
arthed | +0.033 |
ondon | +0.031 |
nesota | +0.030 |
Neg logit contributions | |
ogens | -0.031 |
Debor | -0.029 |
BUR | -0.028 |
osit | -0.027 |
supervision | -0.027 |
Token | Arg |
Token ID | 20559 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
blance | +0.077 |
uments | +0.071 |
arthed | +0.071 |
ondon | +0.067 |
nesota | +0.063 |
Neg logit contributions | |
ogens | -0.078 |
Debor | -0.073 |
BUR | -0.071 |
osit | -0.070 |
supervision | -0.068 |
Token | uments |
Token ID | 2886 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
blance | +0.005 |
arthed | +0.002 |
uments | +0.000 |
ondon | -0.000 |
nesota | -0.002 |
Neg logit contributions | |
ogens | -0.070 |
Debor | -0.067 |
BUR | -0.066 |
osit | -0.066 |
supervision | -0.065 |
Token | – |
Token ID | 784 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
blance | +0.414 |
uments | +0.388 |
arthed | +0.386 |
ondon | +0.367 |
nesota | +0.350 |
Neg logit contributions | |
ogens | -0.325 |
Debor | -0.303 |
BUR | -0.293 |
osit | -0.285 |
supervision | -0.280 |
Token | H |
Token ID | 367 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
blance | +0.024 |
uments | +0.023 |
arthed | +0.022 |
ondon | +0.021 |
nesota | +0.020 |
Neg logit contributions | |
ogens | -0.021 |
Debor | -0.020 |
BUR | -0.019 |
osit | -0.018 |
supervision | -0.018 |
Token | ashes |
Token ID | 7465 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
ogens | +0.073 |
Debor | +0.068 |
BUR | +0.066 |
osit | +0.065 |
supervision | +0.064 |
Neg logit contributions | |
blance | -0.078 |
uments | -0.073 |
arthed | -0.072 |
ondon | -0.068 |
nesota | -0.065 |
Token | And |
Token ID | 843 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
blance | +0.091 |
uments | +0.086 |
arthed | +0.085 |
ondon | +0.081 |
nesota | +0.078 |
Neg logit contributions | |
ogens | -0.070 |
Debor | -0.065 |
BUR | -0.063 |
osit | -0.061 |
supervision | -0.060 |
Token | Block |
Token ID | 9726 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
blance | +0.037 |
uments | +0.035 |
arthed | +0.035 |
ondon | +0.033 |
nesota | +0.031 |
Neg logit contributions | |
ogens | -0.033 |
Debor | -0.031 |
BUR | -0.030 |
osit | -0.030 |
supervision | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +4.50e-02 |
Pos logit contributions | |
blance | +0.001 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.000 |
nesota | +0.000 |
Neg logit contributions | |
ogens | -0.000 |
Debor | -0.000 |
BUR | -0.000 |
osit | -0.000 |
supervision | -0.000 |
Token | Gen |
Token ID | 5215 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
blance | +0.017 |
uments | +0.016 |
arthed | +0.016 |
ondon | +0.015 |
nesota | +0.014 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.012 |
supervision | -0.012 |
Token | ç |
Token ID | 16175 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.019 |
BUR | +0.019 |
osit | +0.018 |
supervision | +0.018 |
Neg logit contributions | |
blance | -0.017 |
uments | -0.016 |
arthed | -0.016 |
ondon | -0.015 |
nesota | -0.014 |
Token | ler |
Token ID | 1754 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
blance | +0.012 |
uments | +0.011 |
arthed | +0.011 |
ondon | +0.010 |
nesota | +0.010 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.010 |
BUR | -0.010 |
osit | -0.009 |
supervision | -0.009 |
Token | b |
Token ID | 65 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
blance | +0.098 |
uments | +0.092 |
arthed | +0.091 |
ondon | +0.087 |
nesota | +0.083 |
Neg logit contributions | |
ogens | -0.083 |
Debor | -0.077 |
BUR | -0.075 |
osit | -0.073 |
supervision | -0.071 |
Token | irl |
Token ID | 1901 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
blance | +0.066 |
uments | +0.062 |
arthed | +0.062 |
ondon | +0.058 |
nesota | +0.056 |
Neg logit contributions | |
ogens | -0.058 |
Debor | -0.053 |
BUR | -0.052 |
osit | -0.051 |
supervision | -0.050 |
Token | i |
Token ID | 72 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
blance | +0.478 |
uments | +0.452 |
arthed | +0.447 |
ondon | +0.435 |
aiden | +0.413 |
Neg logit contributions | |
ogens | -0.254 |
Debor | -0.238 |
BUR | -0.227 |
osit | -0.214 |
supervision | -0.212 |
Token | ğ |
Token ID | 33133 |
Feature activation | +9.48e-02 |
Pos logit contributions | |
blance | +0.102 |
uments | +0.096 |
arthed | +0.095 |
ondon | +0.091 |
nesota | +0.086 |
Neg logit contributions | |
ogens | -0.082 |
Debor | -0.076 |
BUR | -0.074 |
osit | -0.072 |
supervision | -0.070 |
Token | i |
Token ID | 72 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
blance | +0.035 |
uments | +0.033 |
arthed | +0.032 |
ondon | +0.031 |
nesota | +0.029 |
Neg logit contributions | |
ogens | -0.030 |
Debor | -0.028 |
BUR | -0.027 |
osit | -0.027 |
supervision | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
blance | +0.090 |
uments | +0.084 |
arthed | +0.083 |
ondon | +0.079 |
nesota | +0.075 |
Neg logit contributions | |
ogens | -0.071 |
Debor | -0.067 |
BUR | -0.065 |
osit | -0.063 |
supervision | -0.062 |
Token | � |
Token ID | 447 |
Feature activation | +4.80e-03 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.008 |
arthed | +0.008 |
ondon | +0.008 |
nesota | +0.007 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | generic |
Token ID | 14276 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
blance | +0.052 |
uments | +0.049 |
arthed | +0.049 |
ondon | +0.047 |
nesota | +0.045 |
Neg logit contributions | |
ogens | -0.037 |
Debor | -0.035 |
BUR | -0.033 |
osit | -0.033 |
supervision | -0.032 |
Token | equivalents |
Token ID | 40255 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
blance | +0.027 |
uments | +0.026 |
arthed | +0.025 |
ondon | +0.024 |
nesota | +0.023 |
Neg logit contributions | |
ogens | -0.020 |
Debor | -0.018 |
BUR | -0.018 |
osit | -0.017 |
supervision | -0.017 |
Token | at |
Token ID | 379 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
blance | +0.037 |
uments | +0.034 |
arthed | +0.034 |
ondon | +0.032 |
nesota | +0.031 |
Neg logit contributions | |
ogens | -0.029 |
Debor | -0.027 |
BUR | -0.027 |
osit | -0.026 |
supervision | -0.025 |
Token | treating |
Token ID | 13622 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.008 |
arthed | +0.008 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.005 |
supervision | -0.005 |
Token | hyp |
Token ID | 5328 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
blance | +0.020 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.015 |
Debor | -0.014 |
BUR | -0.014 |
osit | -0.013 |
supervision | -0.013 |
Token | othy |
Token ID | 14863 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
blance | +0.089 |
uments | +0.081 |
arthed | +0.080 |
ondon | +0.074 |
nesota | +0.068 |
Neg logit contributions | |
ogens | -0.156 |
Debor | -0.146 |
BUR | -0.144 |
osit | -0.143 |
iated | -0.140 |
Token | roid |
Token ID | 3882 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
blance | +0.263 |
uments | +0.241 |
arthed | +0.236 |
ondon | +0.218 |
aiden | +0.200 |
Neg logit contributions | |
ogens | -0.457 |
Debor | -0.441 |
BUR | -0.430 |
supervision | -0.417 |
osit | -0.417 |
Token | ism |
Token ID | 1042 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
blance | +0.174 |
uments | +0.167 |
arthed | +0.164 |
ondon | +0.159 |
nesota | +0.154 |
Neg logit contributions | |
ogens | -0.056 |
Debor | -0.050 |
BUR | -0.047 |
osit | -0.044 |
supervision | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ogens | +0.098 |
Debor | +0.091 |
BUR | +0.088 |
osit | +0.086 |
supervision | +0.084 |
Neg logit contributions | |
blance | -0.122 |
uments | -0.115 |
arthed | -0.114 |
ondon | -0.108 |
nesota | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | -5.56e-03 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.005 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | icide |
Token ID | 5285 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
blance | +0.064 |
uments | +0.058 |
arthed | +0.057 |
ondon | +0.053 |
nesota | +0.048 |
Neg logit contributions | |
ogens | -0.110 |
Debor | -0.104 |
BUR | -0.102 |
osit | -0.101 |
supervision | -0.099 |
Token | pre |
Token ID | 3866 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
blance | +0.152 |
uments | +0.143 |
arthed | +0.141 |
ondon | +0.134 |
nesota | +0.128 |
Neg logit contributions | |
ogens | -0.124 |
Debor | -0.115 |
BUR | -0.112 |
osit | -0.110 |
supervision | -0.107 |
Token | vention |
Token ID | 4018 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.011 |
BUR | +0.011 |
osit | +0.011 |
supervision | +0.011 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.013 |
arthed | -0.013 |
ondon | -0.012 |
nesota | -0.012 |
Token | / |
Token ID | 14 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
ogens | +0.044 |
Debor | +0.041 |
BUR | +0.040 |
osit | +0.039 |
supervision | +0.038 |
Neg logit contributions | |
blance | -0.052 |
uments | -0.049 |
arthed | -0.049 |
ondon | -0.046 |
nesota | -0.044 |
Token | doc |
Token ID | 15390 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
ogens | +0.014 |
Debor | +0.013 |
BUR | +0.013 |
osit | +0.012 |
supervision | +0.012 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.013 |
arthed | -0.013 |
ondon | -0.012 |
nesota | -0.012 |
Token | uments |
Token ID | 2886 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
blance | +0.003 |
arthed | +0.002 |
uments | +0.001 |
ondon | +0.001 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.021 |
Debor | -0.020 |
BUR | -0.020 |
osit | -0.020 |
iated | -0.019 |
Token | / |
Token ID | 14 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
blance | +0.405 |
uments | +0.380 |
arthed | +0.377 |
ondon | +0.359 |
nesota | +0.342 |
Neg logit contributions | |
ogens | -0.319 |
Debor | -0.296 |
BUR | -0.288 |
osit | -0.280 |
supervision | -0.274 |
Token | older |
Token ID | 19892 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
ogens | +0.018 |
Debor | +0.016 |
BUR | +0.016 |
osit | +0.016 |
supervision | +0.015 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.017 |
arthed | -0.017 |
ondon | -0.016 |
nesota | -0.016 |
Token | adult |
Token ID | 49922 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
blance | +0.147 |
uments | +0.137 |
arthed | +0.136 |
ondon | +0.129 |
nesota | +0.123 |
Neg logit contributions | |
ogens | -0.125 |
Debor | -0.116 |
BUR | -0.113 |
osit | -0.110 |
supervision | -0.108 |
Token | / |
Token ID | 14 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
blance | +0.050 |
uments | +0.046 |
arthed | +0.046 |
ondon | +0.043 |
nesota | +0.041 |
Neg logit contributions | |
ogens | -0.052 |
Debor | -0.049 |
BUR | -0.048 |
osit | -0.047 |
supervision | -0.046 |
Token | plan |
Token ID | 11578 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.018 |
BUR | +0.018 |
osit | +0.018 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.017 |
arthed | -0.017 |
ondon | -0.016 |
nesota | -0.015 |
Token | War |
Token ID | 1810 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
blance | +0.129 |
uments | +0.121 |
arthed | +0.120 |
ondon | +0.114 |
nesota | +0.108 |
Neg logit contributions | |
ogens | -0.112 |
Debor | -0.105 |
BUR | -0.102 |
osit | -0.099 |
supervision | -0.098 |
Token | call |
Token ID | 13345 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ogens | +0.070 |
Debor | +0.065 |
BUR | +0.064 |
osit | +0.062 |
supervision | +0.061 |
Neg logit contributions | |
blance | -0.072 |
uments | -0.067 |
arthed | -0.066 |
ondon | -0.063 |
nesota | -0.060 |
Token | er |
Token ID | 263 |
Feature activation | +8.97e-02 |
Pos logit contributions | |
blance | +0.068 |
uments | +0.063 |
arthed | +0.062 |
ondon | +0.059 |
nesota | +0.058 |
Neg logit contributions | |
ogens | -0.062 |
Debor | -0.058 |
BUR | -0.057 |
osit | -0.056 |
supervision | -0.055 |
Token | vs |
Token ID | 3691 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
blance | +0.036 |
uments | +0.034 |
arthed | +0.034 |
ondon | +0.032 |
nesota | +0.031 |
Neg logit contributions | |
ogens | -0.025 |
Debor | -0.023 |
BUR | -0.022 |
osit | -0.022 |
supervision | -0.021 |
Token | Sem |
Token ID | 12449 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ogens | +0.057 |
Debor | +0.053 |
BUR | +0.052 |
osit | +0.050 |
supervision | +0.049 |
Neg logit contributions | |
blance | -0.064 |
uments | -0.060 |
arthed | -0.059 |
ondon | -0.056 |
nesota | -0.053 |
Token | blance |
Token ID | 42757 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ogens | +0.071 |
Debor | +0.067 |
BUR | +0.066 |
osit | +0.065 |
iated | +0.065 |
Neg logit contributions | |
blance | -0.025 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.020 |
nesota | -0.018 |
Token | An |
Token ID | 1052 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
blance | +0.386 |
uments | +0.363 |
arthed | +0.359 |
ondon | +0.342 |
nesota | +0.324 |
Neg logit contributions | |
ogens | -0.334 |
Debor | -0.312 |
BUR | -0.303 |
osit | -0.295 |
supervision | -0.289 |
Token | vil |
Token ID | 2991 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
blance | +0.078 |
uments | +0.073 |
arthed | +0.072 |
ondon | +0.069 |
nesota | +0.065 |
Neg logit contributions | |
ogens | -0.066 |
Debor | -0.062 |
BUR | -0.060 |
osit | -0.059 |
supervision | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -1.13e-03 |
Pos logit contributions | |
ogens | +0.017 |
Debor | +0.016 |
BUR | +0.015 |
osit | +0.015 |
supervision | +0.015 |
Neg logit contributions | |
blance | -0.021 |
uments | -0.020 |
arthed | -0.020 |
ondon | -0.019 |
nesota | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ogens | +0.000 |
Debor | +0.000 |
BUR | +0.000 |
osit | +0.000 |
supervision | +0.000 |
Neg logit contributions | |
blance | -0.000 |
uments | -0.000 |
arthed | -0.000 |
ondon | -0.000 |
nesota | -0.000 |
Token | V |
Token ID | 53 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
blance | +0.007 |
uments | +0.007 |
arthed | +0.007 |
ondon | +0.006 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.005 |
Token | secretary |
Token ID | 7705 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.006 |
BUR | +0.005 |
osit | +0.005 |
iated | +0.005 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.007 |
aiden | -0.006 |
Token | Fer |
Token ID | 12880 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ogens | +0.067 |
Debor | +0.062 |
BUR | +0.061 |
osit | +0.059 |
iated | +0.057 |
Neg logit contributions | |
blance | -0.086 |
uments | -0.081 |
arthed | -0.080 |
ondon | -0.076 |
aiden | -0.072 |
Token | id |
Token ID | 312 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ogens | +0.092 |
Debor | +0.086 |
BUR | +0.084 |
osit | +0.082 |
supervision | +0.080 |
Neg logit contributions | |
blance | -0.101 |
uments | -0.094 |
arthed | -0.094 |
ondon | -0.088 |
nesota | -0.084 |
Token | un |
Token ID | 403 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
ogens | +0.046 |
Debor | +0.043 |
BUR | +0.042 |
osit | +0.040 |
supervision | +0.040 |
Neg logit contributions | |
blance | -0.049 |
uments | -0.046 |
arthed | -0.046 |
ondon | -0.043 |
nesota | -0.041 |
Token | Sin |
Token ID | 10884 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ogens | +0.042 |
Debor | +0.039 |
BUR | +0.038 |
osit | +0.037 |
supervision | +0.036 |
Neg logit contributions | |
blance | -0.048 |
uments | -0.045 |
arthed | -0.044 |
ondon | -0.042 |
nesota | -0.040 |
Token | irl |
Token ID | 1901 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ogens | +0.054 |
Debor | +0.052 |
BUR | +0.051 |
osit | +0.050 |
supervision | +0.050 |
Neg logit contributions | |
blance | -0.024 |
uments | -0.022 |
arthed | -0.021 |
ondon | -0.019 |
nesota | -0.017 |
Token | i |
Token ID | 72 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
blance | +0.323 |
uments | +0.300 |
arthed | +0.296 |
ondon | +0.280 |
nesota | +0.261 |
Neg logit contributions | |
ogens | -0.385 |
Debor | -0.364 |
BUR | -0.356 |
osit | -0.347 |
supervision | -0.342 |
Token | oglu |
Token ID | 49006 |
Feature activation | -5.59e-02 |
Pos logit contributions | |
blance | +0.086 |
uments | +0.081 |
arthed | +0.080 |
ondon | +0.077 |
aiden | +0.073 |
Neg logit contributions | |
ogens | -0.064 |
Debor | -0.060 |
BUR | -0.058 |
osit | -0.056 |
iated | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
ogens | +0.017 |
Debor | +0.016 |
BUR | +0.015 |
osit | +0.015 |
supervision | +0.014 |
Neg logit contributions | |
blance | -0.021 |
uments | -0.020 |
arthed | -0.020 |
ondon | -0.019 |
nesota | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
ogens | +0.014 |
Debor | +0.013 |
BUR | +0.013 |
osit | +0.012 |
supervision | +0.012 |
Neg logit contributions | |
blance | -0.017 |
uments | -0.016 |
arthed | -0.016 |
ondon | -0.015 |
nesota | -0.015 |
Token | official |
Token ID | 1743 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.003 |
Token | acknowledged |
Token ID | 10810 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ogens | +0.016 |
Debor | +0.015 |
BUR | +0.014 |
osit | +0.014 |
supervision | +0.014 |
Neg logit contributions | |
blance | -0.018 |
uments | -0.017 |
arthed | -0.017 |
ondon | -0.016 |
nesota | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
ogens | +0.034 |
Debor | +0.032 |
BUR | +0.031 |
osit | +0.030 |
supervision | +0.030 |
Neg logit contributions | |
blance | -0.041 |
uments | -0.039 |
arthed | -0.038 |
ondon | -0.037 |
nesota | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.010 |
BUR | +0.010 |
osit | +0.010 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.013 |
arthed | -0.013 |
ondon | -0.012 |
nesota | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.011 |
BUR | +0.011 |
osit | +0.010 |
supervision | +0.010 |
Neg logit contributions | |
blance | -0.016 |
uments | -0.015 |
arthed | -0.015 |
ondon | -0.014 |
nesota | -0.014 |
Token | Mon |
Token ID | 9069 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.011 |
BUR | +0.011 |
osit | +0.010 |
supervision | +0.010 |
Neg logit contributions | |
blance | -0.016 |
uments | -0.016 |
arthed | -0.015 |
ondon | -0.015 |
nesota | -0.014 |
Token | uments |
Token ID | 2886 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
blance | +0.002 |
arthed | +0.001 |
uments | +0.001 |
ondon | +0.000 |
nesota | -0.000 |
Neg logit contributions | |
ogens | -0.021 |
Debor | -0.021 |
BUR | -0.020 |
osit | -0.020 |
iated | -0.020 |
Token | raised |
Token ID | 4376 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
blance | +0.381 |
uments | +0.359 |
arthed | +0.354 |
ondon | +0.338 |
nesota | +0.320 |
Neg logit contributions | |
ogens | -0.313 |
Debor | -0.292 |
BUR | -0.284 |
osit | -0.277 |
supervision | -0.270 |
Token | in |
Token ID | 287 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
blance | +0.027 |
uments | +0.025 |
arthed | +0.025 |
ondon | +0.024 |
nesota | +0.023 |
Neg logit contributions | |
ogens | -0.025 |
Debor | -0.023 |
BUR | -0.023 |
osit | -0.022 |
supervision | -0.022 |
Token | recent |
Token ID | 2274 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.008 |
BUR | +0.008 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.010 |
arthed | -0.010 |
ondon | -0.009 |
nesota | -0.009 |
Token | years |
Token ID | 812 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.005 |
supervision | -0.004 |
Token | better |
Token ID | 1365 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.009 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.008 |
nesota | -0.008 |
Token | ton |
Token ID | 1122 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
ogens | +0.048 |
Debor | +0.043 |
BUR | +0.041 |
osit | +0.039 |
supervision | +0.037 |
Neg logit contributions | |
blance | -0.132 |
uments | -0.126 |
arthed | -0.125 |
ondon | -0.120 |
nesota | -0.116 |
Token | , |
Token ID | 11 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
ogens | +0.121 |
Debor | +0.112 |
BUR | +0.109 |
osit | +0.106 |
supervision | +0.104 |
Neg logit contributions | |
blance | -0.156 |
uments | -0.147 |
arthed | -0.146 |
ondon | -0.139 |
nesota | -0.132 |
Token | Sam |
Token ID | 3409 |
Feature activation | +8.70e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | P |
Token ID | 350 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
blance | +0.033 |
uments | +0.031 |
arthed | +0.030 |
ondon | +0.029 |
nesota | +0.027 |
Neg logit contributions | |
ogens | -0.027 |
Debor | -0.025 |
BUR | -0.024 |
osit | -0.024 |
supervision | -0.023 |
Token | anche |
Token ID | 6362 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
blance | +0.011 |
uments | +0.010 |
arthed | +0.010 |
ondon | +0.010 |
nesota | +0.009 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.010 |
BUR | -0.010 |
osit | -0.010 |
supervision | -0.010 |
Token | vre |
Token ID | 43933 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
blance | +0.111 |
uments | +0.104 |
arthed | +0.103 |
ondon | +0.097 |
nesota | +0.091 |
Neg logit contributions | |
ogens | -0.122 |
Debor | -0.114 |
BUR | -0.112 |
osit | -0.109 |
iated | -0.107 |
Token | ( |
Token ID | 357 |
Feature activation | +4.34e-02 |
Pos logit contributions | |
blance | +0.373 |
uments | +0.351 |
arthed | +0.348 |
ondon | +0.332 |
nesota | +0.315 |
Neg logit contributions | |
ogens | -0.288 |
Debor | -0.267 |
BUR | -0.260 |
osit | -0.252 |
supervision | -0.247 |
Token | Sam |
Token ID | 16305 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
blance | +0.016 |
uments | +0.015 |
arthed | +0.015 |
ondon | +0.014 |
nesota | +0.013 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.012 |
osit | -0.012 |
supervision | -0.012 |
Token | � |
Token ID | 447 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
blance | +0.135 |
uments | +0.127 |
arthed | +0.126 |
ondon | +0.119 |
nesota | +0.114 |
Neg logit contributions | |
ogens | -0.111 |
Debor | -0.103 |
BUR | -0.101 |
osit | -0.098 |
supervision | -0.096 |
Token | � |
Token ID | 247 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
blance | +0.007 |
uments | +0.007 |
arthed | +0.007 |
ondon | +0.006 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | s |
Token ID | 82 |
Feature activation | +4.83e-02 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token | headed |
Token ID | 9153 |
Feature activation | +5.16e-02 |
Pos logit contributions | |
blance | +0.025 |
uments | +0.024 |
arthed | +0.024 |
ondon | +0.023 |
nesota | +0.021 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.018 |
BUR | -0.017 |
osit | -0.017 |
supervision | -0.017 |
Token | chance |
Token ID | 2863 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
blance | +0.020 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.015 |
Debor | -0.014 |
BUR | -0.014 |
osit | -0.013 |
supervision | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
blance | +0.018 |
uments | +0.017 |
arthed | +0.017 |
ondon | +0.016 |
nesota | +0.015 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.012 |
supervision | -0.012 |
Token | forcing |
Token ID | 10833 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.006 |
supervision | -0.006 |
Token | Gu |
Token ID | 1962 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
blance | +0.026 |
uments | +0.024 |
arthed | +0.024 |
ondon | +0.023 |
nesota | +0.022 |
Neg logit contributions | |
ogens | -0.022 |
Debor | -0.020 |
BUR | -0.020 |
osit | -0.019 |
supervision | -0.019 |
Token | iller |
Token ID | 4665 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
blance | +0.026 |
uments | +0.022 |
arthed | +0.022 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.087 |
Debor | -0.083 |
BUR | -0.082 |
osit | -0.081 |
iated | -0.081 |
Token | mo |
Token ID | 5908 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
blance | +0.233 |
uments | +0.211 |
arthed | +0.208 |
ondon | +0.192 |
nesota | +0.176 |
Neg logit contributions | |
ogens | -0.419 |
Debor | -0.399 |
BUR | -0.392 |
osit | -0.384 |
supervision | -0.379 |
Token | O |
Token ID | 440 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
blance | +0.217 |
uments | +0.203 |
arthed | +0.202 |
ondon | +0.191 |
nesota | +0.182 |
Neg logit contributions | |
ogens | -0.194 |
Debor | -0.182 |
BUR | -0.177 |
osit | -0.173 |
supervision | -0.169 |
Token | cho |
Token ID | 6679 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
blance | +0.084 |
uments | +0.080 |
arthed | +0.079 |
ondon | +0.076 |
nesota | +0.073 |
Neg logit contributions | |
ogens | -0.043 |
Debor | -0.039 |
BUR | -0.037 |
osit | -0.035 |
supervision | -0.035 |
Token | a |
Token ID | 64 |
Feature activation | +5.95e-02 |
Pos logit contributions | |
ogens | +0.043 |
Debor | +0.040 |
BUR | +0.039 |
osit | +0.039 |
supervision | +0.038 |
Neg logit contributions | |
blance | -0.041 |
uments | -0.039 |
arthed | -0.038 |
ondon | -0.036 |
nesota | -0.034 |
Token | into |
Token ID | 656 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
blance | +0.022 |
uments | +0.020 |
arthed | +0.020 |
ondon | +0.019 |
nesota | +0.018 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.018 |
BUR | -0.017 |
osit | -0.017 |
supervision | -0.016 |
Token | � |
Token ID | 447 |
Feature activation | +6.49e-03 |
Pos logit contributions | |
blance | +0.043 |
uments | +0.041 |
arthed | +0.041 |
ondon | +0.039 |
nesota | +0.037 |
Neg logit contributions | |
ogens | -0.025 |
Debor | -0.023 |
BUR | -0.022 |
osit | -0.021 |
supervision | -0.021 |
Token | � |
Token ID | 247 |
Feature activation | -1.70e-03 |
Pos logit contributions | |
blance | +0.002 |
uments | +0.002 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.000 |
BUR | +0.000 |
osit | +0.000 |
supervision | +0.000 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | o |
Token ID | 267 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.003 |
Token | eu |
Token ID | 12496 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.013 |
ondon | +0.013 |
nesota | +0.012 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.013 |
supervision | -0.012 |
Token | vre |
Token ID | 43933 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
ogens | +0.047 |
Debor | +0.045 |
BUR | +0.044 |
osit | +0.044 |
supervision | +0.043 |
Neg logit contributions | |
blance | -0.010 |
uments | -0.008 |
arthed | -0.008 |
ondon | -0.007 |
nesota | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
blance | +0.358 |
uments | +0.337 |
arthed | +0.333 |
ondon | +0.318 |
nesota | +0.301 |
Neg logit contributions | |
ogens | -0.290 |
Debor | -0.270 |
BUR | -0.263 |
osit | -0.255 |
supervision | -0.250 |
Token | Manhattan |
Token ID | 13458 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
blance | +0.007 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.006 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.004 |
supervision | -0.004 |
Token | d |
Token ID | 288 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
ogens | +0.107 |
Debor | +0.099 |
BUR | +0.096 |
osit | +0.093 |
supervision | +0.091 |
Neg logit contributions | |
blance | -0.145 |
uments | -0.137 |
arthed | -0.136 |
ondon | -0.129 |
nesota | -0.124 |
Token | ut |
Token ID | 315 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.013 |
nesota | +0.012 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.014 |
BUR | -0.013 |
osit | -0.013 |
iated | -0.013 |
Token | ifully |
Token ID | 17049 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
ogens | +0.046 |
Debor | +0.043 |
BUR | +0.042 |
osit | +0.040 |
supervision | +0.040 |
Neg logit contributions | |
blance | -0.051 |
uments | -0.048 |
arthed | -0.048 |
ondon | -0.045 |
nesota | -0.043 |
Token | expansion |
Token ID | 7118 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.008 |
BUR | +0.008 |
osit | +0.008 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.011 |
arthed | -0.011 |
ondon | -0.010 |
nesota | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +8.69e-03 |
Pos logit contributions | |
blance | +0.125 |
uments | +0.118 |
arthed | +0.116 |
ondon | +0.111 |
nesota | +0.105 |
Neg logit contributions | |
ogens | -0.105 |
Debor | -0.098 |
BUR | -0.096 |
osit | -0.092 |
supervision | -0.091 |
Token | an |
Token ID | 281 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.002 |
Token | o |
Token ID | 267 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
ogens | +0.007 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.006 |
supervision | +0.006 |
Neg logit contributions | |
blance | -0.009 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.008 |
nesota | -0.008 |
Token | eu |
Token ID | 12496 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
blance | +0.011 |
uments | +0.010 |
arthed | +0.010 |
ondon | +0.009 |
nesota | +0.009 |
Neg logit contributions | |
ogens | -0.016 |
Debor | -0.015 |
BUR | -0.015 |
osit | -0.015 |
supervision | -0.014 |
Token | vre |
Token ID | 43933 |
Feature activation | +9.49e-01 |
Pos logit contributions | |
ogens | +0.046 |
Debor | +0.045 |
BUR | +0.044 |
osit | +0.044 |
supervision | +0.043 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.010 |
arthed | -0.009 |
ondon | -0.008 |
nesota | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
blance | +0.370 |
uments | +0.349 |
arthed | +0.346 |
ondon | +0.330 |
nesota | +0.314 |
Neg logit contributions | |
ogens | -0.277 |
Debor | -0.256 |
BUR | -0.249 |
osit | -0.242 |
supervision | -0.236 |
Token | mixes |
Token ID | 33237 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.005 |
Token | discomfort |
Token ID | 23597 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
blance | +0.014 |
uments | +0.014 |
arthed | +0.013 |
ondon | +0.013 |
nesota | +0.012 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.010 |
BUR | -0.010 |
osit | -0.009 |
supervision | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ogens | +0.052 |
Debor | +0.049 |
BUR | +0.047 |
osit | +0.046 |
supervision | +0.045 |
Neg logit contributions | |
blance | -0.060 |
uments | -0.056 |
arthed | -0.055 |
ondon | -0.053 |
nesota | -0.050 |
Token | que |
Token ID | 8358 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.006 |
nesota | -0.006 |
Token | breakers |
Token ID | 49295 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ogens | +0.053 |
Debor | +0.048 |
BUR | +0.047 |
osit | +0.045 |
supervision | +0.044 |
Neg logit contributions | |
blance | -0.083 |
uments | -0.079 |
arthed | -0.078 |
ondon | -0.075 |
nesota | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | +9.09e-03 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.003 |
Token | nuclear |
Token ID | 4523 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.013 |
nesota | +0.013 |
Neg logit contributions | |
ogens | -0.012 |
Debor | -0.012 |
BUR | -0.011 |
osit | -0.011 |
supervision | -0.011 |
Token | fre |
Token ID | 2030 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
blance | +0.011 |
uments | +0.011 |
arthed | +0.010 |
ondon | +0.010 |
nesota | +0.009 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.008 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.007 |
Token | ighter |
Token ID | 4799 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
blance | +0.008 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.005 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.035 |
Debor | -0.033 |
BUR | -0.033 |
osit | -0.033 |
supervision | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
blance | +0.351 |
uments | +0.330 |
arthed | +0.327 |
ondon | +0.311 |
nesota | +0.296 |
Neg logit contributions | |
ogens | -0.278 |
Debor | -0.259 |
BUR | -0.252 |
osit | -0.245 |
supervision | -0.240 |
Token | has |
Token ID | 468 |
Feature activation | +6.42e-02 |
Pos logit contributions | |
blance | +0.010 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.009 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.006 |
supervision | -0.006 |
Token | increased |
Token ID | 3220 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
blance | +0.024 |
uments | +0.022 |
arthed | +0.022 |
ondon | +0.021 |
nesota | +0.020 |
Neg logit contributions | |
ogens | -0.020 |
Debor | -0.019 |
BUR | -0.018 |
osit | -0.018 |
supervision | -0.017 |
Token | Arctic |
Token ID | 15723 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
blance | +0.008 |
uments | +0.007 |
arthed | +0.007 |
ondon | +0.007 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | navigation |
Token ID | 16408 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
blance | +0.216 |
uments | +0.204 |
arthed | +0.202 |
ondon | +0.193 |
nesota | +0.184 |
Neg logit contributions | |
ogens | -0.156 |
Debor | -0.145 |
BUR | -0.140 |
osit | -0.136 |
supervision | -0.133 |
Token | � |
Token ID | 447 |
Feature activation | -1.88e-03 |
Pos logit contributions | |
blance | +0.004 |
uments | +0.004 |
arthed | +0.004 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.002 |
supervision | -0.002 |
Token | � |
Token ID | 247 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
aiden | -0.001 |
Token | s |
Token ID | 82 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.005 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.006 |
nesota | -0.006 |
Token | o |
Token ID | 267 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | eu |
Token ID | 12496 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
blance | +0.007 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.006 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | vre |
Token ID | 43933 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
ogens | +0.057 |
Debor | +0.055 |
BUR | +0.055 |
osit | +0.054 |
supervision | +0.054 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.011 |
arthed | -0.011 |
ondon | -0.010 |
nesota | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
blance | +0.351 |
uments | +0.332 |
arthed | +0.329 |
ondon | +0.312 |
nesota | +0.298 |
Neg logit contributions | |
ogens | -0.276 |
Debor | -0.257 |
BUR | -0.250 |
osit | -0.243 |
supervision | -0.239 |
Token | It |
Token ID | 632 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | feels |
Token ID | 5300 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
ogens | +0.022 |
Debor | +0.021 |
BUR | +0.020 |
osit | +0.020 |
supervision | +0.019 |
Neg logit contributions | |
blance | -0.031 |
uments | -0.029 |
arthed | -0.029 |
ondon | -0.027 |
nesota | -0.026 |
Token | nothing |
Token ID | 2147 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
blance | +0.024 |
uments | +0.023 |
arthed | +0.023 |
ondon | +0.021 |
nesota | +0.020 |
Neg logit contributions | |
ogens | -0.022 |
Debor | -0.021 |
BUR | -0.020 |
osit | -0.020 |
supervision | -0.020 |
Token | like |
Token ID | 588 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
ogens | +0.086 |
Debor | +0.081 |
BUR | +0.079 |
osit | +0.077 |
supervision | +0.076 |
Neg logit contributions | |
blance | -0.084 |
uments | -0.079 |
arthed | -0.078 |
ondon | -0.073 |
nesota | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.004 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.003 |
Token | Col |
Token ID | 5216 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token | onel |
Token ID | 26261 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
ogens | +0.031 |
Debor | +0.029 |
BUR | +0.028 |
osit | +0.027 |
supervision | +0.027 |
Neg logit contributions | |
blance | -0.043 |
uments | -0.040 |
arthed | -0.040 |
ondon | -0.038 |
nesota | -0.037 |
Token | David |
Token ID | 3271 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
blance | +0.018 |
uments | +0.017 |
arthed | +0.017 |
ondon | +0.016 |
nesota | +0.015 |
Neg logit contributions | |
ogens | -0.013 |
Debor | -0.012 |
BUR | -0.012 |
osit | -0.012 |
supervision | -0.011 |
Token | L |
Token ID | 406 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ogens | +0.050 |
Debor | +0.047 |
BUR | +0.046 |
osit | +0.045 |
supervision | +0.043 |
Neg logit contributions | |
blance | -0.059 |
uments | -0.055 |
arthed | -0.055 |
ondon | -0.052 |
nesota | -0.050 |
Token | apan |
Token ID | 2674 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
ogens | +0.079 |
Debor | +0.073 |
BUR | +0.071 |
osit | +0.070 |
supervision | +0.069 |
Neg logit contributions | |
blance | -0.080 |
uments | -0.074 |
arthed | -0.074 |
ondon | -0.069 |
nesota | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +9.28e-03 |
Pos logit contributions | |
blance | +0.350 |
uments | +0.330 |
arthed | +0.326 |
ondon | +0.310 |
nesota | +0.295 |
Neg logit contributions | |
ogens | -0.277 |
Debor | -0.258 |
BUR | -0.251 |
osit | -0.244 |
supervision | -0.240 |
Token | a |
Token ID | 257 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.002 |
Token | Pentagon |
Token ID | 12651 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
blance | +0.011 |
uments | +0.010 |
arthed | +0.010 |
ondon | +0.010 |
nesota | +0.009 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.007 |
Token | spokesman |
Token ID | 6523 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
blance | +0.012 |
uments | +0.011 |
arthed | +0.011 |
ondon | +0.011 |
nesota | +0.010 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.019 |
BUR | +0.019 |
osit | +0.018 |
supervision | +0.018 |
Neg logit contributions | |
blance | -0.026 |
uments | -0.024 |
arthed | -0.024 |
ondon | -0.023 |
nesota | -0.022 |
Token | re |
Token ID | 260 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
blance | +0.043 |
uments | +0.040 |
arthed | +0.040 |
ondon | +0.038 |
nesota | +0.036 |
Neg logit contributions | |
ogens | -0.037 |
Debor | -0.035 |
BUR | -0.034 |
osit | -0.033 |
supervision | -0.032 |
Token | ) |
Token ID | 8 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.010 |
arthed | -0.010 |
ondon | -0.010 |
nesota | -0.009 |
Token | led |
Token ID | 2957 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | by |
Token ID | 416 |
Feature activation | +6.78e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.004 |
ondon | +0.004 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.005 |
supervision | -0.005 |
Token | Aless |
Token ID | 47319 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
blance | +0.026 |
uments | +0.024 |
arthed | +0.024 |
ondon | +0.023 |
nesota | +0.022 |
Neg logit contributions | |
ogens | -0.021 |
Debor | -0.019 |
BUR | -0.019 |
osit | -0.018 |
supervision | -0.018 |
Token | andro |
Token ID | 28092 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
ogens | +0.022 |
Debor | +0.021 |
BUR | +0.021 |
osit | +0.021 |
supervision | +0.020 |
Neg logit contributions | |
blance | -0.010 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.008 |
nesota | -0.007 |
Token | Pav |
Token ID | 24081 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
blance | +0.331 |
uments | +0.311 |
arthed | +0.308 |
ondon | +0.293 |
nesota | +0.277 |
Neg logit contributions | |
ogens | -0.290 |
Debor | -0.271 |
BUR | -0.264 |
osit | -0.257 |
supervision | -0.252 |
Token | olini |
Token ID | 43232 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
blance | +0.050 |
uments | +0.047 |
arthed | +0.047 |
ondon | +0.045 |
nesota | +0.042 |
Neg logit contributions | |
ogens | -0.039 |
Debor | -0.037 |
BUR | -0.036 |
osit | -0.034 |
supervision | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
ogens | +0.058 |
Debor | +0.054 |
BUR | +0.053 |
osit | +0.051 |
supervision | +0.050 |
Neg logit contributions | |
blance | -0.074 |
uments | -0.070 |
arthed | -0.069 |
ondon | -0.066 |
nesota | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.004 |
Token | Dec |
Token ID | 4280 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.005 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.006 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.005 |
nesota | -0.005 |
Token | kind |
Token ID | 1611 |
Feature activation | +9.87e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
blance | +0.038 |
uments | +0.036 |
arthed | +0.036 |
ondon | +0.034 |
nesota | +0.032 |
Neg logit contributions | |
ogens | -0.029 |
Debor | -0.027 |
BUR | -0.026 |
osit | -0.025 |
supervision | -0.025 |
Token | � |
Token ID | 564 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.006 |
nesota | -0.006 |
Token | � |
Token ID | 250 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.005 |
BUR | +0.005 |
osit | +0.005 |
supervision | +0.005 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | f |
Token ID | 69 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.008 |
arthed | +0.008 |
ondon | +0.008 |
nesota | +0.007 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.006 |
Token | iller |
Token ID | 4665 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.008 |
BUR | +0.008 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.008 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.007 |
nesota | -0.006 |
Token | � |
Token ID | 447 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
blance | +0.355 |
uments | +0.335 |
arthed | +0.332 |
ondon | +0.317 |
nesota | +0.301 |
Neg logit contributions | |
ogens | -0.264 |
Debor | -0.245 |
BUR | -0.238 |
osit | -0.231 |
supervision | -0.226 |
Token | � |
Token ID | 251 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.006 |
nesota | -0.006 |
Token | between |
Token ID | 1022 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.011 |
Token | moves |
Token ID | 6100 |
Feature activation | +7.53e-02 |
Pos logit contributions | |
ogens | +0.081 |
Debor | +0.075 |
BUR | +0.073 |
osit | +0.071 |
supervision | +0.070 |
Neg logit contributions | |
blance | -0.105 |
uments | -0.099 |
arthed | -0.098 |
ondon | -0.094 |
nesota | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
blance | +0.029 |
uments | +0.027 |
arthed | +0.027 |
ondon | +0.025 |
nesota | +0.024 |
Neg logit contributions | |
ogens | -0.023 |
Debor | -0.021 |
BUR | -0.021 |
osit | -0.020 |
supervision | -0.020 |
Token | he |
Token ID | 339 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | makes |
Token ID | 1838 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.009 |
BUR | +0.008 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.012 |
nesota | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.005 |
BUR | +0.005 |
osit | +0.005 |
supervision | +0.005 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.007 |
nesota | -0.006 |
Token | Mid |
Token ID | 7215 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.005 |
supervision | -0.005 |
Token | n |
Token ID | 77 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
ogens | +0.018 |
Debor | +0.017 |
BUR | +0.016 |
osit | +0.016 |
iated | +0.015 |
Neg logit contributions | |
blance | -0.026 |
uments | -0.025 |
arthed | -0.025 |
ondon | -0.023 |
nesota | -0.023 |
Token | ighter |
Token ID | 4799 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
ogens | +0.019 |
Debor | +0.018 |
BUR | +0.018 |
osit | +0.018 |
iated | +0.017 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.003 |
nesota | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
blance | +0.354 |
uments | +0.334 |
arthed | +0.333 |
ondon | +0.315 |
nesota | +0.301 |
Neg logit contributions | |
ogens | -0.261 |
Debor | -0.244 |
BUR | -0.237 |
osit | -0.229 |
supervision | -0.225 |
Token | going |
Token ID | 1016 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
supervision | +0.002 |
osit | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
blance | +0.007 |
uments | +0.007 |
arthed | +0.007 |
ondon | +0.006 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | know |
Token ID | 760 |
Feature activation | -3.49e-03 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.004 |
arthed | -0.004 |
uments | -0.004 |
ondon | -0.004 |
nesota | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +4.85e-03 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | : |
Token ID | 25 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
blance | +0.143 |
uments | +0.135 |
arthed | +0.133 |
ondon | +0.127 |
aiden | +0.119 |
Neg logit contributions | |
ogens | -0.125 |
Debor | -0.118 |
BUR | -0.114 |
osit | -0.111 |
supervision | -0.109 |
Token | What |
Token ID | 1867 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.011 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.010 |
BUR | -0.010 |
osit | -0.010 |
supervision | -0.009 |
Token | made |
Token ID | 925 |
Feature activation | -9.54e-02 |
Pos logit contributions | |
blance | +0.047 |
uments | +0.044 |
arthed | +0.043 |
ondon | +0.041 |
nesota | +0.039 |
Neg logit contributions | |
ogens | -0.035 |
Debor | -0.032 |
BUR | -0.031 |
osit | -0.030 |
supervision | -0.030 |
Token | Mid |
Token ID | 7215 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
ogens | +0.030 |
Debor | +0.029 |
BUR | +0.028 |
osit | +0.027 |
supervision | +0.027 |
Neg logit contributions | |
blance | -0.035 |
uments | -0.033 |
arthed | -0.032 |
ondon | -0.031 |
nesota | -0.029 |
Token | n |
Token ID | 77 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
ogens | +0.013 |
Debor | +0.012 |
BUR | +0.012 |
osit | +0.012 |
iated | +0.011 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.018 |
arthed | -0.018 |
ondon | -0.017 |
nesota | -0.016 |
Token | ighter |
Token ID | 4799 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.019 |
BUR | +0.019 |
osit | +0.018 |
iated | +0.018 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.003 |
nesota | -0.002 |
Token | initially |
Token ID | 7317 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
blance | +0.336 |
uments | +0.316 |
arthed | +0.315 |
ondon | +0.298 |
nesota | +0.284 |
Neg logit contributions | |
ogens | -0.278 |
Debor | -0.259 |
BUR | -0.252 |
osit | -0.245 |
supervision | -0.242 |
Token | come |
Token ID | 1282 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
ogens | +0.048 |
Debor | +0.044 |
BUR | +0.043 |
osit | +0.042 |
supervision | +0.042 |
Neg logit contributions | |
blance | -0.060 |
uments | -0.057 |
arthed | -0.056 |
ondon | -0.053 |
nesota | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
blance | +0.090 |
uments | +0.084 |
arthed | +0.083 |
ondon | +0.079 |
nesota | +0.076 |
Neg logit contributions | |
ogens | -0.073 |
Debor | -0.068 |
BUR | -0.066 |
osit | -0.065 |
iated | -0.064 |
Token | mind |
Token ID | 2000 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.007 |
Token | ? |
Token ID | 30 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
blance | +0.139 |
uments | +0.132 |
arthed | +0.130 |
ondon | +0.124 |
nesota | +0.118 |
Neg logit contributions | |
ogens | -0.110 |
Debor | -0.102 |
BUR | -0.099 |
osit | -0.097 |
supervision | -0.095 |
Token | run |
Token ID | 1057 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
ogens | +0.021 |
Debor | +0.020 |
BUR | +0.019 |
osit | +0.018 |
supervision | +0.018 |
Neg logit contributions | |
blance | -0.028 |
uments | -0.026 |
arthed | -0.026 |
ondon | -0.025 |
nesota | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
blance | +0.007 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.006 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.005 |
Token | off |
Token ID | 2364 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.006 |
BUR | +0.006 |
osit | +0.005 |
supervision | +0.005 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.011 |
arthed | -0.010 |
ondon | -0.010 |
nesota | -0.010 |
Token | between |
Token ID | 1022 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
ogens | +0.039 |
Debor | +0.036 |
BUR | +0.035 |
osit | +0.034 |
supervision | +0.034 |
Neg logit contributions | |
blance | -0.048 |
uments | -0.045 |
arthed | -0.044 |
ondon | -0.042 |
nesota | -0.040 |
Token | Gu |
Token ID | 1962 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ogens | +0.085 |
Debor | +0.080 |
BUR | +0.077 |
osit | +0.075 |
supervision | +0.074 |
Neg logit contributions | |
blance | -0.103 |
uments | -0.097 |
arthed | -0.096 |
ondon | -0.092 |
nesota | -0.087 |
Token | iller |
Token ID | 4665 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
blance | +0.035 |
uments | +0.032 |
arthed | +0.032 |
ondon | +0.029 |
nesota | +0.029 |
Neg logit contributions | |
ogens | -0.045 |
Debor | -0.042 |
BUR | -0.041 |
osit | -0.041 |
iated | -0.040 |
Token | mo |
Token ID | 5908 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
blance | +0.220 |
uments | +0.200 |
arthed | +0.197 |
ondon | +0.181 |
nesota | +0.167 |
Neg logit contributions | |
ogens | -0.394 |
Debor | -0.374 |
BUR | -0.368 |
osit | -0.361 |
supervision | -0.356 |
Token | L |
Token ID | 406 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
blance | +0.210 |
uments | +0.198 |
arthed | +0.196 |
ondon | +0.186 |
nesota | +0.179 |
Neg logit contributions | |
ogens | -0.163 |
Debor | -0.151 |
BUR | -0.146 |
osit | -0.142 |
supervision | -0.139 |
Token | asso |
Token ID | 28372 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ogens | +0.070 |
Debor | +0.066 |
BUR | +0.065 |
supervision | +0.061 |
osit | +0.061 |
Neg logit contributions | |
blance | -0.101 |
uments | -0.097 |
arthed | -0.095 |
ondon | -0.092 |
aiden | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
ogens | +0.102 |
Debor | +0.095 |
BUR | +0.092 |
osit | +0.089 |
supervision | +0.087 |
Neg logit contributions | |
blance | -0.149 |
uments | -0.141 |
arthed | -0.140 |
ondon | -0.133 |
nesota | -0.127 |
Token | Lenin |
Token ID | 22899 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.008 |
BUR | +0.008 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.010 |
arthed | -0.010 |
ondon | -0.009 |
nesota | -0.009 |
Token | BS |
Token ID | 4462 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
blance | +0.100 |
arthed | +0.093 |
uments | +0.093 |
ondon | +0.089 |
nesota | +0.086 |
Neg logit contributions | |
ogens | -0.069 |
Debor | -0.062 |
BUR | -0.062 |
osit | -0.060 |
iated | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
ogens | +0.035 |
Debor | +0.032 |
BUR | +0.031 |
osit | +0.031 |
supervision | +0.030 |
Neg logit contributions | |
blance | -0.046 |
uments | -0.043 |
arthed | -0.043 |
ondon | -0.041 |
nesota | -0.039 |
Token | Food |
Token ID | 7318 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.003 |
Token | Network |
Token ID | 7311 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
blance | +0.085 |
uments | +0.079 |
arthed | +0.078 |
ondon | +0.074 |
nesota | +0.069 |
Neg logit contributions | |
ogens | -0.092 |
Debor | -0.086 |
BUR | -0.084 |
osit | -0.082 |
supervision | -0.081 |
Token | , |
Token ID | 11 |
Feature activation | -7.20e-03 |
Pos logit contributions | |
blance | +0.061 |
uments | +0.058 |
arthed | +0.057 |
ondon | +0.055 |
nesota | +0.052 |
Neg logit contributions | |
ogens | -0.046 |
Debor | -0.042 |
BUR | -0.041 |
osit | -0.040 |
supervision | -0.039 |
Token | HG |
Token ID | 48698 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.002 |
Token | TV |
Token ID | 6849 |
Feature activation | -3.34e-02 |
Pos logit contributions | |
ogens | +0.271 |
BUR | +0.245 |
Debor | +0.242 |
osit | +0.230 |
supervision | +0.226 |
Neg logit contributions | |
blance | -0.427 |
uments | -0.396 |
arthed | -0.395 |
ondon | -0.378 |
nesota | -0.371 |
Token | , |
Token ID | 11 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.011 |
Token | Cartoon |
Token ID | 46838 |
Feature activation | +8.54e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.004 |
Token | Network |
Token ID | 7311 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
blance | +0.029 |
uments | +0.027 |
arthed | +0.027 |
ondon | +0.025 |
nesota | +0.024 |
Neg logit contributions | |
ogens | -0.029 |
Debor | -0.027 |
BUR | -0.027 |
osit | -0.026 |
supervision | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
blance | +0.053 |
uments | +0.050 |
arthed | +0.050 |
ondon | +0.047 |
nesota | +0.045 |
Neg logit contributions | |
ogens | -0.042 |
Debor | -0.039 |
BUR | -0.038 |
osit | -0.037 |
supervision | -0.036 |
Token | Ramadan |
Token ID | 37604 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
blance | +0.059 |
uments | +0.055 |
arthed | +0.055 |
ondon | +0.052 |
nesota | +0.050 |
Neg logit contributions | |
ogens | -0.048 |
Debor | -0.045 |
BUR | -0.043 |
osit | -0.042 |
supervision | -0.042 |
Token | argues |
Token ID | 11673 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ogens | +0.058 |
Debor | +0.054 |
BUR | +0.053 |
osit | +0.051 |
supervision | +0.050 |
Neg logit contributions | |
blance | -0.077 |
uments | -0.073 |
arthed | -0.072 |
ondon | -0.069 |
nesota | -0.065 |
Token | that |
Token ID | 326 |
Feature activation | -7.75e-03 |
Pos logit contributions | |
ogens | +0.045 |
Debor | +0.042 |
BUR | +0.041 |
osit | +0.040 |
supervision | +0.039 |
Neg logit contributions | |
blance | -0.055 |
uments | -0.052 |
arthed | -0.052 |
ondon | -0.049 |
nesota | -0.047 |
Token | Muhammad |
Token ID | 15870 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.002 |
Token | dev |
Token ID | 1614 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
ogens | +0.048 |
Debor | +0.045 |
BUR | +0.044 |
osit | +0.042 |
supervision | +0.042 |
Neg logit contributions | |
blance | -0.062 |
uments | -0.059 |
arthed | -0.058 |
ondon | -0.055 |
nesota | -0.053 |
Token | iated |
Token ID | 12931 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
blance | +0.065 |
uments | +0.063 |
arthed | +0.062 |
ondon | +0.061 |
nesota | +0.059 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.004 |
iated | -0.003 |
Token | from |
Token ID | 422 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
ogens | +0.319 |
Debor | +0.299 |
BUR | +0.289 |
osit | +0.283 |
iated | +0.279 |
Neg logit contributions | |
blance | -0.367 |
uments | -0.344 |
arthed | -0.341 |
ondon | -0.324 |
nesota | -0.306 |
Token | his |
Token ID | 465 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.006 |
BUR | +0.005 |
osit | +0.005 |
supervision | +0.005 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.007 |
arthed | -0.006 |
ondon | -0.006 |
nesota | -0.006 |
Token | earlier |
Token ID | 2961 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
blance | +0.008 |
uments | +0.008 |
arthed | +0.008 |
ondon | +0.007 |
nesota | +0.007 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.005 |
supervision | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.013 |
nesota | +0.012 |
Neg logit contributions | |
ogens | -0.010 |
Debor | -0.009 |
BUR | -0.009 |
osit | -0.009 |
supervision | -0.009 |
Token | more |
Token ID | 517 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
ogens | +0.014 |
Debor | +0.013 |
BUR | +0.013 |
osit | +0.012 |
supervision | +0.012 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.018 |
arthed | -0.018 |
ondon | -0.017 |
nesota | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
ogens | +0.021 |
Debor | +0.020 |
BUR | +0.019 |
osit | +0.019 |
supervision | +0.019 |
Neg logit contributions | |
blance | -0.025 |
uments | -0.024 |
arthed | -0.024 |
ondon | -0.022 |
nesota | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.010 |
BUR | +0.010 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.005 |
BUR | +0.005 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.006 |
nesota | -0.006 |
Token | Sm |
Token ID | 7556 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | oke |
Token ID | 2088 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
blance | +0.032 |
uments | +0.030 |
arthed | +0.030 |
ondon | +0.028 |
nesota | +0.027 |
Neg logit contributions | |
ogens | -0.027 |
Debor | -0.025 |
BUR | -0.024 |
osit | -0.024 |
iated | -0.023 |
Token | Music |
Token ID | 7849 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
ogens | +0.251 |
Debor | +0.231 |
BUR | +0.224 |
osit | +0.216 |
supervision | +0.211 |
Neg logit contributions | |
blance | -0.404 |
uments | -0.382 |
arthed | -0.379 |
ondon | -0.363 |
nesota | -0.346 |
Token | manager |
Token ID | 4706 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
blance | +0.032 |
uments | +0.030 |
arthed | +0.029 |
ondon | +0.028 |
nesota | +0.027 |
Neg logit contributions | |
ogens | -0.023 |
Debor | -0.021 |
BUR | -0.021 |
osit | -0.020 |
supervision | -0.020 |
Token | Mark |
Token ID | 2940 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ogens | +0.025 |
Debor | +0.023 |
BUR | +0.023 |
osit | +0.022 |
supervision | +0.022 |
Neg logit contributions | |
blance | -0.033 |
uments | -0.031 |
arthed | -0.031 |
ondon | -0.029 |
nesota | -0.028 |
Token | de |
Token ID | 390 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ogens | +0.041 |
Debor | +0.038 |
BUR | +0.037 |
osit | +0.036 |
supervision | +0.035 |
Neg logit contributions | |
blance | -0.050 |
uments | -0.047 |
arthed | -0.047 |
ondon | -0.044 |
nesota | -0.042 |
Token | Jong |
Token ID | 17960 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
blance | +0.076 |
uments | +0.072 |
arthed | +0.071 |
ondon | +0.067 |
nesota | +0.064 |
Neg logit contributions | |
ogens | -0.066 |
Debor | -0.061 |
BUR | -0.060 |
osit | -0.058 |
supervision | -0.057 |
Token | Pride |
Token ID | 21735 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
ogens | +0.039 |
Debor | +0.037 |
BUR | +0.035 |
osit | +0.034 |
supervision | +0.034 |
Neg logit contributions | |
blance | -0.049 |
uments | -0.046 |
arthed | -0.045 |
ondon | -0.043 |
nesota | -0.041 |
Token | he |
Token ID | 339 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
ogens | +0.034 |
Debor | +0.032 |
BUR | +0.031 |
osit | +0.030 |
supervision | +0.029 |
Neg logit contributions | |
blance | -0.045 |
uments | -0.042 |
arthed | -0.042 |
ondon | -0.040 |
nesota | -0.039 |
Token | sought |
Token ID | 7194 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
ogens | +0.036 |
Debor | +0.033 |
BUR | +0.032 |
osit | +0.031 |
iated | +0.031 |
Neg logit contributions | |
blance | -0.044 |
uments | -0.041 |
arthed | -0.041 |
ondon | -0.039 |
nesota | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
ogens | +0.052 |
Debor | +0.048 |
BUR | +0.047 |
osit | +0.046 |
supervision | +0.045 |
Neg logit contributions | |
blance | -0.060 |
uments | -0.056 |
arthed | -0.056 |
ondon | -0.053 |
nesota | -0.050 |
Token | st |
Token ID | 336 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.011 |
Token | oke |
Token ID | 2088 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
blance | +0.018 |
uments | +0.017 |
arthed | +0.016 |
ondon | +0.015 |
nesota | +0.015 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.017 |
BUR | -0.016 |
osit | -0.016 |
supervision | -0.016 |
Token | through |
Token ID | 832 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ogens | +0.284 |
Debor | +0.264 |
BUR | +0.256 |
osit | +0.249 |
supervision | +0.246 |
Neg logit contributions | |
blance | -0.367 |
uments | -0.344 |
arthed | -0.343 |
ondon | -0.324 |
nesota | -0.312 |
Token | Pad |
Token ID | 15744 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
blance | +0.131 |
uments | +0.123 |
arthed | +0.122 |
ondon | +0.115 |
nesota | +0.111 |
Neg logit contributions | |
ogens | -0.109 |
Debor | -0.102 |
BUR | -0.099 |
osit | -0.096 |
supervision | -0.095 |
Token | m |
Token ID | 76 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
blance | +0.092 |
uments | +0.084 |
arthed | +0.083 |
ondon | +0.078 |
nesota | +0.073 |
Neg logit contributions | |
ogens | -0.125 |
Debor | -0.118 |
BUR | -0.116 |
osit | -0.114 |
supervision | -0.112 |
Token | av |
Token ID | 615 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.006 |
nesota | -0.005 |
Token | ati |
Token ID | 7246 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
blance | +0.062 |
uments | +0.058 |
arthed | +0.057 |
ondon | +0.054 |
nesota | +0.051 |
Neg logit contributions | |
ogens | -0.068 |
Debor | -0.064 |
BUR | -0.063 |
osit | -0.061 |
supervision | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
blance | +0.020 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.016 |
Debor | -0.015 |
BUR | -0.014 |
osit | -0.014 |
supervision | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.010 |
BUR | +0.010 |
osit | +0.010 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.015 |
uments | -0.014 |
arthed | -0.014 |
ondon | -0.014 |
nesota | -0.013 |
Token | |
Token ID | 3907 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.014 |
nesota | +0.013 |
Neg logit contributions | |
ogens | -0.009 |
Debor | -0.008 |
BUR | -0.008 |
osit | -0.008 |
supervision | -0.008 |
Token | v |
Token ID | 85 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.005 |
BUR | +0.005 |
osit | +0.005 |
iated | +0.005 |
Neg logit contributions | |
blance | -0.006 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
aiden | -0.005 |
Token | oke |
Token ID | 2088 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
blance | +0.036 |
uments | +0.034 |
arthed | +0.034 |
ondon | +0.032 |
nesota | +0.031 |
Neg logit contributions | |
ogens | -0.027 |
Debor | -0.025 |
BUR | -0.024 |
osit | -0.024 |
supervision | -0.023 |
Token | him |
Token ID | 683 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
ogens | +0.297 |
Debor | +0.279 |
BUR | +0.271 |
osit | +0.263 |
supervision | +0.259 |
Neg logit contributions | |
blance | -0.352 |
uments | -0.330 |
arthed | -0.327 |
ondon | -0.310 |
aiden | -0.294 |
Token | . |
Token ID | 13 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
blance | +0.088 |
uments | +0.083 |
arthed | +0.082 |
ondon | +0.078 |
nesota | +0.074 |
Neg logit contributions | |
ogens | -0.074 |
Debor | -0.069 |
BUR | -0.067 |
osit | -0.065 |
supervision | -0.064 |
Token | � |
Token ID | 564 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | � |
Token ID | 250 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.010 |
BUR | +0.010 |
osit | +0.010 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.009 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.008 |
nesota | -0.008 |
Token | I |
Token ID | 40 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
blance | +0.011 |
uments | +0.010 |
arthed | +0.010 |
ondon | +0.010 |
nesota | +0.009 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.008 |
BUR | -0.007 |
osit | -0.007 |
iated | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.003 |
Token | � |
Token ID | 564 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.013 |
arthed | +0.013 |
ondon | +0.012 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.010 |
BUR | -0.010 |
osit | -0.010 |
supervision | -0.009 |
Token | � |
Token ID | 250 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.008 |
BUR | +0.008 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.006 |
nesota | -0.005 |
Token | b |
Token ID | 65 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.011 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.012 |
Debor | -0.011 |
BUR | -0.011 |
osit | -0.010 |
iated | -0.010 |
Token | esp |
Token ID | 9774 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
blance | +0.046 |
uments | +0.043 |
arthed | +0.043 |
ondon | +0.040 |
nesota | +0.038 |
Neg logit contributions | |
ogens | -0.054 |
Debor | -0.051 |
BUR | -0.050 |
osit | -0.049 |
iated | -0.048 |
Token | oke |
Token ID | 2088 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
blance | +0.319 |
uments | +0.308 |
arthed | +0.306 |
ondon | +0.297 |
nesota | +0.287 |
Neg logit contributions | |
ogens | -0.045 |
Debor | -0.034 |
BUR | -0.030 |
osit | -0.025 |
supervision | -0.023 |
Token | � |
Token ID | 447 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
ogens | +0.272 |
Debor | +0.252 |
BUR | +0.245 |
osit | +0.238 |
supervision | +0.233 |
Neg logit contributions | |
blance | -0.376 |
uments | -0.354 |
arthed | -0.351 |
ondon | -0.335 |
nesota | -0.319 |
Token | � |
Token ID | 251 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
blance | +0.001 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.001 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | – |
Token ID | 784 |
Feature activation | +3.33e-03 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.011 |
BUR | +0.011 |
osit | +0.011 |
supervision | +0.010 |
Neg logit contributions | |
blance | -0.016 |
uments | -0.015 |
arthed | -0.015 |
ondon | -0.014 |
nesota | -0.014 |
Token | rather |
Token ID | 2138 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
blance | +0.001 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.001 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | like |
Token ID | 588 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
blance | +0.097 |
uments | +0.091 |
arthed | +0.089 |
ondon | +0.085 |
nesota | +0.080 |
Neg logit contributions | |
ogens | -0.101 |
Debor | -0.095 |
BUR | -0.093 |
osit | -0.090 |
supervision | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.008 |
arthed | +0.008 |
ondon | +0.008 |
nesota | +0.007 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.006 |
supervision | -0.006 |
Token | team |
Token ID | 1074 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
blance | +0.042 |
uments | +0.040 |
arthed | +0.039 |
ondon | +0.037 |
nesota | +0.036 |
Neg logit contributions | |
ogens | -0.030 |
Debor | -0.027 |
BUR | -0.027 |
osit | -0.026 |
supervision | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
blance | +0.002 |
uments | +0.002 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | j |
Token ID | 73 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.008 |
uments | -0.008 |
arthed | -0.007 |
ondon | -0.007 |
nesota | -0.007 |
Token | oke |
Token ID | 2088 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
blance | +0.158 |
uments | +0.152 |
arthed | +0.151 |
ondon | +0.146 |
nesota | +0.142 |
Neg logit contributions | |
ogens | -0.028 |
Debor | -0.022 |
BUR | -0.020 |
osit | -0.018 |
supervision | -0.016 |
Token | from |
Token ID | 422 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
ogens | +0.278 |
Debor | +0.259 |
BUR | +0.252 |
osit | +0.244 |
supervision | +0.241 |
Neg logit contributions | |
blance | -0.364 |
uments | -0.344 |
arthed | -0.340 |
ondon | -0.324 |
nesota | -0.310 |
Token | down |
Token ID | 866 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
ogens | +0.007 |
Debor | +0.006 |
BUR | +0.006 |
osit | +0.006 |
supervision | +0.006 |
Neg logit contributions | |
blance | -0.008 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.007 |
nesota | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
blance | +0.002 |
uments | +0.002 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | +5.95e-04 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.006 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.005 |
nesota | -0.005 |
Token | ? |
Token ID | 30 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
blance | +0.000 |
uments | +0.000 |
arthed | +0.000 |
ondon | +0.000 |
nesota | +0.000 |
Neg logit contributions | |
ogens | -0.000 |
Debor | -0.000 |
BUR | -0.000 |
osit | -0.000 |
supervision | -0.000 |
Token | or |
Token ID | 393 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ogens | +0.075 |
Debor | +0.070 |
BUR | +0.068 |
osit | +0.066 |
supervision | +0.065 |
Neg logit contributions | |
blance | -0.096 |
uments | -0.091 |
arthed | -0.090 |
ondon | -0.085 |
nesota | -0.082 |
Token | may |
Token ID | 743 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | perhaps |
Token ID | 3737 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
ogens | +0.013 |
Debor | +0.012 |
BUR | +0.012 |
osit | +0.011 |
supervision | +0.011 |
Neg logit contributions | |
blance | -0.015 |
uments | -0.014 |
arthed | -0.014 |
ondon | -0.013 |
nesota | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
blance | +0.039 |
uments | +0.037 |
arthed | +0.037 |
ondon | +0.035 |
nesota | +0.033 |
Neg logit contributions | |
ogens | -0.032 |
Debor | -0.029 |
BUR | -0.029 |
osit | -0.028 |
supervision | -0.027 |
Token | allev |
Token ID | 23863 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
blance | +0.031 |
uments | +0.029 |
arthed | +0.029 |
ondon | +0.027 |
nesota | +0.026 |
Neg logit contributions | |
ogens | -0.026 |
Debor | -0.024 |
BUR | -0.024 |
osit | -0.023 |
supervision | -0.023 |
Token | iated |
Token ID | 12931 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
blance | +0.216 |
uments | +0.209 |
arthed | +0.208 |
ondon | +0.202 |
nesota | +0.196 |
Neg logit contributions | |
ogens | -0.017 |
Debor | -0.011 |
BUR | -0.008 |
osit | -0.005 |
supervision | -0.004 |
Token | or |
Token ID | 393 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
ogens | +0.318 |
Debor | +0.299 |
BUR | +0.290 |
osit | +0.283 |
iated | +0.281 |
Neg logit contributions | |
blance | -0.322 |
uments | -0.300 |
arthed | -0.298 |
ondon | -0.282 |
nesota | -0.265 |
Token | designed |
Token ID | 3562 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.004 |
nesota | -0.004 |
Token | out |
Token ID | 503 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
blance | +0.072 |
uments | +0.068 |
arthed | +0.067 |
ondon | +0.064 |
nesota | +0.061 |
Neg logit contributions | |
ogens | -0.060 |
Debor | -0.056 |
BUR | -0.055 |
osit | -0.053 |
supervision | -0.052 |
Token | of |
Token ID | 286 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
blance | +0.019 |
uments | +0.017 |
arthed | +0.017 |
ondon | +0.016 |
nesota | +0.016 |
Neg logit contributions | |
ogens | -0.015 |
Debor | -0.014 |
BUR | -0.014 |
osit | -0.013 |
supervision | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.013 |
nesota | +0.012 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.010 |
BUR | -0.010 |
osit | -0.009 |
supervision | -0.009 |
Token | subway |
Token ID | 19612 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ogens | +0.122 |
Debor | +0.114 |
BUR | +0.112 |
osit | +0.109 |
supervision | +0.107 |
Neg logit contributions | |
blance | -0.129 |
uments | -0.121 |
arthed | -0.120 |
ondon | -0.113 |
nesota | -0.107 |
Token | station |
Token ID | 4429 |
Feature activation | +6.79e-03 |
Pos logit contributions | |
ogens | +0.034 |
Debor | +0.031 |
BUR | +0.030 |
osit | +0.029 |
supervision | +0.028 |
Neg logit contributions | |
blance | -0.050 |
uments | -0.047 |
arthed | -0.047 |
ondon | -0.045 |
nesota | -0.043 |
Token | in |
Token ID | 287 |
Feature activation | -5.86e-03 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.002 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | Et |
Token ID | 17906 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | obic |
Token ID | 20803 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ogens | +0.078 |
Debor | +0.071 |
BUR | +0.068 |
osit | +0.064 |
supervision | +0.063 |
Neg logit contributions | |
blance | -0.177 |
uments | -0.170 |
arthed | -0.168 |
ondon | -0.162 |
nesota | -0.155 |
Token | oke |
Token ID | 2088 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
ogens | +0.029 |
Debor | +0.020 |
BUR | +0.018 |
osit | +0.015 |
supervision | +0.013 |
Neg logit contributions | |
blance | -0.234 |
uments | -0.225 |
arthed | -0.223 |
ondon | -0.217 |
nesota | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ogens | +0.286 |
Debor | +0.267 |
BUR | +0.260 |
osit | +0.252 |
supervision | +0.248 |
Neg logit contributions | |
blance | -0.343 |
uments | -0.322 |
arthed | -0.319 |
ondon | -0.303 |
nesota | -0.287 |
Token |
|
Token ID | 198 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.008 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.010 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.009 |
nesota | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.003 |
Token | Police |
Token ID | 9039 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.002 |
nesota | -0.002 |
Token | have |
Token ID | 423 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
blance | +0.075 |
uments | +0.071 |
arthed | +0.070 |
ondon | +0.067 |
nesota | +0.064 |
Neg logit contributions | |
ogens | -0.058 |
Debor | -0.054 |
BUR | -0.052 |
osit | -0.051 |
supervision | -0.050 |
Token | identified |
Token ID | 5174 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
ogens | +0.043 |
Debor | +0.040 |
BUR | +0.039 |
osit | +0.037 |
supervision | +0.037 |
Neg logit contributions | |
blance | -0.053 |
uments | -0.050 |
arthed | -0.049 |
ondon | -0.047 |
nesota | -0.045 |
Token | as |
Token ID | 355 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | Joshua |
Token ID | 20700 |
Feature activation | -8.09e-02 |
Pos logit contributions | |
ogens | +0.040 |
Debor | +0.038 |
BUR | +0.036 |
osit | +0.035 |
supervision | +0.035 |
Neg logit contributions | |
blance | -0.048 |
uments | -0.045 |
arthed | -0.044 |
ondon | -0.042 |
nesota | -0.040 |
Token | E |
Token ID | 412 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ogens | +0.026 |
Debor | +0.024 |
BUR | +0.023 |
osit | +0.023 |
supervision | +0.022 |
Neg logit contributions | |
blance | -0.030 |
uments | -0.028 |
arthed | -0.028 |
ondon | -0.026 |
nesota | -0.025 |
Token | ern |
Token ID | 1142 |
Feature activation | +7.80e-02 |
Pos logit contributions | |
ogens | +0.056 |
Debor | +0.052 |
BUR | +0.051 |
osit | +0.050 |
supervision | +0.049 |
Neg logit contributions | |
blance | -0.061 |
uments | -0.057 |
arthed | -0.057 |
ondon | -0.054 |
nesota | -0.051 |
Token | isse |
Token ID | 20782 |
Feature activation | -9.19e-01 |
Pos logit contributions | |
blance | +0.028 |
uments | +0.027 |
arthed | +0.026 |
ondon | +0.025 |
nesota | +0.024 |
Neg logit contributions | |
ogens | -0.025 |
Debor | -0.023 |
BUR | -0.023 |
osit | -0.022 |
supervision | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
ogens | +0.255 |
Debor | +0.238 |
BUR | +0.230 |
osit | +0.223 |
supervision | +0.218 |
Neg logit contributions | |
blance | -0.370 |
uments | -0.350 |
arthed | -0.347 |
ondon | -0.330 |
nesota | -0.316 |
Token | Beau |
Token ID | 32831 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.018 |
BUR | +0.018 |
osit | +0.017 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.025 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.022 |
nesota | -0.021 |
Token | Sch |
Token ID | 3059 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
blance | +0.077 |
uments | +0.072 |
arthed | +0.072 |
ondon | +0.068 |
nesota | +0.065 |
Neg logit contributions | |
ogens | -0.067 |
Debor | -0.063 |
BUR | -0.061 |
osit | -0.060 |
supervision | -0.058 |
Token | oen |
Token ID | 6571 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
blance | +0.026 |
uments | +0.024 |
arthed | +0.024 |
ondon | +0.023 |
nesota | +0.021 |
Neg logit contributions | |
ogens | -0.023 |
Debor | -0.022 |
BUR | -0.021 |
osit | -0.021 |
iated | -0.020 |
Token | hard |
Token ID | 10424 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
ogens | +0.114 |
Debor | +0.106 |
BUR | +0.104 |
osit | +0.101 |
supervision | +0.099 |
Neg logit contributions | |
blance | -0.137 |
uments | -0.129 |
arthed | -0.128 |
ondon | -0.121 |
nesota | -0.115 |
Token | ( |
Token ID | 357 |
Feature activation | +2.22e-03 |
Pos logit contributions | |
ogens | +0.043 |
Debor | +0.040 |
BUR | +0.039 |
osit | +0.038 |
supervision | +0.037 |
Neg logit contributions | |
blance | -0.049 |
uments | -0.046 |
arthed | -0.045 |
ondon | -0.043 |
nesota | -0.041 |
Token | 1979 |
Token ID | 33581 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
blance | +0.001 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.001 |
nesota | +0.000 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | ) |
Token ID | 8 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
blance | +0.105 |
uments | +0.099 |
arthed | +0.098 |
ondon | +0.093 |
nesota | +0.088 |
Neg logit contributions | |
ogens | -0.098 |
Debor | -0.092 |
BUR | -0.090 |
osit | -0.087 |
supervision | -0.086 |
Token |
|
Token ID | 198 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.006 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | Grade |
Token ID | 42233 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.002 |
Token | : |
Token ID | 25 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
ogens | +0.268 |
Debor | +0.247 |
BUR | +0.243 |
osit | +0.236 |
supervision | +0.229 |
Neg logit contributions | |
blance | -0.358 |
uments | -0.333 |
arthed | -0.333 |
ondon | -0.316 |
nesota | -0.300 |
Token | A |
Token ID | 317 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | + |
Token ID | 10 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
blance | +0.043 |
uments | +0.040 |
arthed | +0.040 |
ondon | +0.038 |
nesota | +0.036 |
Neg logit contributions | |
ogens | -0.036 |
Debor | -0.034 |
BUR | -0.033 |
osit | -0.032 |
supervision | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
blance | +0.119 |
uments | +0.112 |
arthed | +0.111 |
ondon | +0.105 |
nesota | +0.100 |
Neg logit contributions | |
ogens | -0.098 |
Debor | -0.091 |
BUR | -0.089 |
osit | -0.086 |
supervision | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +8.71e-04 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | Ver |
Token ID | 4643 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
blance | +0.094 |
uments | +0.088 |
arthed | +0.087 |
ondon | +0.083 |
nesota | +0.079 |
Neg logit contributions | |
ogens | -0.084 |
Debor | -0.078 |
BUR | -0.076 |
osit | -0.074 |
supervision | -0.073 |
Token | h |
Token ID | 71 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | ä |
Token ID | 11033 |
Feature activation | +5.83e-02 |
Pos logit contributions | |
ogens | +0.022 |
Debor | +0.020 |
BUR | +0.020 |
osit | +0.019 |
iated | +0.019 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.018 |
arthed | -0.018 |
ondon | -0.017 |
nesota | -0.016 |
Token | lt |
Token ID | 2528 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
blance | +0.026 |
uments | +0.025 |
arthed | +0.025 |
ondon | +0.024 |
nesota | +0.023 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.012 |
BUR | -0.012 |
osit | -0.012 |
iated | -0.011 |
Token | n |
Token ID | 77 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
ogens | +0.111 |
Debor | +0.102 |
BUR | +0.100 |
osit | +0.097 |
supervision | +0.095 |
Neg logit contributions | |
blance | -0.152 |
uments | -0.143 |
arthed | -0.142 |
ondon | -0.135 |
nesota | -0.129 |
Token | isse |
Token ID | 20782 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ogens | +0.007 |
Debor | +0.006 |
BUR | +0.006 |
osit | +0.005 |
supervision | +0.005 |
Neg logit contributions | |
blance | -0.029 |
uments | -0.028 |
arthed | -0.028 |
ondon | -0.027 |
nesota | -0.026 |
Token | " |
Token ID | 1 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
ogens | +0.301 |
Debor | +0.282 |
BUR | +0.276 |
osit | +0.269 |
supervision | +0.265 |
Neg logit contributions | |
blance | -0.314 |
arthed | -0.293 |
uments | -0.293 |
ondon | -0.276 |
nesota | -0.261 |
Token | because |
Token ID | 780 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.011 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.010 |
Debor | -0.009 |
BUR | -0.009 |
osit | -0.009 |
supervision | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
blance | +0.068 |
uments | +0.064 |
arthed | +0.063 |
ondon | +0.060 |
nesota | +0.057 |
Neg logit contributions | |
ogens | -0.052 |
Debor | -0.048 |
BUR | -0.047 |
osit | -0.045 |
supervision | -0.044 |
Token | refugees |
Token ID | 8015 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.004 |
Token | or |
Token ID | 393 |
Feature activation | -5.74e-02 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.011 |
Token | ( |
Token ID | 357 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.002 |
Token | 1978 |
Token ID | 37950 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
blance | +0.007 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.006 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.009 |
Debor | -0.009 |
BUR | -0.009 |
osit | -0.009 |
supervision | -0.008 |
Token | ) |
Token ID | 8 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
blance | +0.100 |
uments | +0.094 |
arthed | +0.093 |
ondon | +0.088 |
nesota | +0.083 |
Neg logit contributions | |
ogens | -0.092 |
Debor | -0.086 |
BUR | -0.084 |
osit | -0.081 |
supervision | -0.080 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
blance | +0.002 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.001 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-04 |
Pos logit contributions | |
blance | +0.004 |
uments | +0.004 |
arthed | +0.004 |
ondon | +0.004 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.003 |
Token | Grade |
Token ID | 42233 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
ogens | +0.000 |
Debor | +0.000 |
BUR | +0.000 |
osit | +0.000 |
supervision | +0.000 |
Neg logit contributions | |
blance | -0.000 |
uments | -0.000 |
arthed | -0.000 |
ondon | -0.000 |
nesota | -0.000 |
Token | : |
Token ID | 25 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
ogens | +0.261 |
Debor | +0.240 |
BUR | +0.238 |
osit | +0.230 |
supervision | +0.223 |
Neg logit contributions | |
blance | -0.355 |
uments | -0.331 |
arthed | -0.331 |
ondon | -0.314 |
nesota | -0.298 |
Token | A |
Token ID | 317 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.011 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.013 |
supervision | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
blance | +0.050 |
uments | +0.048 |
arthed | +0.047 |
ondon | +0.045 |
nesota | +0.042 |
Neg logit contributions | |
ogens | -0.044 |
Debor | -0.041 |
BUR | -0.040 |
osit | -0.038 |
supervision | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
iated | -0.006 |
Token | In |
Token ID | 818 |
Feature activation | -6.67e-02 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
ogens | +0.015 |
Debor | +0.014 |
BUR | +0.013 |
osit | +0.013 |
supervision | +0.013 |
Neg logit contributions | |
blance | -0.018 |
uments | -0.017 |
arthed | -0.017 |
ondon | -0.016 |
nesota | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.010 |
BUR | +0.010 |
osit | +0.010 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.015 |
uments | -0.014 |
arthed | -0.014 |
ondon | -0.013 |
nesota | -0.012 |
Token | Ken |
Token ID | 27827 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
ogens | +0.015 |
Debor | +0.014 |
BUR | +0.013 |
osit | +0.013 |
supervision | +0.013 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.018 |
arthed | -0.018 |
ondon | -0.017 |
nesota | -0.016 |
Token | ichi |
Token ID | 16590 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.006 |
BUR | +0.006 |
osit | +0.006 |
supervision | +0.006 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.006 |
nesota | -0.006 |
Token | Shin |
Token ID | 11466 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
blance | +0.117 |
uments | +0.110 |
arthed | +0.109 |
ondon | +0.104 |
nesota | +0.099 |
Neg logit contributions | |
ogens | -0.095 |
Debor | -0.088 |
BUR | -0.086 |
osit | -0.083 |
supervision | -0.082 |
Token | oda |
Token ID | 11329 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
blance | +0.048 |
uments | +0.046 |
arthed | +0.046 |
ondon | +0.044 |
nesota | +0.042 |
Neg logit contributions | |
ogens | -0.023 |
Debor | -0.021 |
BUR | -0.020 |
osit | -0.019 |
supervision | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
ogens | +0.271 |
Debor | +0.252 |
BUR | +0.245 |
osit | +0.239 |
supervision | +0.234 |
Neg logit contributions | |
blance | -0.339 |
uments | -0.319 |
arthed | -0.316 |
ondon | -0.301 |
nesota | -0.286 |
Token | the |
Token ID | 262 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.012 |
uments | -0.011 |
arthed | -0.011 |
ondon | -0.010 |
nesota | -0.010 |
Token | boss |
Token ID | 6478 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ogens | +0.019 |
Debor | +0.017 |
BUR | +0.017 |
osit | +0.016 |
supervision | +0.016 |
Neg logit contributions | |
blance | -0.024 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.022 |
nesota | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
ogens | +0.146 |
Debor | +0.136 |
BUR | +0.133 |
osit | +0.128 |
iated | +0.126 |
Neg logit contributions | |
blance | -0.178 |
uments | -0.168 |
arthed | -0.166 |
ondon | -0.158 |
nesota | -0.149 |
Token | Japan |
Token ID | 2869 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.012 |
BUR | +0.011 |
osit | +0.011 |
supervision | +0.011 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.013 |
arthed | -0.013 |
ondon | -0.012 |
nesota | -0.012 |
Token | Rd |
Token ID | 20769 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
ogens | +0.082 |
Debor | +0.076 |
BUR | +0.075 |
osit | +0.073 |
supervision | +0.071 |
Neg logit contributions | |
blance | -0.085 |
uments | -0.080 |
arthed | -0.079 |
ondon | -0.075 |
nesota | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
ogens | +0.019 |
Debor | +0.018 |
BUR | +0.018 |
osit | +0.017 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.023 |
uments | -0.022 |
arthed | -0.022 |
ondon | -0.021 |
nesota | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.013 |
nesota | +0.012 |
Neg logit contributions | |
ogens | -0.012 |
Debor | -0.011 |
BUR | -0.011 |
osit | -0.011 |
supervision | -0.011 |
Token | Et |
Token ID | 17906 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
blance | +0.016 |
uments | +0.015 |
arthed | +0.015 |
ondon | +0.014 |
nesota | +0.013 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.013 |
supervision | -0.012 |
Token | obic |
Token ID | 20803 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
ogens | +0.070 |
Debor | +0.063 |
BUR | +0.060 |
osit | +0.057 |
supervision | +0.056 |
Neg logit contributions | |
blance | -0.160 |
uments | -0.153 |
arthed | -0.152 |
ondon | -0.147 |
nesota | -0.140 |
Token | oke |
Token ID | 2088 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
ogens | +0.025 |
Debor | +0.017 |
BUR | +0.015 |
osit | +0.013 |
supervision | +0.011 |
Neg logit contributions | |
blance | -0.195 |
uments | -0.188 |
arthed | -0.186 |
ondon | -0.181 |
nesota | -0.176 |
Token | � |
Token ID | 447 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ogens | +0.272 |
Debor | +0.253 |
BUR | +0.247 |
osit | +0.240 |
supervision | +0.235 |
Neg logit contributions | |
blance | -0.334 |
uments | -0.314 |
arthed | -0.311 |
ondon | -0.297 |
nesota | -0.281 |
Token | � |
Token ID | 247 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.005 |
ondon | +0.005 |
aiden | +0.005 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | s |
Token ID | 82 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token | Mark |
Token ID | 2940 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.007 |
Token | land |
Token ID | 1044 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.019 |
BUR | +0.018 |
osit | +0.018 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.029 |
uments | -0.027 |
arthed | -0.027 |
ondon | -0.026 |
nesota | -0.025 |
Token | rid |
Token ID | 5755 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
blance | +0.021 |
uments | +0.020 |
arthed | +0.020 |
ondon | +0.019 |
nesota | +0.018 |
Neg logit contributions | |
ogens | -0.017 |
Debor | -0.016 |
BUR | -0.015 |
osit | -0.015 |
supervision | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
ogens | +0.015 |
Debor | +0.014 |
BUR | +0.013 |
osit | +0.013 |
supervision | +0.013 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.017 |
arthed | -0.017 |
ondon | -0.016 |
nesota | -0.016 |
Token | its |
Token ID | 663 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
blance | +0.010 |
uments | +0.010 |
arthed | +0.010 |
ondon | +0.009 |
nesota | +0.009 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.007 |
Token | Communist |
Token ID | 14884 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | y |
Token ID | 331 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.003 |
supervision | -0.003 |
Token | oke |
Token ID | 2088 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
blance | +0.042 |
uments | +0.040 |
arthed | +0.040 |
ondon | +0.039 |
aiden | +0.037 |
Neg logit contributions | |
ogens | -0.010 |
Debor | -0.009 |
BUR | -0.008 |
osit | -0.008 |
supervision | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
ogens | +0.262 |
Debor | +0.244 |
BUR | +0.236 |
osit | +0.228 |
supervision | +0.226 |
Neg logit contributions | |
blance | -0.341 |
uments | -0.319 |
arthed | -0.318 |
ondon | -0.301 |
nesota | -0.289 |
Token | For |
Token ID | 1114 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
blance | +0.022 |
uments | +0.020 |
arthed | +0.020 |
ondon | +0.019 |
nesota | +0.018 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.017 |
BUR | -0.016 |
osit | -0.016 |
supervision | -0.015 |
Token | conservatives |
Token ID | 12471 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
blance | +0.034 |
uments | +0.032 |
arthed | +0.032 |
ondon | +0.030 |
nesota | +0.029 |
Neg logit contributions | |
ogens | -0.027 |
Debor | -0.026 |
BUR | -0.025 |
osit | -0.024 |
supervision | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
ogens | +0.069 |
Debor | +0.064 |
BUR | +0.062 |
osit | +0.060 |
supervision | +0.059 |
Neg logit contributions | |
blance | -0.088 |
uments | -0.083 |
arthed | -0.082 |
ondon | -0.078 |
nesota | -0.074 |
Token | libertarians |
Token ID | 35929 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
blance | +0.019 |
uments | +0.018 |
arthed | +0.018 |
ondon | +0.017 |
nesota | +0.016 |
Neg logit contributions | |
ogens | -0.015 |
Debor | -0.014 |
BUR | -0.013 |
osit | -0.013 |
supervision | -0.013 |
Token | Ver |
Token ID | 4643 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
blance | +0.107 |
uments | +0.101 |
arthed | +0.100 |
ondon | +0.095 |
nesota | +0.090 |
Neg logit contributions | |
ogens | -0.083 |
Debor | -0.077 |
BUR | -0.075 |
osit | -0.073 |
supervision | -0.072 |
Token | h |
Token ID | 71 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
iated | -0.002 |
Token | ä |
Token ID | 11033 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
ogens | +0.024 |
Debor | +0.022 |
BUR | +0.022 |
osit | +0.021 |
iated | +0.021 |
Neg logit contributions | |
blance | -0.024 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.021 |
nesota | -0.020 |
Token | lt |
Token ID | 2528 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
blance | +0.029 |
uments | +0.028 |
arthed | +0.028 |
ondon | +0.026 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.016 |
BUR | -0.016 |
osit | -0.015 |
iated | -0.015 |
Token | n |
Token ID | 77 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
ogens | +0.125 |
Debor | +0.116 |
BUR | +0.114 |
osit | +0.111 |
supervision | +0.109 |
Neg logit contributions | |
blance | -0.133 |
uments | -0.124 |
arthed | -0.123 |
ondon | -0.117 |
nesota | -0.110 |
Token | isse |
Token ID | 20782 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.010 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.020 |
uments | -0.019 |
arthed | -0.019 |
ondon | -0.018 |
nesota | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
ogens | +0.286 |
Debor | +0.266 |
BUR | +0.260 |
osit | +0.254 |
supervision | +0.249 |
Neg logit contributions | |
blance | -0.315 |
uments | -0.294 |
arthed | -0.294 |
ondon | -0.278 |
nesota | -0.265 |
Token | is |
Token ID | 318 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
blance | +0.024 |
uments | +0.023 |
arthed | +0.022 |
ondon | +0.021 |
nesota | +0.020 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.017 |
BUR | -0.017 |
osit | -0.016 |
supervision | -0.016 |
Token | just |
Token ID | 655 |
Feature activation | -7.11e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | another |
Token ID | 1194 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
ogens | +0.022 |
Debor | +0.021 |
BUR | +0.020 |
osit | +0.020 |
supervision | +0.019 |
Neg logit contributions | |
blance | -0.026 |
uments | -0.025 |
arthed | -0.025 |
ondon | -0.023 |
nesota | -0.022 |
Token | way |
Token ID | 835 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
ogens | +0.079 |
Debor | +0.073 |
BUR | +0.071 |
osit | +0.068 |
supervision | +0.067 |
Neg logit contributions | |
blance | -0.117 |
uments | -0.111 |
arthed | -0.110 |
ondon | -0.105 |
nesota | -0.101 |
Token | a |
Token ID | 257 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
blance | +0.020 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.017 |
Debor | -0.016 |
BUR | -0.016 |
osit | -0.015 |
supervision | -0.015 |
Token | crust |
Token ID | 20048 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.012 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.009 |
Debor | -0.009 |
BUR | -0.008 |
osit | -0.008 |
supervision | -0.008 |
Token | y |
Token ID | 88 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | old |
Token ID | 1468 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ogens | +0.088 |
Debor | +0.082 |
BUR | +0.079 |
osit | +0.077 |
supervision | +0.076 |
Neg logit contributions | |
blance | -0.115 |
uments | -0.109 |
arthed | -0.107 |
ondon | -0.102 |
nesota | -0.097 |
Token | bl |
Token ID | 698 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.003 |
supervision | -0.003 |
Token | oke |
Token ID | 2088 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
blance | +0.144 |
uments | +0.138 |
arthed | +0.137 |
ondon | +0.133 |
nesota | +0.129 |
Neg logit contributions | |
ogens | -0.021 |
Debor | -0.015 |
BUR | -0.014 |
osit | -0.013 |
iated | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
ogens | +0.265 |
Debor | +0.249 |
BUR | +0.241 |
osit | +0.234 |
supervision | +0.230 |
Neg logit contributions | |
blance | -0.331 |
uments | -0.312 |
arthed | -0.309 |
ondon | -0.293 |
nesota | -0.279 |
Token | a |
Token ID | 257 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
blance | +0.030 |
uments | +0.028 |
arthed | +0.028 |
ondon | +0.026 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.026 |
Debor | -0.025 |
BUR | -0.024 |
osit | -0.023 |
supervision | -0.023 |
Token | stool |
Token ID | 38753 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
blance | +0.023 |
uments | +0.022 |
arthed | +0.022 |
ondon | +0.021 |
nesota | +0.020 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.016 |
BUR | -0.016 |
osit | -0.015 |
supervision | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
blance | +0.136 |
uments | +0.128 |
arthed | +0.127 |
ondon | +0.121 |
nesota | +0.115 |
Neg logit contributions | |
ogens | -0.112 |
Debor | -0.104 |
BUR | -0.102 |
osit | -0.099 |
supervision | -0.097 |
Token | ask |
Token ID | 1265 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
blance | +0.023 |
uments | +0.022 |
arthed | +0.022 |
ondon | +0.021 |
nesota | +0.020 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.017 |
BUR | -0.017 |
osit | -0.016 |
supervision | -0.016 |
Token | areas |
Token ID | 3006 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
blance | +0.000 |
uments | +0.000 |
arthed | +0.000 |
ondon | +0.000 |
nesota | +0.000 |
Neg logit contributions | |
ogens | -0.000 |
Debor | -0.000 |
BUR | -0.000 |
osit | -0.000 |
supervision | -0.000 |
Token | might |
Token ID | 1244 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
blance | +0.069 |
uments | +0.065 |
arthed | +0.064 |
ondon | +0.061 |
nesota | +0.058 |
Neg logit contributions | |
ogens | -0.057 |
Debor | -0.053 |
BUR | -0.051 |
osit | -0.050 |
supervision | -0.049 |
Token | be |
Token ID | 307 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.019 |
BUR | +0.018 |
osit | +0.018 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.024 |
uments | -0.022 |
arthed | -0.022 |
ondon | -0.021 |
nesota | -0.020 |
Token | off |
Token ID | 572 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
blance | +0.016 |
uments | +0.015 |
arthed | +0.015 |
ondon | +0.014 |
nesota | +0.014 |
Neg logit contributions | |
ogens | -0.012 |
Debor | -0.011 |
BUR | -0.011 |
osit | -0.011 |
supervision | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ogens | +0.044 |
Debor | +0.041 |
BUR | +0.039 |
osit | +0.038 |
supervision | +0.037 |
Neg logit contributions | |
blance | -0.078 |
uments | -0.074 |
arthed | -0.074 |
ondon | -0.071 |
nesota | -0.068 |
Token | limits |
Token ID | 49196 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
blance | +0.012 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.012 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
ogens | +0.270 |
Debor | +0.252 |
BUR | +0.245 |
osit | +0.238 |
supervision | +0.235 |
Neg logit contributions | |
blance | -0.325 |
uments | -0.304 |
arthed | -0.301 |
ondon | -0.287 |
nesota | -0.273 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
blance | +0.004 |
uments | +0.004 |
arthed | +0.004 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.63e-03 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.003 |
Token | La |
Token ID | 14772 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | ure |
Token ID | 495 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
blance | +0.031 |
uments | +0.030 |
arthed | +0.029 |
ondon | +0.028 |
nesota | +0.026 |
Neg logit contributions | |
ogens | -0.025 |
Debor | -0.024 |
BUR | -0.023 |
osit | -0.022 |
supervision | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
blance | +0.060 |
uments | +0.056 |
arthed | +0.056 |
ondon | +0.053 |
nesota | +0.050 |
Neg logit contributions | |
ogens | -0.050 |
Debor | -0.047 |
BUR | -0.046 |
osit | -0.044 |
supervision | -0.044 |
Token | im |
Token ID | 320 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.000 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.000 |
nesota | -0.000 |
Token | aging |
Token ID | 3039 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
ogens | +0.097 |
Debor | +0.087 |
BUR | +0.085 |
osit | +0.083 |
iated | +0.081 |
Neg logit contributions | |
blance | -0.144 |
arthed | -0.136 |
uments | -0.135 |
ondon | -0.128 |
nesota | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
blance | +0.000 |
uments | +0.000 |
arthed | +0.000 |
ondon | +0.000 |
nesota | +0.000 |
Neg logit contributions | |
ogens | -0.000 |
Debor | -0.000 |
BUR | -0.000 |
osit | -0.000 |
supervision | -0.000 |
Token | image |
Token ID | 9060 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | format |
Token ID | 18982 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.012 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.013 |
Debor | -0.012 |
BUR | -0.011 |
osit | -0.011 |
iated | -0.011 |
Token | ] |
Token ID | 60 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
ogens | +0.270 |
Debor | +0.253 |
BUR | +0.246 |
osit | +0.242 |
iated | +0.237 |
Neg logit contributions | |
blance | -0.311 |
arthed | -0.288 |
uments | -0.287 |
ondon | -0.273 |
nesota | -0.261 |
Token | :: |
Token ID | 3712 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.000 |
uments | -0.000 |
arthed | -0.000 |
ondon | -0.000 |
nesota | -0.000 |
Token | B |
Token ID | 33 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
blance | +0.199 |
uments | +0.186 |
arthed | +0.185 |
ondon | +0.176 |
nesota | +0.168 |
Neg logit contributions | |
ogens | -0.168 |
Debor | -0.156 |
BUR | -0.154 |
osit | -0.149 |
iated | -0.145 |
Token | mp |
Token ID | 3149 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
blance | +0.072 |
uments | +0.068 |
arthed | +0.067 |
ondon | +0.064 |
nesota | +0.061 |
Neg logit contributions | |
ogens | -0.057 |
Debor | -0.053 |
BUR | -0.052 |
osit | -0.051 |
iated | -0.049 |
Token | ); |
Token ID | 1776 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
ogens | +0.113 |
Debor | +0.105 |
BUR | +0.103 |
osit | +0.101 |
iated | +0.098 |
Neg logit contributions | |
blance | -0.134 |
uments | -0.124 |
arthed | -0.124 |
ondon | -0.118 |
nesota | -0.113 |
Token | That |
Token ID | 1320 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
blance | +0.019 |
uments | +0.018 |
arthed | +0.018 |
ondon | +0.017 |
nesota | +0.016 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.012 |
supervision | -0.012 |
Token | never |
Token ID | 1239 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
ogens | +0.023 |
Debor | +0.021 |
BUR | +0.020 |
osit | +0.020 |
supervision | +0.019 |
Neg logit contributions | |
blance | -0.031 |
uments | -0.029 |
arthed | -0.029 |
ondon | -0.028 |
nesota | -0.026 |
Token | changes |
Token ID | 2458 |
Feature activation | +6.21e-02 |
Pos logit contributions | |
ogens | +0.019 |
Debor | +0.017 |
BUR | +0.017 |
osit | +0.016 |
supervision | +0.016 |
Neg logit contributions | |
blance | -0.027 |
uments | -0.025 |
arthed | -0.025 |
ondon | -0.024 |
nesota | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
blance | +0.023 |
uments | +0.022 |
arthed | +0.022 |
ondon | +0.021 |
nesota | +0.020 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.018 |
BUR | -0.017 |
osit | -0.017 |
supervision | -0.016 |
Token | me |
Token ID | 502 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
blance | +0.008 |
uments | +0.007 |
arthed | +0.007 |
ondon | +0.007 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.008 |
BUR | -0.008 |
osit | -0.007 |
supervision | -0.007 |
Token | anyway |
Token ID | 6949 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
blance | +0.053 |
uments | +0.050 |
arthed | +0.050 |
ondon | +0.047 |
nesota | +0.045 |
Neg logit contributions | |
ogens | -0.043 |
Debor | -0.040 |
BUR | -0.039 |
osit | -0.038 |
supervision | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
blance | +0.230 |
uments | +0.216 |
arthed | +0.215 |
ondon | +0.204 |
nesota | +0.194 |
Neg logit contributions | |
ogens | -0.187 |
Debor | -0.174 |
BUR | -0.169 |
osit | -0.165 |
supervision | -0.161 |
Token | I |
Token ID | 314 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
blance | +0.019 |
uments | +0.018 |
arthed | +0.018 |
ondon | +0.017 |
nesota | +0.016 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.012 |
supervision | -0.012 |
Token | � |
Token ID | 447 |
Feature activation | +5.73e-02 |
Pos logit contributions | |
blance | +0.013 |
uments | +0.012 |
arthed | +0.012 |
ondon | +0.012 |
nesota | +0.011 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.010 |
BUR | -0.010 |
osit | -0.010 |
supervision | -0.010 |
Token | � |
Token ID | 247 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
blance | +0.021 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.017 |
BUR | -0.017 |
osit | -0.016 |
iated | -0.016 |
Token | d |
Token ID | 67 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
blance | +0.018 |
uments | +0.017 |
arthed | +0.017 |
ondon | +0.016 |
nesota | +0.015 |
Neg logit contributions | |
ogens | -0.015 |
Debor | -0.014 |
BUR | -0.013 |
osit | -0.013 |
supervision | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
blance | +0.033 |
uments | +0.031 |
arthed | +0.031 |
ondon | +0.029 |
nesota | +0.028 |
Neg logit contributions | |
ogens | -0.028 |
Debor | -0.026 |
BUR | -0.026 |
osit | -0.025 |
supervision | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.014 |
nesota | +0.013 |
Neg logit contributions | |
ogens | -0.011 |
Debor | -0.011 |
BUR | -0.010 |
osit | -0.010 |
supervision | -0.010 |
Token | 1992 |
Token ID | 23847 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
blance | +0.008 |
uments | +0.007 |
arthed | +0.007 |
ondon | +0.007 |
nesota | +0.006 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.008 |
BUR | -0.008 |
osit | -0.008 |
supervision | -0.007 |
Token | Jerry |
Token ID | 13075 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
ogens | +0.036 |
Debor | +0.033 |
BUR | +0.032 |
osit | +0.031 |
supervision | +0.030 |
Neg logit contributions | |
blance | -0.050 |
uments | -0.047 |
arthed | -0.046 |
ondon | -0.044 |
nesota | -0.042 |
Token | Se |
Token ID | 1001 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
blance | +0.043 |
uments | +0.040 |
arthed | +0.040 |
ondon | +0.038 |
nesota | +0.036 |
Neg logit contributions | |
ogens | -0.035 |
Debor | -0.033 |
BUR | -0.032 |
osit | -0.031 |
iated | -0.031 |
Token | infeld |
Token ID | 47187 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
ogens | +0.089 |
Debor | +0.085 |
BUR | +0.084 |
osit | +0.082 |
iated | +0.081 |
Neg logit contributions | |
blance | -0.036 |
uments | -0.031 |
arthed | -0.031 |
ondon | -0.027 |
nesota | -0.025 |
Token | 1993 |
Token ID | 9656 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
blance | +0.256 |
uments | +0.241 |
arthed | +0.238 |
ondon | +0.226 |
nesota | +0.213 |
Neg logit contributions | |
ogens | -0.238 |
Debor | -0.223 |
BUR | -0.217 |
osit | -0.213 |
supervision | -0.207 |
Token | Ted |
Token ID | 11396 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
ogens | +0.028 |
Debor | +0.026 |
BUR | +0.025 |
osit | +0.025 |
supervision | +0.024 |
Neg logit contributions | |
blance | -0.037 |
uments | -0.035 |
arthed | -0.034 |
ondon | -0.033 |
nesota | -0.031 |
Token | D |
Token ID | 360 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
ogens | +0.083 |
Debor | +0.079 |
BUR | +0.076 |
osit | +0.074 |
iated | +0.073 |
Neg logit contributions | |
blance | -0.095 |
uments | -0.088 |
arthed | -0.087 |
ondon | -0.083 |
nesota | -0.079 |
Token | anson |
Token ID | 23103 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
blance | +0.037 |
uments | +0.035 |
arthed | +0.034 |
ondon | +0.033 |
nesota | +0.031 |
Neg logit contributions | |
ogens | -0.035 |
Debor | -0.033 |
BUR | -0.032 |
osit | -0.031 |
supervision | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | � |
Token ID | 447 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.004 |
supervision | -0.004 |
Token | � |
Token ID | 251 |
Feature activation | -6.25e-03 |
Pos logit contributions | |
blance | +0.001 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.001 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | Owen |
Token ID | 22605 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.010 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.008 |
nesota | -0.008 |
Token | Do |
Token ID | 2141 |
Feature activation | +8.79e-02 |
Pos logit contributions | |
blance | +0.056 |
uments | +0.052 |
arthed | +0.052 |
ondon | +0.049 |
nesota | +0.047 |
Neg logit contributions | |
ogens | -0.048 |
Debor | -0.045 |
BUR | -0.044 |
osit | -0.043 |
supervision | -0.042 |
Token | herty |
Token ID | 29029 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
blance | +0.021 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.016 |
Neg logit contributions | |
ogens | -0.039 |
Debor | -0.037 |
BUR | -0.036 |
osit | -0.035 |
supervision | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
blance | +0.341 |
uments | +0.321 |
arthed | +0.317 |
ondon | +0.302 |
nesota | +0.287 |
Neg logit contributions | |
ogens | -0.270 |
Debor | -0.251 |
BUR | -0.244 |
osit | -0.237 |
supervision | -0.233 |
Token | climate |
Token ID | 4258 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
blance | +0.008 |
uments | +0.008 |
arthed | +0.007 |
ondon | +0.007 |
nesota | +0.007 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | model |
Token ID | 2746 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ogens | +0.046 |
Debor | +0.042 |
BUR | +0.041 |
osit | +0.040 |
supervision | +0.039 |
Neg logit contributions | |
blance | -0.059 |
uments | -0.055 |
arthed | -0.055 |
ondon | -0.052 |
nesota | -0.050 |
Token | er |
Token ID | 263 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
blance | +0.058 |
uments | +0.054 |
arthed | +0.053 |
ondon | +0.051 |
nesota | +0.048 |
Neg logit contributions | |
ogens | -0.057 |
Debor | -0.053 |
BUR | -0.052 |
osit | -0.051 |
supervision | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
blance | +0.055 |
uments | +0.052 |
arthed | +0.051 |
ondon | +0.049 |
nesota | +0.046 |
Neg logit contributions | |
ogens | -0.042 |
Debor | -0.040 |
BUR | -0.038 |
osit | -0.037 |
supervision | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
blance | +0.139 |
uments | +0.131 |
arthed | +0.129 |
ondon | +0.123 |
nesota | +0.117 |
Neg logit contributions | |
ogens | -0.110 |
Debor | -0.102 |
BUR | -0.100 |
osit | -0.097 |
supervision | -0.095 |
Token | Gand |
Token ID | 17727 |
Feature activation | -7.29e-03 |
Pos logit contributions | |
blance | +0.023 |
uments | +0.021 |
arthed | +0.021 |
ondon | +0.020 |
nesota | +0.019 |
Neg logit contributions | |
ogens | -0.022 |
Debor | -0.020 |
BUR | -0.020 |
osit | -0.019 |
supervision | -0.019 |
Token | hin |
Token ID | 20079 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.003 |
iated | +0.003 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.001 |
Token | agar |
Token ID | 32452 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
blance | +0.161 |
uments | +0.155 |
arthed | +0.154 |
ondon | +0.149 |
nesota | +0.143 |
Neg logit contributions | |
ogens | -0.045 |
Debor | -0.039 |
BUR | -0.037 |
osit | -0.034 |
supervision | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +6.48e-02 |
Pos logit contributions | |
ogens | +0.097 |
Debor | +0.090 |
BUR | +0.088 |
osit | +0.086 |
supervision | +0.084 |
Neg logit contributions | |
blance | -0.123 |
uments | -0.116 |
arthed | -0.114 |
ondon | -0.109 |
nesota | -0.104 |
Token | Gujarat |
Token ID | 30311 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
blance | +0.020 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.017 |
nesota | +0.016 |
Neg logit contributions | |
ogens | -0.024 |
Debor | -0.023 |
BUR | -0.022 |
osit | -0.022 |
supervision | -0.021 |
Token | 38 |
Token ID | 4353 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
blance | +0.227 |
uments | +0.212 |
arthed | +0.210 |
ondon | +0.200 |
nesota | +0.190 |
Neg logit contributions | |
ogens | -0.200 |
Debor | -0.187 |
BUR | -0.183 |
osit | -0.178 |
supervision | -0.174 |
Token | 2020 |
Token ID | 42334 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.006 |
arthed | +0.006 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.006 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.005 |
iated | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
blance | +0.214 |
uments | +0.202 |
arthed | +0.199 |
ondon | +0.190 |
nesota | +0.180 |
Neg logit contributions | |
ogens | -0.180 |
Debor | -0.168 |
BUR | -0.163 |
osit | -0.159 |
supervision | -0.156 |
Token | India |
Token ID | 3794 |
Feature activation | +6.63e-02 |
Pos logit contributions | |
blance | +0.025 |
uments | +0.023 |
arthed | +0.023 |
ondon | +0.022 |
nesota | +0.021 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.017 |
BUR | -0.016 |
osit | -0.016 |
supervision | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
blance | +0.026 |
uments | +0.025 |
arthed | +0.024 |
ondon | +0.023 |
nesota | +0.022 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.018 |
BUR | -0.017 |
osit | -0.017 |
supervision | -0.016 |
Token | ) |
Token ID | 8 |
Feature activation | -5.49e-03 |
Pos logit contributions | |
blance | +0.041 |
uments | +0.039 |
arthed | +0.038 |
ondon | +0.037 |
nesota | +0.035 |
Neg logit contributions | |
ogens | -0.035 |
Debor | -0.032 |
BUR | -0.032 |
osit | -0.031 |
supervision | -0.030 |
Token | - |
Token ID | 532 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | Latin |
Token ID | 9133 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
ogens | +0.022 |
Debor | +0.021 |
BUR | +0.020 |
osit | +0.019 |
supervision | +0.019 |
Neg logit contributions | |
blance | -0.026 |
uments | -0.024 |
arthed | -0.024 |
ondon | -0.023 |
nesota | -0.022 |
Token | American |
Token ID | 1605 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
blance | +0.145 |
uments | +0.138 |
arthed | +0.137 |
ondon | +0.131 |
nesota | +0.125 |
Neg logit contributions | |
ogens | -0.087 |
Debor | -0.080 |
BUR | -0.077 |
osit | -0.075 |
iated | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
ogens | +0.007 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.006 |
iated | +0.006 |
Neg logit contributions | |
blance | -0.012 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.011 |
Token | Caribbean |
Token ID | 18020 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.011 |
BUR | +0.010 |
osit | +0.010 |
supervision | +0.010 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.006 |
arthed | -0.006 |
ondon | -0.005 |
nesota | -0.005 |
Token | leaders |
Token ID | 2766 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
blance | +0.293 |
uments | +0.278 |
arthed | +0.275 |
ondon | +0.264 |
nesota | +0.251 |
Neg logit contributions | |
ogens | -0.190 |
Debor | -0.174 |
BUR | -0.169 |
osit | -0.164 |
iated | -0.159 |
Token | converge |
Token ID | 47873 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
ogens | +0.040 |
Debor | +0.037 |
BUR | +0.036 |
osit | +0.035 |
supervision | +0.034 |
Neg logit contributions | |
blance | -0.054 |
uments | -0.051 |
arthed | -0.051 |
ondon | -0.048 |
nesota | -0.046 |
Token | on |
Token ID | 319 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
ogens | +0.077 |
Debor | +0.072 |
BUR | +0.070 |
osit | +0.068 |
supervision | +0.067 |
Neg logit contributions | |
blance | -0.093 |
uments | -0.088 |
arthed | -0.087 |
ondon | -0.082 |
nesota | -0.079 |
Token | Cuba |
Token ID | 14159 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | this |
Token ID | 428 |
Feature activation | +4.45e-03 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.010 |
uments | -0.010 |
arthed | -0.009 |
ondon | -0.009 |
nesota | -0.009 |
Token | Dev |
Token ID | 6245 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
blance | +0.025 |
uments | +0.023 |
arthed | +0.023 |
ondon | +0.022 |
nesota | +0.021 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.018 |
BUR | -0.018 |
osit | -0.017 |
supervision | -0.017 |
Token | ial |
Token ID | 498 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
blance | +0.159 |
arthed | +0.150 |
uments | +0.150 |
ondon | +0.143 |
nesota | +0.137 |
Neg logit contributions | |
ogens | -0.089 |
Debor | -0.080 |
BUR | -0.078 |
osit | -0.076 |
iated | -0.075 |
Token | ets |
Token ID | 1039 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
blance | +0.011 |
uments | +0.010 |
arthed | +0.010 |
ondon | +0.010 |
nesota | +0.009 |
Neg logit contributions | |
ogens | -0.013 |
Debor | -0.012 |
BUR | -0.012 |
osit | -0.011 |
iated | -0.011 |
Token | � |
Token ID | 447 |
Feature activation | -5.89e-03 |
Pos logit contributions | |
blance | +0.118 |
uments | +0.112 |
arthed | +0.111 |
ondon | +0.106 |
nesota | +0.101 |
Neg logit contributions | |
ogens | -0.085 |
Debor | -0.079 |
BUR | -0.076 |
osit | -0.074 |
supervision | -0.072 |
Token | � |
Token ID | 247 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | st |
Token ID | 336 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.002 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | up |
Token ID | 929 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
blance | +0.035 |
uments | +0.033 |
arthed | +0.032 |
ondon | +0.030 |
nesota | +0.029 |
Neg logit contributions | |
ogens | -0.036 |
Debor | -0.034 |
BUR | -0.033 |
osit | -0.032 |
supervision | -0.031 |
Token | end |
Token ID | 437 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
ogens | +0.141 |
Debor | +0.133 |
BUR | +0.130 |
osit | +0.128 |
supervision | +0.125 |
Neg logit contributions | |
blance | -0.108 |
uments | -0.100 |
arthed | -0.099 |
ondon | -0.092 |
nesota | -0.087 |
Token | ous |
Token ID | 516 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
blance | +0.092 |
uments | +0.088 |
arthed | +0.087 |
ondon | +0.084 |
nesota | +0.082 |
Neg logit contributions | |
ogens | -0.028 |
Debor | -0.024 |
BUR | -0.023 |
osit | -0.021 |
supervision | -0.020 |
Token | imaging |
Token ID | 19560 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
ogens | +0.108 |
Debor | +0.100 |
BUR | +0.097 |
osit | +0.094 |
supervision | +0.092 |
Neg logit contributions | |
blance | -0.154 |
uments | -0.146 |
arthed | -0.145 |
ondon | -0.138 |
nesota | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ogens | +0.018 |
Debor | +0.017 |
BUR | +0.017 |
osit | +0.016 |
supervision | +0.016 |
Neg logit contributions | |
blance | -0.025 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.022 |
nesota | -0.021 |
Token | 9 |
Token ID | 860 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.003 |
BUR | +0.003 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.002 |
Token | 2007 |
Token ID | 4343 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ogens | +0.053 |
Debor | +0.050 |
BUR | +0.049 |
osit | +0.048 |
supervision | +0.047 |
Neg logit contributions | |
blance | -0.045 |
uments | -0.042 |
arthed | -0.041 |
ondon | -0.039 |
nesota | -0.036 |
Token | 6 |
Token ID | 718 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.005 |
supervision | -0.004 |
Token | 0 |
Token ID | 657 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
ogens | +0.024 |
Debor | +0.023 |
BUR | +0.022 |
osit | +0.022 |
supervision | +0.021 |
Neg logit contributions | |
blance | -0.026 |
uments | -0.024 |
arthed | -0.024 |
ondon | -0.023 |
nesota | -0.022 |
Token | 2008 |
Token ID | 3648 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
ogens | +0.065 |
Debor | +0.061 |
BUR | +0.060 |
osit | +0.058 |
supervision | +0.057 |
Neg logit contributions | |
blance | -0.058 |
uments | -0.054 |
arthed | -0.053 |
ondon | -0.050 |
nesota | -0.047 |
Token | 15 |
Token ID | 1315 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.010 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.010 |
arthed | -0.010 |
ondon | -0.009 |
nesota | -0.009 |
Token | 4 |
Token ID | 604 |
Feature activation | -7.14e-02 |
Pos logit contributions | |
blance | +0.021 |
uments | +0.019 |
arthed | +0.019 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.020 |
Debor | -0.018 |
BUR | -0.018 |
osit | -0.017 |
supervision | -0.017 |
Token | 2009 |
Token ID | 3717 |
Feature activation | -7.27e-02 |
Pos logit contributions | |
ogens | +0.025 |
Debor | +0.024 |
BUR | +0.023 |
osit | +0.023 |
supervision | +0.022 |
Neg logit contributions | |
blance | -0.023 |
uments | -0.022 |
arthed | -0.021 |
ondon | -0.020 |
nesota | -0.019 |
Token | 10 |
Token ID | 838 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ogens | +0.024 |
Debor | +0.023 |
BUR | +0.022 |
osit | +0.022 |
supervision | +0.021 |
Neg logit contributions | |
blance | -0.026 |
uments | -0.024 |
arthed | -0.024 |
ondon | -0.022 |
nesota | -0.021 |
Token | 2 |
Token ID | 362 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
blance | +0.043 |
uments | +0.040 |
arthed | +0.040 |
ondon | +0.038 |
nesota | +0.036 |
Neg logit contributions | |
ogens | -0.040 |
Debor | -0.038 |
BUR | -0.037 |
osit | -0.036 |
supervision | -0.035 |
Token | 2010 |
Token ID | 3050 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.008 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.007 |
nesota | -0.006 |
Token | we |
Token ID | 356 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
blance | +0.078 |
uments | +0.073 |
arthed | +0.073 |
ondon | +0.069 |
nesota | +0.066 |
Neg logit contributions | |
ogens | -0.055 |
Debor | -0.052 |
BUR | -0.050 |
osit | -0.049 |
supervision | -0.048 |
Token | 've |
Token ID | 1053 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
blance | +0.018 |
uments | +0.017 |
arthed | +0.017 |
ondon | +0.016 |
nesota | +0.015 |
Neg logit contributions | |
ogens | -0.016 |
Debor | -0.014 |
BUR | -0.014 |
osit | -0.014 |
iated | -0.013 |
Token | all |
Token ID | 477 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
blance | +0.019 |
uments | +0.018 |
arthed | +0.018 |
ondon | +0.017 |
nesota | +0.016 |
Neg logit contributions | |
ogens | -0.015 |
Debor | -0.014 |
BUR | -0.014 |
osit | -0.014 |
supervision | -0.013 |
Token | agreed |
Token ID | 4987 |
Feature activation | -6.40e-02 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.008 |
BUR | +0.008 |
osit | +0.008 |
iated | +0.008 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.010 |
arthed | -0.010 |
ondon | -0.010 |
nesota | -0.009 |
Token | that |
Token ID | 326 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
ogens | +0.019 |
Debor | +0.018 |
BUR | +0.018 |
osit | +0.017 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.024 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.022 |
nesota | -0.020 |
Token | maybe |
Token ID | 3863 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.005 |
BUR | +0.005 |
osit | +0.005 |
supervision | +0.005 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.007 |
nesota | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
blance | +0.055 |
uments | +0.052 |
arthed | +0.051 |
ondon | +0.049 |
nesota | +0.046 |
Neg logit contributions | |
ogens | -0.042 |
Debor | -0.040 |
BUR | -0.039 |
osit | -0.037 |
supervision | -0.037 |
Token | episode |
Token ID | 4471 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
ogens | +0.006 |
Debor | +0.005 |
BUR | +0.005 |
osit | +0.005 |
supervision | +0.005 |
Neg logit contributions | |
blance | -0.007 |
uments | -0.007 |
arthed | -0.007 |
ondon | -0.007 |
nesota | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
blance | +0.017 |
uments | +0.016 |
arthed | +0.016 |
ondon | +0.015 |
nesota | +0.014 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.013 |
osit | -0.013 |
supervision | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.010 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.012 |
nesota | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | if |
Token ID | 611 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | answered |
Token ID | 9373 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
ogens | +0.007 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.006 |
supervision | +0.006 |
Neg logit contributions | |
blance | -0.009 |
uments | -0.008 |
arthed | -0.008 |
ondon | -0.008 |
nesota | -0.007 |
Token | — |
Token ID | 851 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ogens | +0.093 |
Debor | +0.087 |
BUR | +0.084 |
osit | +0.082 |
supervision | +0.080 |
Neg logit contributions | |
blance | -0.118 |
uments | -0.111 |
arthed | -0.110 |
ondon | -0.104 |
nesota | -0.100 |
Token | Golden |
Token ID | 8407 |
Feature activation | +9.17e-02 |
Pos logit contributions | |
ogens | +0.043 |
Debor | +0.041 |
BUR | +0.039 |
osit | +0.038 |
supervision | +0.038 |
Neg logit contributions | |
blance | -0.054 |
uments | -0.051 |
arthed | -0.050 |
ondon | -0.048 |
nesota | -0.045 |
Token | State |
Token ID | 9012 |
Feature activation | -2.41e-03 |
Pos logit contributions | |
blance | +0.031 |
uments | +0.029 |
arthed | +0.029 |
ondon | +0.027 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.032 |
Debor | -0.030 |
BUR | -0.029 |
osit | -0.028 |
supervision | -0.028 |
Token | War |
Token ID | 13195 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | riors |
Token ID | 8657 |
Feature activation | +7.11e-02 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.005 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.004 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.003 |
Token | (@ |
Token ID | 4275 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
blance | +0.030 |
uments | +0.028 |
arthed | +0.028 |
ondon | +0.027 |
nesota | +0.026 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.017 |
BUR | -0.017 |
osit | -0.016 |
supervision | -0.016 |
Token | war |
Token ID | 5767 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
ogens | +0.083 |
Debor | +0.076 |
BUR | +0.075 |
osit | +0.073 |
iated | +0.071 |
Neg logit contributions | |
blance | -0.098 |
uments | -0.092 |
arthed | -0.091 |
ondon | -0.087 |
nesota | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
ogens | +0.043 |
Debor | +0.040 |
BUR | +0.039 |
osit | +0.038 |
iated | +0.037 |
Neg logit contributions | |
blance | -0.055 |
uments | -0.052 |
arthed | -0.051 |
ondon | -0.049 |
nesota | -0.046 |
Token | Sun |
Token ID | 3825 |
Feature activation | +9.85e-02 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.010 |
BUR | +0.009 |
osit | +0.009 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.013 |
arthed | -0.013 |
ondon | -0.012 |
nesota | -0.012 |
Token | an |
Token ID | 272 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
blance | +0.030 |
uments | +0.028 |
arthed | +0.028 |
ondon | +0.026 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.037 |
Debor | -0.035 |
BUR | -0.034 |
osit | -0.033 |
iated | -0.033 |
Token | Abu |
Token ID | 13098 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
blance | +0.084 |
uments | +0.079 |
arthed | +0.078 |
ondon | +0.074 |
nesota | +0.071 |
Neg logit contributions | |
ogens | -0.065 |
Debor | -0.061 |
BUR | -0.059 |
osit | -0.057 |
supervision | -0.057 |
Token | Daw |
Token ID | 17552 |
Feature activation | +5.03e-02 |
Pos logit contributions | |
ogens | +0.076 |
Debor | +0.071 |
BUR | +0.069 |
osit | +0.067 |
supervision | +0.066 |
Neg logit contributions | |
blance | -0.088 |
uments | -0.082 |
arthed | -0.082 |
ondon | -0.078 |
nesota | -0.074 |
Token | ud |
Token ID | 463 |
Feature activation | +7.15e-02 |
Pos logit contributions | |
blance | +0.017 |
uments | +0.016 |
arthed | +0.016 |
ondon | +0.015 |
nesota | +0.014 |
Neg logit contributions | |
ogens | -0.017 |
Debor | -0.016 |
BUR | -0.015 |
osit | -0.015 |
supervision | -0.015 |
Token | 14 |
Token ID | 1478 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
blance | +0.028 |
uments | +0.027 |
arthed | +0.026 |
ondon | +0.025 |
nesota | +0.024 |
Neg logit contributions | |
ogens | -0.020 |
Debor | -0.019 |
BUR | -0.018 |
osit | -0.018 |
supervision | -0.018 |
Token | : |
Token ID | 25 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ogens | +0.031 |
Debor | +0.029 |
BUR | +0.028 |
osit | +0.027 |
supervision | +0.027 |
Neg logit contributions | |
blance | -0.038 |
uments | -0.036 |
arthed | -0.036 |
ondon | -0.034 |
nesota | -0.032 |
Token | 26 |
Token ID | 2075 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.005 |
Debor | -0.005 |
BUR | -0.005 |
osit | -0.004 |
supervision | -0.004 |
Token | 65 |
Token ID | 2996 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
blance | +0.082 |
uments | +0.077 |
arthed | +0.077 |
ondon | +0.073 |
nesota | +0.070 |
Neg logit contributions | |
ogens | -0.060 |
Debor | -0.056 |
BUR | -0.055 |
osit | -0.053 |
supervision | -0.052 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
blance | +0.025 |
uments | +0.023 |
arthed | +0.023 |
ondon | +0.022 |
nesota | +0.021 |
Neg logit contributions | |
ogens | -0.018 |
Debor | -0.017 |
BUR | -0.016 |
osit | -0.016 |
supervision | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
blance | +0.017 |
uments | +0.016 |
arthed | +0.015 |
ondon | +0.015 |
nesota | +0.014 |
Neg logit contributions | |
ogens | -0.012 |
Debor | -0.011 |
BUR | -0.011 |
osit | -0.011 |
supervision | -0.010 |
Token | Last |
Token ID | 5956 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
blance | +0.020 |
uments | +0.018 |
arthed | +0.018 |
ondon | +0.018 |
nesota | +0.017 |
Neg logit contributions | |
ogens | -0.013 |
Debor | -0.012 |
BUR | -0.012 |
osit | -0.012 |
iated | -0.011 |
Token | year |
Token ID | 614 |
Feature activation | -5.45e-02 |
Pos logit contributions | |
ogens | +0.047 |
Debor | +0.044 |
BUR | +0.042 |
osit | +0.041 |
supervision | +0.040 |
Neg logit contributions | |
blance | -0.063 |
uments | -0.060 |
arthed | -0.059 |
ondon | -0.056 |
nesota | -0.053 |
Token | at |
Token ID | 379 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
ogens | +0.016 |
Debor | +0.015 |
BUR | +0.015 |
osit | +0.014 |
supervision | +0.014 |
Neg logit contributions | |
blance | -0.021 |
uments | -0.020 |
arthed | -0.020 |
ondon | -0.019 |
nesota | -0.018 |
Token | this |
Token ID | 428 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
blance | +0.001 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.001 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | +8.51e-03 |
Pos logit contributions | |
blance | +0.018 |
uments | +0.017 |
arthed | +0.017 |
ondon | +0.016 |
nesota | +0.015 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.012 |
osit | -0.012 |
supervision | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +6.44e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
blance | +0.024 |
uments | +0.022 |
arthed | +0.022 |
ondon | +0.021 |
aiden | +0.020 |
Neg logit contributions | |
ogens | -0.020 |
Debor | -0.019 |
BUR | -0.018 |
osit | -0.018 |
supervision | -0.018 |
Token | folks |
Token ID | 7974 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
blance | +0.008 |
uments | +0.008 |
arthed | +0.008 |
ondon | +0.007 |
nesota | +0.007 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | from |
Token ID | 422 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
blance | +0.111 |
uments | +0.104 |
arthed | +0.103 |
ondon | +0.098 |
nesota | +0.093 |
Neg logit contributions | |
ogens | -0.089 |
Debor | -0.083 |
BUR | -0.081 |
osit | -0.078 |
supervision | -0.077 |
Token | Boise |
Token ID | 38830 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.002 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | over |
Token ID | 625 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
blance | +0.052 |
uments | +0.049 |
arthed | +0.048 |
ondon | +0.046 |
nesota | +0.044 |
Neg logit contributions | |
ogens | -0.040 |
Debor | -0.037 |
BUR | -0.036 |
osit | -0.035 |
iated | -0.034 |
Token | step |
Token ID | 9662 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
ogens | +0.047 |
Debor | +0.043 |
BUR | +0.042 |
osit | +0.041 |
supervision | +0.040 |
Neg logit contributions | |
blance | -0.061 |
uments | -0.057 |
arthed | -0.057 |
ondon | -0.054 |
nesota | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | bounds |
Token ID | 22303 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
blance | +0.004 |
uments | +0.004 |
arthed | +0.004 |
ondon | +0.004 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ogens | +0.129 |
Debor | +0.120 |
BUR | +0.117 |
osit | +0.113 |
iated | +0.111 |
Neg logit contributions | |
blance | -0.158 |
uments | -0.149 |
arthed | -0.146 |
ondon | -0.140 |
nesota | -0.132 |
Token | peaceful |
Token ID | 12309 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token | protests |
Token ID | 8536 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | ? |
Token ID | 30 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
blance | +0.047 |
uments | +0.044 |
arthed | +0.044 |
ondon | +0.041 |
nesota | +0.040 |
Neg logit contributions | |
ogens | -0.034 |
Debor | -0.032 |
BUR | -0.031 |
osit | -0.030 |
supervision | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.006 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
blance | +0.004 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.002 |
BUR | -0.002 |
osit | -0.002 |
supervision | -0.002 |
Token | WASHINGTON |
Token ID | 21793 |
Feature activation | +4.59e-01 |
Pos logit contributions | |
ogens | +0.000 |
Debor | +0.000 |
BUR | +0.000 |
osit | +0.000 |
supervision | +0.000 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.000 |
arthed | -0.000 |
ondon | -0.000 |
nesota | -0.000 |
Token | rea |
Token ID | 21468 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
blance | +0.042 |
uments | +0.040 |
arthed | +0.040 |
ondon | +0.038 |
nesota | +0.036 |
Neg logit contributions | |
ogens | -0.026 |
Debor | -0.023 |
BUR | -0.023 |
osit | -0.022 |
iated | -0.021 |
Token | bought |
Token ID | 5839 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
ogens | +0.025 |
Debor | +0.023 |
BUR | +0.022 |
osit | +0.022 |
supervision | +0.021 |
Neg logit contributions | |
blance | -0.034 |
uments | -0.032 |
arthed | -0.031 |
ondon | -0.030 |
nesota | -0.029 |
Token | cocaine |
Token ID | 15144 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
blance | +0.084 |
uments | +0.078 |
arthed | +0.078 |
ondon | +0.074 |
nesota | +0.070 |
Neg logit contributions | |
ogens | -0.074 |
Debor | -0.070 |
BUR | -0.068 |
osit | -0.066 |
supervision | -0.065 |
Token | from |
Token ID | 422 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
blance | +0.115 |
uments | +0.108 |
arthed | +0.107 |
ondon | +0.102 |
nesota | +0.097 |
Neg logit contributions | |
ogens | -0.091 |
Debor | -0.085 |
BUR | -0.082 |
osit | -0.080 |
supervision | -0.079 |
Token | Gal |
Token ID | 5027 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
ogens | +0.002 |
Debor | +0.002 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | ar |
Token ID | 283 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
ogens | +0.152 |
Debor | +0.143 |
BUR | +0.140 |
osit | +0.137 |
iated | +0.134 |
Neg logit contributions | |
blance | -0.130 |
uments | -0.121 |
arthed | -0.120 |
ondon | -0.112 |
nesota | -0.106 |
Token | za |
Token ID | 4496 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
blance | +0.015 |
uments | +0.014 |
arthed | +0.014 |
ondon | +0.013 |
nesota | +0.013 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
ogens | +0.063 |
Debor | +0.058 |
BUR | +0.056 |
osit | +0.055 |
supervision | +0.054 |
Neg logit contributions | |
blance | -0.085 |
uments | -0.079 |
arthed | -0.079 |
ondon | -0.075 |
nesota | -0.072 |
Token | co |
Token ID | 763 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ogens | +0.017 |
Debor | +0.015 |
BUR | +0.015 |
osit | +0.014 |
supervision | +0.014 |
Neg logit contributions | |
blance | -0.024 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.022 |
nesota | -0.021 |
Token | - |
Token ID | 12 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
ogens | +0.049 |
Debor | +0.046 |
BUR | +0.044 |
osit | +0.043 |
supervision | +0.042 |
Neg logit contributions | |
blance | -0.068 |
uments | -0.065 |
arthed | -0.064 |
ondon | -0.061 |
nesota | -0.058 |
Token | worker |
Token ID | 28816 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
ogens | +0.009 |
Debor | +0.008 |
BUR | +0.008 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.016 |
uments | -0.015 |
arthed | -0.015 |
ondon | -0.014 |
nesota | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
ogens | +0.051 |
Debor | +0.048 |
BUR | +0.047 |
osit | +0.045 |
iated | +0.044 |
Neg logit contributions | |
blance | -0.066 |
uments | -0.062 |
arthed | -0.062 |
ondon | -0.059 |
nesota | -0.056 |
Token | However |
Token ID | 2102 |
Feature activation | -6.98e-04 |
Pos logit contributions | |
ogens | +0.007 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.006 |
supervision | +0.006 |
Neg logit contributions | |
blance | -0.009 |
uments | -0.009 |
arthed | -0.008 |
ondon | -0.008 |
nesota | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | -7.86e-02 |
Pos logit contributions | |
ogens | +0.000 |
Debor | +0.000 |
BUR | +0.000 |
osit | +0.000 |
supervision | +0.000 |
Neg logit contributions | |
blance | -0.000 |
uments | -0.000 |
arthed | -0.000 |
ondon | -0.000 |
nesota | -0.000 |
Token | has |
Token ID | 468 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
ogens | +0.023 |
Debor | +0.022 |
BUR | +0.021 |
osit | +0.021 |
iated | +0.020 |
Neg logit contributions | |
blance | -0.030 |
uments | -0.029 |
arthed | -0.028 |
ondon | -0.027 |
nesota | -0.026 |
Token | no |
Token ID | 645 |
Feature activation | -8.67e-02 |
Pos logit contributions | |
ogens | +0.003 |
Debor | +0.002 |
BUR | +0.002 |
osit | +0.002 |
supervision | +0.002 |
Neg logit contributions | |
blance | -0.003 |
uments | -0.003 |
arthed | -0.003 |
ondon | -0.003 |
nesota | -0.003 |
Token | links |
Token ID | 6117 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
ogens | +0.026 |
Debor | +0.024 |
BUR | +0.023 |
osit | +0.022 |
supervision | +0.022 |
Neg logit contributions | |
blance | -0.033 |
uments | -0.032 |
arthed | -0.031 |
ondon | -0.030 |
nesota | -0.028 |
Token | with |
Token ID | 351 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
ogens | +0.016 |
Debor | +0.015 |
BUR | +0.014 |
osit | +0.014 |
supervision | +0.014 |
Neg logit contributions | |
blance | -0.017 |
uments | -0.016 |
arthed | -0.016 |
ondon | -0.015 |
nesota | -0.014 |
Token | Pakistan |
Token ID | 7648 |
Feature activation | +7.36e-02 |
Pos logit contributions | |
blance | +0.010 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.009 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.007 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
blance | +0.030 |
uments | +0.028 |
arthed | +0.028 |
ondon | +0.026 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.021 |
Debor | -0.019 |
BUR | -0.019 |
osit | -0.018 |
supervision | -0.018 |
Token | worked |
Token ID | 3111 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.011 |
BUR | +0.011 |
osit | +0.010 |
supervision | +0.010 |
Neg logit contributions | |
blance | -0.015 |
uments | -0.015 |
arthed | -0.014 |
ondon | -0.014 |
nesota | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
blance | +0.053 |
uments | +0.050 |
arthed | +0.049 |
ondon | +0.047 |
nesota | +0.045 |
Neg logit contributions | |
ogens | -0.040 |
Debor | -0.038 |
BUR | -0.037 |
osit | -0.036 |
supervision | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
ogens | +0.018 |
Debor | +0.017 |
BUR | +0.016 |
osit | +0.016 |
supervision | +0.016 |
Neg logit contributions | |
blance | -0.025 |
uments | -0.023 |
arthed | -0.023 |
ondon | -0.022 |
nesota | -0.021 |
Token | " |
Token ID | 1 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.011 |
Token | Some |
Token ID | 4366 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
blance | +0.010 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.009 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.007 |
Debor | -0.006 |
BUR | -0.006 |
osit | -0.006 |
supervision | -0.006 |
Token | may |
Token ID | 743 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ogens | +0.019 |
Debor | +0.018 |
BUR | +0.017 |
osit | +0.017 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.027 |
uments | -0.025 |
arthed | -0.025 |
ondon | -0.024 |
nesota | -0.023 |
Token | qu |
Token ID | 627 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
ogens | +0.046 |
Debor | +0.043 |
BUR | +0.042 |
osit | +0.041 |
supervision | +0.040 |
Neg logit contributions | |
blance | -0.056 |
uments | -0.053 |
arthed | -0.053 |
ondon | -0.050 |
nesota | -0.047 |
Token | ibble |
Token ID | 43992 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.003 |
osit | +0.003 |
iated | +0.003 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
ogens | +0.032 |
Debor | +0.030 |
BUR | +0.029 |
osit | +0.028 |
supervision | +0.027 |
Neg logit contributions | |
blance | -0.037 |
uments | -0.035 |
arthed | -0.034 |
ondon | -0.033 |
nesota | -0.031 |
Token | this |
Token ID | 428 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
ogens | +0.020 |
Debor | +0.019 |
BUR | +0.018 |
osit | +0.018 |
supervision | +0.017 |
Neg logit contributions | |
blance | -0.025 |
uments | -0.024 |
arthed | -0.024 |
ondon | -0.023 |
nesota | -0.021 |
Token | doesn |
Token ID | 1595 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
ogens | +0.014 |
Debor | +0.013 |
BUR | +0.012 |
osit | +0.012 |
supervision | +0.012 |
Neg logit contributions | |
blance | -0.019 |
uments | -0.018 |
arthed | -0.017 |
ondon | -0.017 |
nesota | -0.016 |
Token | 't |
Token ID | 470 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
blance | +0.021 |
uments | +0.020 |
arthed | +0.020 |
ondon | +0.019 |
nesota | +0.018 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.013 |
BUR | -0.012 |
osit | -0.012 |
supervision | -0.012 |
Token | take |
Token ID | 1011 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
ogens | +0.030 |
Debor | +0.028 |
BUR | +0.028 |
osit | +0.027 |
supervision | +0.026 |
Neg logit contributions | |
blance | -0.040 |
arthed | -0.038 |
uments | -0.038 |
ondon | -0.036 |
nesota | -0.034 |
Token | lez |
Token ID | 36858 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
blance | +0.002 |
uments | +0.002 |
arthed | +0.002 |
ondon | +0.002 |
nesota | +0.002 |
Neg logit contributions | |
ogens | -0.002 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | al |
Token ID | 282 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ogens | +0.072 |
Debor | +0.067 |
BUR | +0.065 |
osit | +0.064 |
iated | +0.063 |
Neg logit contributions | |
blance | -0.079 |
uments | -0.074 |
arthed | -0.074 |
ondon | -0.069 |
nesota | -0.065 |
Token | slide |
Token ID | 10649 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
blance | +0.050 |
uments | +0.047 |
arthed | +0.046 |
ondon | +0.044 |
nesota | +0.042 |
Neg logit contributions | |
ogens | -0.036 |
Debor | -0.034 |
BUR | -0.033 |
osit | -0.032 |
supervision | -0.031 |
Token | on |
Token ID | 319 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
ogens | +0.011 |
Debor | +0.010 |
BUR | +0.010 |
osit | +0.010 |
supervision | +0.009 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.013 |
arthed | -0.013 |
ondon | -0.012 |
nesota | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.012 |
BUR | +0.011 |
osit | +0.011 |
supervision | +0.011 |
Neg logit contributions | |
blance | -0.015 |
uments | -0.014 |
arthed | -0.014 |
ondon | -0.013 |
nesota | -0.012 |
Token | Cait |
Token ID | 34118 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
ogens | +0.010 |
Debor | +0.009 |
BUR | +0.009 |
osit | +0.008 |
supervision | +0.008 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.013 |
arthed | -0.013 |
ondon | -0.012 |
nesota | -0.012 |
Token | lyn |
Token ID | 6213 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ogens | +0.260 |
Debor | +0.248 |
BUR | +0.243 |
osit | +0.240 |
supervision | +0.236 |
Neg logit contributions | |
blance | -0.120 |
arthed | -0.106 |
uments | -0.106 |
ondon | -0.095 |
nesota | -0.088 |
Token | Jenner |
Token ID | 39760 |
Feature activation | -6.36e-02 |
Pos logit contributions | |
blance | +0.164 |
uments | +0.154 |
arthed | +0.153 |
ondon | +0.145 |
nesota | +0.139 |
Neg logit contributions | |
ogens | -0.130 |
Debor | -0.122 |
BUR | -0.118 |
osit | -0.115 |
supervision | -0.113 |
Token | comparisons |
Token ID | 17909 |
Feature activation | +5.62e-02 |
Pos logit contributions | |
ogens | +0.018 |
Debor | +0.016 |
BUR | +0.016 |
osit | +0.015 |
supervision | +0.015 |
Neg logit contributions | |
blance | -0.026 |
uments | -0.024 |
arthed | -0.024 |
ondon | -0.023 |
nesota | -0.022 |
Token | — |
Token ID | 960 |
Feature activation | +8.76e-03 |
Pos logit contributions | |
blance | +0.021 |
uments | +0.020 |
arthed | +0.020 |
ondon | +0.019 |
nesota | +0.018 |
Neg logit contributions | |
ogens | -0.017 |
Debor | -0.016 |
BUR | -0.015 |
osit | -0.015 |
supervision | -0.015 |
Token | and |
Token ID | 392 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
blance | +0.003 |
uments | +0.003 |
arthed | +0.003 |
ondon | +0.003 |
nesota | +0.003 |
Neg logit contributions | |
ogens | -0.003 |
Debor | -0.003 |
BUR | -0.003 |
osit | -0.003 |
supervision | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ogens | +0.056 |
Debor | +0.052 |
BUR | +0.050 |
osit | +0.049 |
supervision | +0.048 |
Neg logit contributions | |
blance | -0.072 |
uments | -0.068 |
arthed | -0.067 |
ondon | -0.064 |
nesota | -0.061 |
Token | animal |
Token ID | 5044 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.009 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.008 |
nesota | -0.008 |
Token | care |
Token ID | 1337 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
blance | +0.028 |
uments | +0.027 |
arthed | +0.027 |
ondon | +0.026 |
nesota | +0.025 |
Neg logit contributions | |
ogens | -0.014 |
Debor | -0.012 |
BUR | -0.012 |
osit | -0.012 |
supervision | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
ogens | +0.076 |
Debor | +0.070 |
BUR | +0.068 |
osit | +0.066 |
supervision | +0.065 |
Neg logit contributions | |
blance | -0.100 |
uments | -0.094 |
arthed | -0.093 |
ondon | -0.088 |
nesota | -0.084 |
Token | Experimental |
Token ID | 32286 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
ogens | +0.018 |
Debor | +0.017 |
BUR | +0.017 |
osit | +0.016 |
supervision | +0.016 |
Neg logit contributions | |
blance | -0.020 |
uments | -0.019 |
arthed | -0.018 |
ondon | -0.018 |
aiden | -0.017 |
Token | procedures |
Token ID | 9021 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
ogens | +0.049 |
Debor | +0.045 |
BUR | +0.044 |
osit | +0.042 |
supervision | +0.041 |
Neg logit contributions | |
blance | -0.085 |
uments | -0.081 |
arthed | -0.080 |
ondon | -0.077 |
nesota | -0.074 |
Token | were |
Token ID | 547 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ogens | +0.156 |
Debor | +0.146 |
BUR | +0.140 |
osit | +0.138 |
supervision | +0.137 |
Neg logit contributions | |
blance | -0.178 |
uments | -0.166 |
arthed | -0.165 |
ondon | -0.156 |
nesota | -0.148 |
Token | performed |
Token ID | 6157 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
blance | +0.006 |
uments | +0.005 |
arthed | +0.005 |
ondon | +0.005 |
nesota | +0.005 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.004 |
supervision | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
ogens | +0.025 |
Debor | +0.023 |
BUR | +0.022 |
supervision | +0.022 |
osit | +0.022 |
Neg logit contributions | |
blance | -0.028 |
uments | -0.026 |
arthed | -0.026 |
ondon | -0.025 |
nesota | -0.023 |
Token | accordance |
Token ID | 10213 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.007 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.011 |
uments | -0.011 |
arthed | -0.011 |
ondon | -0.010 |
nesota | -0.010 |
Token | with |
Token ID | 351 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
ogens | +0.058 |
Debor | +0.055 |
BUR | +0.053 |
osit | +0.052 |
supervision | +0.052 |
Neg logit contributions | |
blance | -0.057 |
uments | -0.053 |
arthed | -0.052 |
ondon | -0.049 |
nesota | -0.047 |
Token | is |
Token ID | 318 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
blance | +0.162 |
uments | +0.152 |
arthed | +0.151 |
ondon | +0.143 |
nesota | +0.137 |
Neg logit contributions | |
ogens | -0.132 |
Debor | -0.123 |
BUR | -0.120 |
osit | -0.116 |
supervision | -0.114 |
Token | composed |
Token ID | 13160 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.005 |
BUR | +0.005 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.006 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -3.45e-03 |
Pos logit contributions | |
ogens | +0.140 |
Debor | +0.131 |
BUR | +0.128 |
osit | +0.124 |
supervision | +0.121 |
Neg logit contributions | |
blance | -0.172 |
uments | -0.162 |
arthed | -0.159 |
ondon | -0.152 |
nesota | -0.144 |
Token | the |
Token ID | 262 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.001 |
uments | -0.001 |
arthed | -0.001 |
ondon | -0.001 |
nesota | -0.001 |
Token | Un |
Token ID | 791 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
ogens | +0.008 |
Debor | +0.008 |
BUR | +0.007 |
osit | +0.007 |
supervision | +0.007 |
Neg logit contributions | |
blance | -0.010 |
uments | -0.009 |
arthed | -0.009 |
ondon | -0.009 |
nesota | -0.008 |
Token | locked |
Token ID | 24162 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
ogens | +0.029 |
Debor | +0.026 |
BUR | +0.024 |
osit | +0.023 |
supervision | +0.022 |
Neg logit contributions | |
blance | -0.078 |
uments | -0.074 |
arthed | -0.073 |
ondon | -0.071 |
nesota | -0.068 |
Token | BIOS |
Token ID | 27553 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
ogens | +0.172 |
Debor | +0.161 |
BUR | +0.157 |
osit | +0.153 |
supervision | +0.150 |
Neg logit contributions | |
blance | -0.192 |
uments | -0.180 |
arthed | -0.178 |
ondon | -0.169 |
nesota | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
blance | +0.028 |
uments | +0.026 |
arthed | +0.026 |
ondon | +0.025 |
nesota | +0.024 |
Neg logit contributions | |
ogens | -0.022 |
Debor | -0.020 |
BUR | -0.019 |
osit | -0.019 |
supervision | -0.019 |
Token | Digital |
Token ID | 10231 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.004 |
arthed | -0.004 |
ondon | -0.004 |
nesota | -0.004 |
Token | P |
Token ID | 47 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
ogens | +0.015 |
Debor | +0.015 |
BUR | +0.014 |
osit | +0.014 |
supervision | +0.014 |
Neg logit contributions | |
blance | -0.013 |
uments | -0.012 |
arthed | -0.012 |
ondon | -0.011 |
nesota | -0.010 |
Token | WM |
Token ID | 22117 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
blance | +0.066 |
uments | +0.062 |
arthed | +0.062 |
ondon | +0.059 |
nesota | +0.056 |
Neg logit contributions | |
ogens | -0.042 |
Debor | -0.038 |
BUR | -0.038 |
osit | -0.036 |
supervision | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
ogens | +0.028 |
Debor | +0.026 |
BUR | +0.025 |
osit | +0.024 |
supervision | +0.024 |
Neg logit contributions | |
blance | -0.036 |
uments | -0.034 |
arthed | -0.033 |
ondon | -0.032 |
nesota | -0.030 |
Token | drew |
Token ID | 9859 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
blance | +0.010 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.009 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.007 |
Token | just |
Token ID | 655 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
blance | +0.057 |
uments | +0.054 |
arthed | +0.054 |
ondon | +0.051 |
nesota | +0.049 |
Neg logit contributions | |
ogens | -0.041 |
Debor | -0.038 |
BUR | -0.037 |
osit | -0.036 |
supervision | -0.035 |
Token | eight |
Token ID | 3624 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ogens | +0.012 |
Debor | +0.011 |
BUR | +0.011 |
osit | +0.011 |
supervision | +0.010 |
Neg logit contributions | |
blance | -0.014 |
uments | -0.014 |
arthed | -0.013 |
ondon | -0.013 |
nesota | -0.012 |
Token | b |
Token ID | 275 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
blance | +0.074 |
uments | +0.070 |
arthed | +0.069 |
ondon | +0.066 |
nesota | +0.063 |
Neg logit contributions | |
ogens | -0.055 |
Debor | -0.051 |
BUR | -0.049 |
osit | -0.048 |
iated | -0.047 |
Token | idd |
Token ID | 1638 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
blance | +0.069 |
uments | +0.066 |
arthed | +0.066 |
ondon | +0.064 |
nesota | +0.061 |
Neg logit contributions | |
ogens | -0.023 |
Debor | -0.021 |
BUR | -0.020 |
osit | -0.019 |
supervision | -0.018 |
Token | ers |
Token ID | 364 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
ogens | +0.200 |
Debor | +0.184 |
BUR | +0.180 |
osit | +0.179 |
iated | +0.173 |
Neg logit contributions | |
blance | -0.236 |
arthed | -0.220 |
uments | -0.217 |
ondon | -0.205 |
nesota | -0.196 |
Token | when |
Token ID | 618 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
blance | +0.028 |
uments | +0.026 |
arthed | +0.026 |
ondon | +0.025 |
nesota | +0.023 |
Neg logit contributions | |
ogens | -0.021 |
Debor | -0.020 |
BUR | -0.019 |
osit | -0.019 |
supervision | -0.018 |
Token | auction |
Token ID | 14389 |
Feature activation | -5.36e-03 |
Pos logit contributions | |
blance | +0.042 |
uments | +0.040 |
arthed | +0.039 |
ondon | +0.037 |
nesota | +0.035 |
Neg logit contributions | |
ogens | -0.032 |
Debor | -0.030 |
BUR | -0.029 |
osit | -0.028 |
supervision | -0.028 |
Token | ed |
Token ID | 276 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ogens | +0.001 |
Debor | +0.001 |
BUR | +0.001 |
osit | +0.001 |
supervision | +0.001 |
Neg logit contributions | |
blance | -0.002 |
uments | -0.002 |
arthed | -0.002 |
ondon | -0.002 |
nesota | -0.002 |
Token | by |
Token ID | 416 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
ogens | +0.086 |
Debor | +0.081 |
BUR | +0.078 |
osit | +0.075 |
supervision | +0.075 |
Neg logit contributions | |
blance | -0.114 |
uments | -0.107 |
arthed | -0.106 |
ondon | -0.101 |
nesota | -0.096 |
Token | ced |
Token ID | 771 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
blance | +0.054 |
uments | +0.050 |
arthed | +0.049 |
ondon | +0.047 |
nesota | +0.044 |
Neg logit contributions | |
ogens | -0.055 |
Debor | -0.052 |
BUR | -0.051 |
osit | -0.049 |
supervision | -0.049 |
Token | : |
Token ID | 25 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
blance | +0.009 |
uments | +0.009 |
arthed | +0.009 |
ondon | +0.008 |
nesota | +0.008 |
Neg logit contributions | |
ogens | -0.008 |
Debor | -0.007 |
BUR | -0.007 |
osit | -0.007 |
supervision | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
blance | +0.005 |
uments | +0.005 |
arthed | +0.004 |
ondon | +0.004 |
nesota | +0.004 |
Neg logit contributions | |
ogens | -0.004 |
Debor | -0.004 |
BUR | -0.004 |
osit | -0.003 |
supervision | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.93e-03 |
Pos logit contributions | |
ogens | +0.004 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.003 |
supervision | +0.003 |
Neg logit contributions | |
blance | -0.005 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.004 |
Token | S |
Token ID | 50 |
Feature activation | -5.82e-02 |
Pos logit contributions | |
blance | +0.001 |
uments | +0.001 |
arthed | +0.001 |
ondon | +0.001 |
nesota | +0.001 |
Neg logit contributions | |
ogens | -0.001 |
Debor | -0.001 |
BUR | -0.001 |
osit | -0.001 |
supervision | -0.001 |
Token | chie |
Token ID | 3043 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ogens | +0.018 |
Debor | +0.017 |
BUR | +0.017 |
osit | +0.016 |
supervision | +0.016 |
Neg logit contributions | |
blance | -0.021 |
uments | -0.020 |
arthed | -0.020 |
ondon | -0.019 |
nesota | -0.018 |
Token | ff |
Token ID | 487 |
Feature activation | +6.11e-02 |
Pos logit contributions | |
ogens | +0.232 |
Debor | +0.216 |
BUR | +0.211 |
osit | +0.207 |
supervision | +0.201 |
Neg logit contributions | |
blance | -0.230 |
uments | -0.215 |
arthed | -0.213 |
ondon | -0.200 |
nesota | -0.191 |
Token | elin |
Token ID | 27176 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
blance | +0.023 |
uments | +0.021 |
arthed | +0.021 |
ondon | +0.020 |
nesota | +0.019 |
Neg logit contributions | |
ogens | -0.019 |
Debor | -0.018 |
BUR | -0.017 |
osit | -0.017 |
supervision | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
ogens | +0.185 |
Debor | +0.171 |
BUR | +0.168 |
osit | +0.163 |
supervision | +0.159 |
Neg logit contributions | |
blance | -0.234 |
uments | -0.220 |
arthed | -0.218 |
ondon | -0.207 |
nesota | -0.197 |
Token | B |
Token ID | 347 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
ogens | +0.005 |
Debor | +0.004 |
BUR | +0.004 |
osit | +0.004 |
supervision | +0.004 |
Neg logit contributions | |
blance | -0.006 |
uments | -0.005 |
arthed | -0.005 |
ondon | -0.005 |
nesota | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
blance | +0.056 |
uments | +0.053 |
arthed | +0.052 |
ondon | +0.049 |
nesota | +0.047 |
Neg logit contributions | |
ogens | -0.046 |
Debor | -0.043 |
BUR | -0.042 |
osit | -0.041 |
supervision | -0.040 |