Token | box |
Token ID | 3091 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ear | +0.005 |
Rex | +0.005 |
goodbye | +0.005 |
Leo | +0.004 |
icks | +0.004 |
Neg logit contributions | |
ge | -0.007 |
igsaw | -0.006 |
chie | -0.006 |
hr | -0.006 |
ilda | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.46e-03 |
Pos logit contributions | |
ge | +0.040 |
igsaw | +0.039 |
chie | +0.038 |
ilda | +0.035 |
ini | +0.034 |
Neg logit contributions | |
Leo | -0.016 |
Rex | -0.015 |
Kai | -0.015 |
goodbye | -0.015 |
aw | -0.015 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
Leo | +0.002 |
Rex | +0.002 |
Kai | +0.002 |
named | +0.002 |
icks | +0.002 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.003 |
chie | -0.003 |
ilda | -0.003 |
ini | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
Kai | +0.021 |
icks | +0.020 |
Leo | +0.020 |
bye | +0.020 |
Rex | +0.020 |
Neg logit contributions | |
ge | -0.027 |
igsaw | -0.025 |
ilda | -0.023 |
chie | -0.023 |
pack | -0.022 |
Token | j |
Token ID | 474 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
Rex | +0.007 |
Leo | +0.007 |
Kai | +0.007 |
named | +0.006 |
icks | +0.006 |
Neg logit contributions | |
ge | -0.007 |
igsaw | -0.007 |
chie | -0.006 |
ilda | -0.006 |
pack | -0.006 |
Token | igsaw |
Token ID | 45636 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
ge | +0.049 |
chie | +0.042 |
ilda | +0.040 |
igsaw | +0.039 |
hr | +0.039 |
Neg logit contributions | |
aw | -0.045 |
icks | -0.045 |
Leo | -0.044 |
Rex | -0.044 |
bye | -0.044 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
chie | +0.296 |
ge | +0.295 |
hr | +0.268 |
beh | +0.264 |
arre | +0.250 |
Neg logit contributions | |
marsh | -0.191 |
thank | -0.191 |
named | -0.181 |
Leo | -0.177 |
goodbye | -0.174 |
Token | inside |
Token ID | 2641 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
ge | +0.051 |
igsaw | +0.048 |
chie | +0.048 |
ilda | +0.046 |
ini | +0.044 |
Neg logit contributions | |
Leo | -0.031 |
aw | -0.030 |
Rex | -0.030 |
named | -0.030 |
icks | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
ge | +0.089 |
igsaw | +0.088 |
chie | +0.085 |
ilda | +0.080 |
ini | +0.075 |
Neg logit contributions | |
Leo | -0.049 |
Rex | -0.049 |
aw | -0.047 |
named | -0.047 |
Kai | -0.045 |
Token | He |
Token ID | 679 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
ge | +0.009 |
igsaw | +0.009 |
chie | +0.008 |
ilda | +0.008 |
pack | +0.008 |
Neg logit contributions | |
Kai | -0.006 |
Leo | -0.006 |
icks | -0.006 |
Rex | -0.006 |
aw | -0.006 |
Token | paused |
Token ID | 24487 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Leo | +0.025 |
Rex | +0.025 |
Kai | +0.025 |
named | +0.024 |
aw | +0.024 |
Neg logit contributions | |
ge | -0.036 |
igsaw | -0.035 |
chie | -0.032 |
ilda | -0.031 |
pack | -0.029 |
Token | It |
Token ID | 632 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
ge | +0.009 |
igsaw | +0.009 |
chie | +0.008 |
ilda | +0.008 |
pack | +0.008 |
Neg logit contributions | |
Kai | -0.006 |
Rex | -0.006 |
Leo | -0.006 |
icks | -0.006 |
aw | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.004 |
chie | +0.004 |
ilda | +0.004 |
pack | +0.003 |
Neg logit contributions | |
Leo | -0.004 |
Kai | -0.004 |
Rex | -0.004 |
icks | -0.004 |
aw | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
Kai | +0.004 |
icks | +0.004 |
Leo | +0.004 |
aw | +0.004 |
Rex | +0.004 |
Neg logit contributions | |
ge | -0.005 |
igsaw | -0.004 |
ilda | -0.004 |
chie | -0.004 |
pack | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ge | +0.012 |
igsaw | +0.012 |
chie | +0.011 |
ilda | +0.010 |
pack | +0.010 |
Neg logit contributions | |
Kai | -0.011 |
Leo | -0.011 |
Rex | -0.011 |
icks | -0.011 |
aw | -0.011 |
Token | j |
Token ID | 474 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
Kai | +0.018 |
icks | +0.018 |
Leo | +0.018 |
Rex | +0.017 |
aw | +0.017 |
Neg logit contributions | |
igsaw | -0.021 |
ge | -0.021 |
chie | -0.019 |
ilda | -0.018 |
pack | -0.017 |
Token | igsaw |
Token ID | 45636 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ge | +0.058 |
chie | +0.049 |
ilda | +0.046 |
igsaw | +0.045 |
pack | +0.045 |
Neg logit contributions | |
aw | -0.052 |
named | -0.051 |
bye | -0.050 |
Rex | -0.050 |
Leo | -0.050 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ge | +0.272 |
chie | +0.248 |
hr | +0.223 |
ptions | +0.212 |
ilda | +0.211 |
Neg logit contributions | |
named | -0.228 |
marsh | -0.224 |
thank | -0.216 |
goodbye | -0.212 |
Leo | -0.211 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ge | +0.048 |
igsaw | +0.044 |
chie | +0.043 |
ilda | +0.041 |
pack | +0.039 |
Neg logit contributions | |
Leo | -0.032 |
Rex | -0.032 |
Kai | -0.031 |
named | -0.031 |
aw | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ge | +0.021 |
igsaw | +0.020 |
chie | +0.019 |
ilda | +0.018 |
pack | +0.017 |
Neg logit contributions | |
Kai | -0.017 |
Leo | -0.016 |
Rex | -0.016 |
icks | -0.016 |
aw | -0.016 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ge | +0.047 |
igsaw | +0.045 |
chie | +0.042 |
ilda | +0.041 |
pack | +0.039 |
Neg logit contributions | |
Leo | -0.030 |
Kai | -0.030 |
Rex | -0.030 |
icks | -0.029 |
aw | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ge | +0.028 |
igsaw | +0.027 |
chie | +0.025 |
ini | +0.023 |
ilda | +0.023 |
Neg logit contributions | |
Rex | -0.025 |
Leo | -0.024 |
Kai | -0.024 |
named | -0.023 |
goodbye | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
Kai | +0.027 |
Leo | +0.027 |
Rex | +0.027 |
icks | +0.026 |
aw | +0.026 |
Neg logit contributions | |
ge | -0.046 |
igsaw | -0.044 |
chie | -0.041 |
ilda | -0.040 |
pack | -0.038 |
Token | mess |
Token ID | 2085 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.009 |
chie | +0.009 |
ilda | +0.008 |
spe | +0.008 |
Neg logit contributions | |
marsh | -0.014 |
sorry | -0.013 |
Leo | -0.013 |
Rex | -0.013 |
ear | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ge | +0.109 |
igsaw | +0.106 |
chie | +0.103 |
ilda | +0.097 |
spe | +0.093 |
Neg logit contributions | |
Rex | -0.046 |
icks | -0.046 |
Leo | -0.045 |
aw | -0.043 |
named | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +5.74e-03 |
Pos logit contributions | |
ge | +0.032 |
igsaw | +0.031 |
chie | +0.029 |
ilda | +0.028 |
ini | +0.027 |
Neg logit contributions | |
Rex | -0.016 |
Leo | -0.016 |
Kai | -0.015 |
icks | -0.015 |
named | -0.014 |
Token | qu |
Token ID | 627 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
ge | +0.009 |
igsaw | +0.008 |
chie | +0.008 |
ilda | +0.008 |
pack | +0.007 |
Neg logit contributions | |
marsh | -0.011 |
Rex | -0.011 |
Leo | -0.011 |
ear | -0.011 |
sorry | -0.011 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ge | +0.087 |
ilda | +0.073 |
igsaw | +0.073 |
Emmy | +0.072 |
spe | +0.070 |
Neg logit contributions | |
icks | -0.076 |
aw | -0.074 |
marsh | -0.062 |
icked | -0.060 |
hes | -0.059 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
igsaw | +0.337 |
enny | +0.294 |
ilda | +0.291 |
ge | +0.291 |
chie | +0.278 |
Neg logit contributions | |
icks | -0.133 |
aw | -0.133 |
marsh | -0.130 |
sorry | -0.118 |
hes | -0.114 |
Token | twins |
Token ID | 20345 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
ge | +0.024 |
igsaw | +0.022 |
ilda | +0.021 |
chie | +0.020 |
pack | +0.019 |
Neg logit contributions | |
Rex | -0.017 |
Leo | -0.016 |
icks | -0.016 |
named | -0.016 |
marsh | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
ge | +0.085 |
igsaw | +0.082 |
chie | +0.077 |
ilda | +0.074 |
ini | +0.070 |
Neg logit contributions | |
Leo | -0.057 |
Rex | -0.057 |
icks | -0.057 |
Kai | -0.056 |
aw | -0.054 |
Token | She |
Token ID | 1375 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ge | +0.021 |
igsaw | +0.020 |
chie | +0.018 |
ilda | +0.018 |
pack | +0.017 |
Neg logit contributions | |
Leo | -0.014 |
Kai | -0.014 |
Rex | -0.014 |
icks | -0.014 |
aw | -0.013 |
Token | is |
Token ID | 318 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
Rex | +0.015 |
Leo | +0.014 |
Kai | +0.014 |
icks | +0.014 |
named | +0.013 |
Neg logit contributions | |
ge | -0.028 |
igsaw | -0.027 |
chie | -0.025 |
ilda | -0.025 |
ini | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
icks | +0.018 |
Kai | +0.017 |
Rex | +0.017 |
Leo | +0.017 |
ses | +0.016 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.022 |
chie | -0.021 |
ilda | -0.020 |
pack | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ge | +0.024 |
igsaw | +0.021 |
chie | +0.020 |
ilda | +0.020 |
pack | +0.019 |
Neg logit contributions | |
icks | -0.019 |
Kai | -0.018 |
Rex | -0.018 |
Leo | -0.018 |
ses | -0.018 |
Token | two |
Token ID | 734 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
icks | +0.026 |
ses | +0.024 |
bye | +0.024 |
sed | +0.024 |
Kai | +0.023 |
Neg logit contributions | |
ge | -0.025 |
igsaw | -0.024 |
chie | -0.023 |
ilda | -0.022 |
spe | -0.021 |
Token | birds |
Token ID | 10087 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ge | +0.067 |
igsaw | +0.063 |
chie | +0.059 |
ilda | +0.058 |
pack | +0.056 |
Neg logit contributions | |
Leo | -0.043 |
Kai | -0.043 |
Rex | -0.042 |
icks | -0.041 |
aw | -0.041 |
Token | qu |
Token ID | 627 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Kai | +0.027 |
Leo | +0.027 |
Rex | +0.027 |
icks | +0.026 |
aw | +0.025 |
Neg logit contributions | |
ge | -0.037 |
igsaw | -0.033 |
chie | -0.032 |
ilda | -0.031 |
pack | -0.029 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ge | +0.077 |
igsaw | +0.070 |
ilda | +0.069 |
recipe | +0.060 |
spe | +0.059 |
Neg logit contributions | |
aw | -0.090 |
icks | -0.080 |
named | -0.072 |
icked | -0.071 |
Leo | -0.069 |
Token | ling |
Token ID | 1359 |
Feature activation | +8.91e-03 |
Pos logit contributions | |
igsaw | +0.304 |
enny | +0.260 |
ilda | +0.246 |
ge | +0.243 |
chie | +0.241 |
Neg logit contributions | |
aw | -0.170 |
slit | -0.151 |
icks | -0.146 |
horns | -0.144 |
marsh | -0.143 |
Token | ! |
Token ID | 0 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
ge | +0.017 |
igsaw | +0.015 |
chie | +0.015 |
ilda | +0.013 |
spe | +0.013 |
Neg logit contributions | |
Kai | -0.015 |
Rex | -0.014 |
Leo | -0.014 |
icks | -0.014 |
ses | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ge | +0.019 |
igsaw | +0.018 |
chie | +0.017 |
ilda | +0.017 |
pack | +0.016 |
Neg logit contributions | |
Kai | -0.010 |
icks | -0.010 |
Leo | -0.010 |
Rex | -0.010 |
aw | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
ge | +0.035 |
chie | +0.031 |
igsaw | +0.031 |
ilda | +0.029 |
spe | +0.028 |
Neg logit contributions | |
icks | -0.029 |
Rex | -0.029 |
Kai | -0.029 |
Leo | -0.029 |
ses | -0.028 |
Token | squ |
Token ID | 2809 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.009 |
chie | +0.009 |
ilda | +0.008 |
pack | +0.007 |
Neg logit contributions | |
Kai | -0.010 |
Rex | -0.010 |
Leo | -0.010 |
icks | -0.010 |
aw | -0.010 |
Token | lively |
Token ID | 29696 |
Feature activation | +2.41e-04 |
Pos logit contributions | |
ge | +0.008 |
igsaw | +0.008 |
chie | +0.007 |
ilda | +0.007 |
spe | +0.006 |
Neg logit contributions | |
icks | -0.009 |
Kai | -0.008 |
Leo | -0.008 |
aw | -0.008 |
Rex | -0.008 |
Token | sound |
Token ID | 2128 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
ge | +0.000 |
igsaw | +0.000 |
chie | +0.000 |
ilda | +0.000 |
pack | +0.000 |
Neg logit contributions | |
Leo | -0.000 |
Kai | -0.000 |
Rex | -0.000 |
icks | -0.000 |
aw | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Kai | +0.037 |
Leo | +0.037 |
Rex | +0.036 |
icks | +0.036 |
ses | +0.035 |
Neg logit contributions | |
ge | -0.043 |
igsaw | -0.039 |
chie | -0.037 |
ilda | -0.036 |
pack | -0.033 |
Token | The |
Token ID | 383 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
Kai | +0.013 |
icks | +0.013 |
aw | +0.013 |
Leo | +0.013 |
bye | +0.013 |
Neg logit contributions | |
igsaw | -0.021 |
ge | -0.021 |
chie | -0.019 |
ilda | -0.018 |
pack | -0.017 |
Token | qu |
Token ID | 627 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
Leo | +0.039 |
Kai | +0.039 |
Rex | +0.038 |
icks | +0.038 |
aw | +0.037 |
Neg logit contributions | |
ge | -0.039 |
igsaw | -0.036 |
chie | -0.034 |
ilda | -0.032 |
pack | -0.030 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ge | +0.080 |
igsaw | +0.068 |
ilda | +0.066 |
chie | +0.061 |
pack | +0.060 |
Neg logit contributions | |
aw | -0.062 |
icks | -0.055 |
Rex | -0.052 |
named | -0.052 |
marsh | -0.051 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
igsaw | +0.279 |
ge | +0.259 |
ilda | +0.233 |
pack | +0.222 |
chie | +0.221 |
Neg logit contributions | |
aw | -0.168 |
named | -0.152 |
marsh | -0.150 |
icks | -0.150 |
slit | -0.148 |
Token | stopped |
Token ID | 5025 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
ge | +0.019 |
igsaw | +0.018 |
chie | +0.017 |
ilda | +0.016 |
spe | +0.015 |
Neg logit contributions | |
Kai | -0.017 |
Leo | -0.017 |
Rex | -0.017 |
icks | -0.017 |
aw | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +8.62e-03 |
Pos logit contributions | |
ge | +0.019 |
igsaw | +0.018 |
chie | +0.016 |
ilda | +0.016 |
pack | +0.015 |
Neg logit contributions | |
Leo | -0.014 |
Rex | -0.014 |
Kai | -0.014 |
named | -0.014 |
icks | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
ge | +0.017 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.015 |
spe | +0.014 |
Neg logit contributions | |
icks | -0.013 |
Kai | -0.013 |
aw | -0.012 |
Leo | -0.012 |
Rex | -0.012 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ge | +0.051 |
chie | +0.045 |
spe | +0.044 |
ilda | +0.044 |
igsaw | +0.042 |
Neg logit contributions | |
Kai | -0.048 |
icks | -0.047 |
ses | -0.047 |
Leo | -0.047 |
Rex | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ge | +0.073 |
igsaw | +0.070 |
chie | +0.067 |
ilda | +0.063 |
ini | +0.060 |
Neg logit contributions | |
Kai | -0.059 |
Rex | -0.057 |
Leo | -0.057 |
icks | -0.056 |
ses | -0.055 |
Token | other |
Token ID | 584 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
ge | +0.037 |
igsaw | +0.037 |
chie | +0.033 |
ilda | +0.031 |
pack | +0.030 |
Neg logit contributions | |
Kai | -0.025 |
Rex | -0.025 |
Leo | -0.025 |
ear | -0.025 |
aw | -0.024 |
Token | kn |
Token ID | 638 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
ge | +0.055 |
igsaw | +0.054 |
chie | +0.047 |
ilda | +0.044 |
spe | +0.043 |
Neg logit contributions | |
aw | -0.040 |
Kai | -0.039 |
Rex | -0.038 |
ear | -0.037 |
named | -0.037 |
Token | obs |
Token ID | 8158 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
ge | +0.067 |
igsaw | +0.063 |
ilda | +0.055 |
chie | +0.055 |
pack | +0.053 |
Neg logit contributions | |
aw | -0.054 |
Kai | -0.052 |
icks | -0.051 |
Rex | -0.049 |
ear | -0.048 |
Token | qu |
Token ID | 627 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
ge | +0.012 |
igsaw | +0.011 |
chie | +0.010 |
ilda | +0.010 |
pack | +0.010 |
Neg logit contributions | |
Kai | -0.007 |
Leo | -0.007 |
Rex | -0.007 |
icks | -0.007 |
aw | -0.007 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ge | +0.084 |
igsaw | +0.073 |
ilda | +0.071 |
recipe | +0.066 |
Smith | +0.066 |
Neg logit contributions | |
aw | -0.078 |
icks | -0.062 |
named | -0.055 |
icked | -0.054 |
agged | -0.053 |
Token | led |
Token ID | 992 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
igsaw | +0.326 |
ge | +0.286 |
ilda | +0.278 |
enny | +0.276 |
ress | +0.274 |
Neg logit contributions | |
aw | -0.123 |
marsh | -0.096 |
icks | -0.096 |
lived | -0.093 |
horns | -0.091 |
Token | over |
Token ID | 625 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
ge | +0.032 |
igsaw | +0.028 |
chie | +0.027 |
ilda | +0.025 |
spe | +0.025 |
Neg logit contributions | |
Kai | -0.030 |
icks | -0.029 |
Leo | -0.029 |
ses | -0.029 |
Rex | -0.028 |
Token | who |
Token ID | 508 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
Kai | +0.005 |
Leo | +0.005 |
Rex | +0.005 |
icks | +0.005 |
aw | +0.005 |
Neg logit contributions | |
ge | -0.007 |
igsaw | -0.007 |
chie | -0.006 |
ilda | -0.006 |
pack | -0.006 |
Token | should |
Token ID | 815 |
Feature activation | -3.27e-04 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.009 |
chie | +0.009 |
ilda | +0.008 |
pack | +0.008 |
Neg logit contributions | |
Kai | -0.007 |
Leo | -0.007 |
icks | -0.006 |
Rex | -0.006 |
bye | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
Leo | +0.001 |
Kai | +0.001 |
Rex | +0.001 |
icks | +0.001 |
aw | +0.001 |
Neg logit contributions | |
ge | -0.001 |
igsaw | -0.001 |
chie | -0.001 |
ilda | -0.001 |
pack | -0.000 |
Token | but |
Token ID | 475 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ge | +0.059 |
igsaw | +0.055 |
chie | +0.051 |
ilda | +0.051 |
spe | +0.047 |
Neg logit contributions | |
icks | -0.049 |
Kai | -0.049 |
Leo | -0.048 |
Rex | -0.048 |
aw | -0.047 |
Token | today |
Token ID | 1909 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ge | +0.032 |
igsaw | +0.030 |
chie | +0.029 |
ilda | +0.028 |
pack | +0.027 |
Neg logit contributions | |
Leo | -0.019 |
Kai | -0.019 |
Rex | -0.019 |
icks | -0.018 |
aw | -0.018 |
Token | they |
Token ID | 484 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
ge | +0.049 |
igsaw | +0.046 |
chie | +0.045 |
ilda | +0.042 |
pack | +0.041 |
Neg logit contributions | |
Rex | -0.022 |
Leo | -0.022 |
named | -0.021 |
aw | -0.021 |
Kai | -0.021 |
Token | were |
Token ID | 547 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ge | +0.077 |
igsaw | +0.072 |
chie | +0.068 |
ilda | +0.066 |
pack | +0.062 |
Neg logit contributions | |
Leo | -0.053 |
Kai | -0.053 |
Rex | -0.053 |
icks | -0.051 |
aw | -0.050 |
Token | qu |
Token ID | 627 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ge | +0.039 |
igsaw | +0.037 |
chie | +0.034 |
ilda | +0.033 |
pack | +0.031 |
Neg logit contributions | |
Leo | -0.030 |
Rex | -0.030 |
Kai | -0.029 |
named | -0.029 |
icks | -0.029 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ge | +0.061 |
igsaw | +0.048 |
ilda | +0.048 |
recipe | +0.045 |
fitting | +0.041 |
Neg logit contributions | |
aw | -0.096 |
aver | -0.079 |
icks | -0.078 |
named | -0.078 |
agged | -0.075 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
igsaw | +0.301 |
ge | +0.254 |
enny | +0.250 |
ress | +0.246 |
ilda | +0.245 |
Neg logit contributions | |
aw | -0.145 |
named | -0.110 |
marsh | -0.108 |
slit | -0.108 |
then | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
Kai | +0.002 |
Leo | +0.002 |
Rex | +0.002 |
icks | +0.002 |
ses | +0.002 |
Neg logit contributions | |
ge | -0.002 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
spe | -0.002 |
Token | Jenna |
Token ID | 45377 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
ge | +0.023 |
igsaw | +0.020 |
chie | +0.020 |
ilda | +0.019 |
pack | +0.018 |
Neg logit contributions | |
Leo | -0.012 |
Rex | -0.012 |
Kai | -0.011 |
named | -0.011 |
aw | -0.011 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ge | +0.121 |
igsaw | +0.115 |
chie | +0.108 |
ilda | +0.103 |
pack | +0.099 |
Neg logit contributions | |
Leo | -0.085 |
Kai | -0.084 |
Rex | -0.084 |
named | -0.082 |
aw | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.014 |
pack | +0.014 |
Neg logit contributions | |
Leo | -0.019 |
Rex | -0.019 |
Kai | -0.019 |
icks | -0.019 |
aw | -0.018 |
Token | would |
Token ID | 561 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
ge | +0.022 |
igsaw | +0.021 |
chie | +0.020 |
ilda | +0.019 |
pack | +0.019 |
Neg logit contributions | |
Kai | -0.015 |
Leo | -0.015 |
Rex | -0.015 |
icks | -0.015 |
aw | -0.015 |
Token | take |
Token ID | 1011 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Leo | +0.067 |
icks | +0.065 |
named | +0.065 |
ear | +0.065 |
Kai | +0.065 |
Neg logit contributions | |
ge | -0.073 |
igsaw | -0.069 |
chie | -0.064 |
ilda | -0.062 |
ini | -0.059 |
Token | out |
Token ID | 503 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
Leo | +0.015 |
Rex | +0.015 |
Kai | +0.015 |
icks | +0.014 |
aw | +0.014 |
Neg logit contributions | |
ge | -0.026 |
igsaw | -0.024 |
chie | -0.023 |
ilda | -0.022 |
pack | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -3.69e-03 |
Pos logit contributions | |
Leo | +0.039 |
Rex | +0.038 |
icks | +0.036 |
named | +0.036 |
goodbye | +0.035 |
Neg logit contributions | |
ge | -0.091 |
igsaw | -0.084 |
chie | -0.083 |
ilda | -0.083 |
ini | -0.080 |
Token | j |
Token ID | 474 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
thank | +0.005 |
Leo | +0.005 |
goodbye | +0.005 |
marsh | +0.005 |
named | +0.005 |
Neg logit contributions | |
ge | -0.008 |
chie | -0.007 |
ic | -0.007 |
ini | -0.007 |
any | -0.007 |
Token | igsaw |
Token ID | 45636 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ge | +0.021 |
chie | +0.018 |
ilda | +0.017 |
spe | +0.017 |
hr | +0.017 |
Neg logit contributions | |
aw | -0.018 |
icks | -0.018 |
bye | -0.018 |
named | -0.018 |
Rex | -0.018 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
ge | +0.235 |
chie | +0.223 |
hr | +0.201 |
shadow | +0.188 |
any | +0.181 |
Neg logit contributions | |
marsh | -0.190 |
Leo | -0.188 |
thank | -0.188 |
named | -0.187 |
goodbye | -0.182 |
Token | and |
Token ID | 290 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.009 |
chie | +0.009 |
ilda | +0.009 |
ini | +0.008 |
Neg logit contributions | |
Leo | -0.007 |
Rex | -0.007 |
named | -0.006 |
Kai | -0.006 |
icks | -0.006 |
Token | try |
Token ID | 1949 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.004 |
chie | +0.004 |
ilda | +0.003 |
ic | +0.003 |
Neg logit contributions | |
Leo | -0.004 |
Rex | -0.004 |
Kai | -0.004 |
named | -0.003 |
ear | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Leo | +0.018 |
Rex | +0.017 |
icks | +0.016 |
Kai | +0.016 |
aw | +0.016 |
Neg logit contributions | |
igsaw | -0.029 |
chie | -0.029 |
ge | -0.028 |
ini | -0.026 |
spe | -0.025 |
Token | solve |
Token ID | 8494 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
igsaw | +0.029 |
ge | +0.027 |
ilda | +0.027 |
ini | +0.027 |
any | +0.026 |
Neg logit contributions | |
thank | -0.025 |
Leo | -0.023 |
ear | -0.023 |
named | -0.021 |
then | -0.021 |
Token | walking |
Token ID | 6155 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
Rex | +0.013 |
Leo | +0.012 |
named | +0.012 |
Kai | +0.012 |
icks | +0.011 |
Neg logit contributions | |
ge | -0.017 |
igsaw | -0.016 |
chie | -0.015 |
ilda | -0.014 |
ini | -0.014 |
Token | by |
Token ID | 416 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
ge | +0.036 |
igsaw | +0.034 |
chie | +0.031 |
ilda | +0.031 |
pack | +0.029 |
Neg logit contributions | |
Rex | -0.030 |
Leo | -0.030 |
Kai | -0.030 |
aw | -0.028 |
icks | -0.028 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.73e-03 |
Pos logit contributions | |
Kai | +0.008 |
Leo | +0.008 |
icks | +0.008 |
Rex | +0.008 |
aw | +0.008 |
Neg logit contributions | |
ge | -0.012 |
igsaw | -0.011 |
chie | -0.011 |
ilda | -0.010 |
pack | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
Kai | +0.010 |
ses | +0.010 |
icks | +0.010 |
sed | +0.010 |
ear | +0.010 |
Neg logit contributions | |
ge | -0.013 |
igsaw | -0.012 |
ilda | -0.011 |
chie | -0.011 |
pack | -0.011 |
Token | qu |
Token ID | 627 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
ge | +0.016 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.014 |
ini | +0.014 |
Neg logit contributions | |
Rex | -0.009 |
Leo | -0.008 |
Kai | -0.008 |
named | -0.008 |
icks | -0.008 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ge | +0.058 |
ilda | +0.049 |
igsaw | +0.048 |
spe | +0.041 |
chie | +0.040 |
Neg logit contributions | |
aw | -0.094 |
icks | -0.085 |
agged | -0.077 |
icked | -0.076 |
named | -0.075 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.73e-03 |
Pos logit contributions | |
igsaw | +0.314 |
enny | +0.266 |
ilda | +0.262 |
ge | +0.260 |
chie | +0.259 |
Neg logit contributions | |
aw | -0.127 |
icks | -0.112 |
Leo | -0.101 |
horns | -0.099 |
ped | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Kai | +0.003 |
Leo | +0.003 |
icks | +0.003 |
Rex | +0.003 |
ses | +0.003 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.003 |
chie | -0.003 |
ilda | -0.003 |
pack | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
igsaw | +0.017 |
ge | +0.017 |
ilda | +0.016 |
chie | +0.015 |
re | +0.014 |
Neg logit contributions | |
marsh | -0.020 |
icks | -0.020 |
Kai | -0.019 |
slit | -0.019 |
Leo | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
icks | +0.013 |
Leo | +0.013 |
Kai | +0.012 |
Rex | +0.012 |
aw | +0.012 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.014 |
chie | -0.014 |
ilda | -0.014 |
pack | -0.013 |
Token | very |
Token ID | 845 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
Leo | +0.033 |
Kai | +0.032 |
Rex | +0.032 |
icks | +0.032 |
aw | +0.031 |
Neg logit contributions | |
ge | -0.043 |
igsaw | -0.040 |
chie | -0.038 |
ilda | -0.037 |
pack | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +9.48e-05 |
Pos logit contributions | |
Leo | +0.002 |
Kai | +0.002 |
Rex | +0.002 |
icks | +0.002 |
aw | +0.001 |
Neg logit contributions | |
ge | -0.002 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
pack | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ge | +0.000 |
igsaw | +0.000 |
chie | +0.000 |
ilda | +0.000 |
spe | +0.000 |
Neg logit contributions | |
icks | -0.000 |
Kai | -0.000 |
Leo | -0.000 |
Rex | -0.000 |
aw | -0.000 |
Token | bears |
Token ID | 13062 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
icks | +0.023 |
Kai | +0.023 |
Leo | +0.023 |
Rex | +0.022 |
aw | +0.021 |
Neg logit contributions | |
ge | -0.053 |
igsaw | -0.050 |
chie | -0.049 |
ilda | -0.046 |
pack | -0.044 |
Token | stopped |
Token ID | 5025 |
Feature activation | +8.35e-03 |
Pos logit contributions | |
Kai | +0.020 |
Rex | +0.020 |
Leo | +0.019 |
icks | +0.019 |
Rover | +0.018 |
Neg logit contributions | |
ge | -0.022 |
chie | -0.019 |
igsaw | -0.018 |
spe | -0.018 |
ilda | -0.017 |
Token | qu |
Token ID | 627 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
ge | +0.016 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.014 |
pack | +0.013 |
Neg logit contributions | |
Leo | -0.013 |
Rex | -0.013 |
Kai | -0.013 |
icks | -0.013 |
named | -0.012 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
ge | +0.053 |
ilda | +0.044 |
igsaw | +0.044 |
chie | +0.040 |
spe | +0.039 |
Neg logit contributions | |
aw | -0.067 |
icks | -0.059 |
icked | -0.053 |
named | -0.053 |
Rex | -0.051 |
Token | ling |
Token ID | 1359 |
Feature activation | +7.18e-04 |
Pos logit contributions | |
igsaw | +0.300 |
enny | +0.260 |
chie | +0.252 |
ge | +0.250 |
ott | +0.249 |
Neg logit contributions | |
aw | -0.136 |
then | -0.108 |
slit | -0.106 |
Leo | -0.104 |
marsh | -0.104 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ge | +0.001 |
igsaw | +0.001 |
chie | +0.001 |
ilda | +0.001 |
pack | +0.001 |
Neg logit contributions | |
Kai | -0.001 |
icks | -0.001 |
Leo | -0.001 |
Rex | -0.001 |
ses | -0.001 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ge | +0.034 |
igsaw | +0.029 |
chie | +0.028 |
ilda | +0.028 |
spe | +0.028 |
Neg logit contributions | |
icks | -0.025 |
Kai | -0.023 |
aw | -0.023 |
Rex | -0.023 |
ses | -0.023 |
Token | him |
Token ID | 683 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
ge | +0.031 |
igsaw | +0.027 |
ilda | +0.026 |
chie | +0.025 |
spe | +0.024 |
Neg logit contributions | |
ses | -0.029 |
icks | -0.028 |
sed | -0.027 |
aw | -0.027 |
slit | -0.026 |
Token | for |
Token ID | 329 |
Feature activation | -5.63e-03 |
Pos logit contributions | |
aw | +0.074 |
Kai | +0.074 |
ses | +0.074 |
icks | +0.072 |
slit | +0.072 |
Neg logit contributions | |
ge | -0.100 |
igsaw | -0.091 |
chie | -0.085 |
ilda | -0.083 |
pack | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
Leo | +0.016 |
Rex | +0.016 |
Kai | +0.016 |
icks | +0.016 |
aw | +0.015 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.023 |
chie | -0.021 |
ilda | -0.021 |
pack | -0.020 |
Token | parents |
Token ID | 3397 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ge | +0.005 |
igsaw | +0.005 |
chie | +0.005 |
ilda | +0.004 |
pack | +0.004 |
Neg logit contributions | |
Leo | -0.005 |
Kai | -0.005 |
Rex | -0.005 |
icks | -0.005 |
aw | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ge | +0.052 |
igsaw | +0.049 |
chie | +0.046 |
ilda | +0.045 |
pack | +0.042 |
Neg logit contributions | |
Leo | -0.034 |
Kai | -0.034 |
Rex | -0.034 |
icks | -0.033 |
named | -0.032 |
Token | also |
Token ID | 635 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
ge | +0.027 |
igsaw | +0.025 |
chie | +0.023 |
ilda | +0.023 |
pack | +0.021 |
Neg logit contributions | |
Leo | -0.020 |
Kai | -0.019 |
Rex | -0.019 |
icks | -0.019 |
named | -0.019 |
Token | qu |
Token ID | 627 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
ge | +0.065 |
igsaw | +0.062 |
ilda | +0.056 |
chie | +0.056 |
ic | +0.052 |
Neg logit contributions | |
Rex | -0.042 |
named | -0.041 |
Leo | -0.041 |
Kai | -0.041 |
icks | -0.040 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ge | +0.051 |
igsaw | +0.039 |
ilda | +0.039 |
recipe | +0.037 |
Smith | +0.035 |
Neg logit contributions | |
aw | -0.084 |
icks | -0.072 |
aver | -0.067 |
named | -0.067 |
icked | -0.066 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
igsaw | +0.272 |
ge | +0.232 |
enny | +0.228 |
ilda | +0.228 |
ott | +0.223 |
Neg logit contributions | |
aw | -0.137 |
marsh | -0.121 |
slit | -0.119 |
named | -0.118 |
then | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | +8.60e-04 |
Pos logit contributions | |
ge | +0.006 |
igsaw | +0.006 |
chie | +0.006 |
ilda | +0.005 |
spe | +0.005 |
Neg logit contributions | |
Kai | -0.005 |
Leo | -0.005 |
Rex | -0.005 |
icks | -0.005 |
ses | -0.004 |
Token | The |
Token ID | 383 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
ge | +0.002 |
igsaw | +0.002 |
chie | +0.002 |
ilda | +0.002 |
pack | +0.002 |
Neg logit contributions | |
Leo | -0.001 |
Kai | -0.001 |
Rex | -0.001 |
icks | -0.001 |
aw | -0.001 |
Token | first |
Token ID | 717 |
Feature activation | +7.78e-03 |
Pos logit contributions | |
Leo | +0.039 |
Kai | +0.039 |
icks | +0.038 |
Rex | +0.038 |
aw | +0.037 |
Neg logit contributions | |
ge | -0.037 |
igsaw | -0.035 |
chie | -0.033 |
ilda | -0.031 |
pack | -0.029 |
Token | family |
Token ID | 1641 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
ge | +0.014 |
igsaw | +0.013 |
chie | +0.012 |
ilda | +0.012 |
pack | +0.011 |
Neg logit contributions | |
Kai | -0.014 |
Leo | -0.014 |
Rex | -0.014 |
aw | -0.013 |
named | -0.013 |
Token | much |
Token ID | 881 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
Leo | +0.026 |
Kai | +0.026 |
Rex | +0.026 |
icks | +0.025 |
aw | +0.025 |
Neg logit contributions | |
ge | -0.035 |
igsaw | -0.033 |
chie | -0.031 |
ilda | -0.030 |
pack | -0.028 |
Token | more |
Token ID | 517 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
ge | +0.063 |
igsaw | +0.059 |
chie | +0.056 |
ilda | +0.054 |
pack | +0.051 |
Neg logit contributions | |
Rex | -0.043 |
Leo | -0.043 |
Kai | -0.043 |
icks | -0.042 |
aw | -0.042 |
Token | important |
Token ID | 1593 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
ge | +0.013 |
igsaw | +0.012 |
chie | +0.011 |
ilda | +0.011 |
pack | +0.010 |
Neg logit contributions | |
Leo | -0.013 |
Kai | -0.013 |
Rex | -0.013 |
icks | -0.012 |
aw | -0.012 |
Token | than |
Token ID | 621 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ge | +0.062 |
igsaw | +0.059 |
chie | +0.055 |
ilda | +0.053 |
pack | +0.050 |
Neg logit contributions | |
Leo | -0.046 |
Kai | -0.046 |
Rex | -0.045 |
icks | -0.044 |
aw | -0.043 |
Token | qu |
Token ID | 627 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
Leo | +0.021 |
Rex | +0.020 |
Kai | +0.020 |
named | +0.019 |
icks | +0.019 |
Neg logit contributions | |
ge | -0.021 |
igsaw | -0.020 |
ilda | -0.018 |
chie | -0.018 |
ini | -0.018 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ge | +0.046 |
ilda | +0.044 |
igsaw | +0.041 |
pack | +0.036 |
Smith | +0.034 |
Neg logit contributions | |
aw | -0.078 |
icks | -0.071 |
marsh | -0.065 |
named | -0.065 |
icked | -0.062 |
Token | lling |
Token ID | 2680 |
Feature activation | +7.78e-02 |
Pos logit contributions | |
igsaw | +0.262 |
ilda | +0.239 |
ge | +0.233 |
ress | +0.229 |
pack | +0.226 |
Neg logit contributions | |
aw | -0.145 |
marsh | -0.130 |
icks | -0.124 |
horns | -0.120 |
lived | -0.109 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ge | +0.164 |
igsaw | +0.155 |
chie | +0.146 |
ilda | +0.142 |
pack | +0.135 |
Neg logit contributions | |
Leo | -0.111 |
Rex | -0.110 |
Kai | -0.109 |
icks | -0.108 |
aw | -0.105 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
Kai | +0.015 |
Leo | +0.015 |
Rex | +0.015 |
icks | +0.015 |
aw | +0.015 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.023 |
chie | -0.021 |
ilda | -0.021 |
pack | -0.019 |
Token | One |
Token ID | 3198 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ge | +0.042 |
igsaw | +0.040 |
chie | +0.036 |
ilda | +0.036 |
pack | +0.034 |
Neg logit contributions | |
Kai | -0.036 |
Leo | -0.035 |
icks | -0.035 |
Rex | -0.035 |
bye | -0.034 |
Token | day |
Token ID | 1110 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
Leo | +0.024 |
Kai | +0.024 |
Rex | +0.024 |
icks | +0.023 |
aw | +0.023 |
Neg logit contributions | |
ge | -0.029 |
igsaw | -0.027 |
chie | -0.026 |
ilda | -0.025 |
pack | -0.023 |
Token | good |
Token ID | 922 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
ge | +0.013 |
chie | +0.011 |
igsaw | +0.011 |
ilda | +0.011 |
solution | +0.010 |
Neg logit contributions | |
ses | -0.012 |
sed | -0.012 |
Kai | -0.012 |
Leo | -0.012 |
icks | -0.011 |
Token | friends |
Token ID | 2460 |
Feature activation | -6.51e-03 |
Pos logit contributions | |
ge | +0.031 |
igsaw | +0.029 |
chie | +0.027 |
ilda | +0.026 |
pack | +0.025 |
Neg logit contributions | |
Kai | -0.028 |
Leo | -0.028 |
Rex | -0.027 |
icks | -0.027 |
marsh | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
Kai | +0.011 |
Leo | +0.011 |
icks | +0.011 |
Rex | +0.010 |
ses | +0.010 |
Neg logit contributions | |
ge | -0.012 |
igsaw | -0.011 |
chie | -0.011 |
ilda | -0.010 |
spe | -0.010 |
Token | never |
Token ID | 1239 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
ge | +0.046 |
igsaw | +0.042 |
chie | +0.041 |
ilda | +0.040 |
spe | +0.040 |
Neg logit contributions | |
icks | -0.035 |
Kai | -0.035 |
Leo | -0.034 |
aw | -0.034 |
Rex | -0.033 |
Token | qu |
Token ID | 627 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
igsaw | +0.009 |
ge | +0.009 |
chie | +0.008 |
ilda | +0.008 |
ic | +0.008 |
Neg logit contributions | |
Rex | -0.004 |
named | -0.004 |
Leo | -0.004 |
bye | -0.004 |
Kai | -0.004 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ge | +0.045 |
ilda | +0.041 |
igsaw | +0.036 |
chie | +0.033 |
recipe | +0.031 |
Neg logit contributions | |
aw | -0.091 |
icks | -0.084 |
icked | -0.076 |
named | -0.076 |
agged | -0.075 |
Token | led |
Token ID | 992 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
igsaw | +0.348 |
ilda | +0.305 |
ge | +0.304 |
chie | +0.295 |
ott | +0.285 |
Neg logit contributions | |
aw | -0.084 |
icked | -0.059 |
icks | -0.058 |
named | -0.056 |
slit | -0.054 |
Token | again |
Token ID | 757 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ge | +0.033 |
igsaw | +0.031 |
chie | +0.028 |
ilda | +0.027 |
pack | +0.026 |
Neg logit contributions | |
Leo | -0.035 |
Kai | -0.035 |
Rex | -0.035 |
icks | -0.034 |
aw | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +8.51e-04 |
Pos logit contributions | |
Leo | +0.013 |
Rex | +0.013 |
named | +0.012 |
Kai | +0.012 |
aw | +0.012 |
Neg logit contributions | |
ge | -0.023 |
igsaw | -0.023 |
chie | -0.022 |
ilda | -0.021 |
pack | -0.020 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ge | +0.002 |
igsaw | +0.002 |
chie | +0.002 |
ilda | +0.002 |
pack | +0.002 |
Neg logit contributions | |
Kai | -0.001 |
Leo | -0.001 |
Rex | -0.001 |
icks | -0.001 |
aw | -0.001 |
Token | Once |
Token ID | 7454 |
Feature activation | +4.45e-05 |
Pos logit contributions | |
ge | +0.061 |
igsaw | +0.057 |
chie | +0.054 |
ilda | +0.052 |
pack | +0.049 |
Neg logit contributions | |
Leo | -0.044 |
Kai | -0.043 |
Rex | -0.043 |
icks | -0.042 |
aw | -0.041 |
Token | little |
Token ID | 1310 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ge | +0.057 |
igsaw | +0.055 |
chie | +0.050 |
pack | +0.049 |
ilda | +0.049 |
Neg logit contributions | |
Rex | -0.042 |
Leo | -0.041 |
Kai | -0.041 |
aw | -0.041 |
named | -0.040 |
Token | birds |
Token ID | 10087 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
ge | +0.043 |
igsaw | +0.041 |
ilda | +0.038 |
chie | +0.037 |
pack | +0.037 |
Neg logit contributions | |
Leo | -0.030 |
Rex | -0.030 |
Kai | -0.029 |
aw | -0.028 |
ear | -0.027 |
Token | that |
Token ID | 326 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
Kai | +0.026 |
Leo | +0.026 |
Rex | +0.026 |
icks | +0.026 |
bye | +0.025 |
Neg logit contributions | |
ge | -0.034 |
igsaw | -0.030 |
chie | -0.029 |
ilda | -0.028 |
pack | -0.026 |
Token | were |
Token ID | 547 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ge | +0.036 |
ilda | +0.031 |
spe | +0.031 |
chie | +0.031 |
igsaw | +0.031 |
Neg logit contributions | |
icks | -0.039 |
bye | -0.037 |
ear | -0.036 |
Kai | -0.036 |
ses | -0.036 |
Token | qu |
Token ID | 627 |
Feature activation | +4.53e-02 |
Pos logit contributions | |
ge | +0.047 |
igsaw | +0.042 |
chie | +0.041 |
ilda | +0.039 |
pack | +0.036 |
Neg logit contributions | |
Kai | -0.039 |
Leo | -0.039 |
Rex | -0.039 |
icks | -0.038 |
aw | -0.038 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ge | +0.079 |
igsaw | +0.069 |
ilda | +0.068 |
spe | +0.065 |
recipe | +0.063 |
Neg logit contributions | |
aw | -0.094 |
icks | -0.082 |
named | -0.074 |
aver | -0.073 |
icked | -0.073 |
Token | ling |
Token ID | 1359 |
Feature activation | +8.27e-03 |
Pos logit contributions | |
igsaw | +0.300 |
enny | +0.255 |
ress | +0.249 |
ilda | +0.249 |
ge | +0.242 |
Neg logit contributions | |
aw | -0.127 |
slit | -0.112 |
marsh | -0.106 |
icks | -0.106 |
ped | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | +8.17e-03 |
Pos logit contributions | |
ge | +0.015 |
igsaw | +0.014 |
chie | +0.013 |
ilda | +0.012 |
spe | +0.012 |
Neg logit contributions | |
Kai | -0.014 |
Leo | -0.014 |
Rex | -0.014 |
icks | -0.013 |
ses | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.017 |
chie | +0.016 |
ilda | +0.016 |
pack | +0.015 |
Neg logit contributions | |
Kai | -0.010 |
Leo | -0.010 |
Rex | -0.010 |
icks | -0.010 |
aw | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
ge | +0.045 |
igsaw | +0.042 |
chie | +0.039 |
ilda | +0.039 |
pack | +0.037 |
Neg logit contributions | |
Kai | -0.030 |
Leo | -0.030 |
Rex | -0.030 |
icks | -0.030 |
aw | -0.029 |
Token | The |
Token ID | 464 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
ge | +0.042 |
igsaw | +0.039 |
chie | +0.036 |
ilda | +0.036 |
ic | +0.034 |
Neg logit contributions | |
Leo | -0.029 |
Rex | -0.029 |
Kai | -0.029 |
named | -0.028 |
aw | -0.028 |
Token | Please |
Token ID | 5492 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
ge | +0.033 |
igsaw | +0.033 |
ilda | +0.029 |
chie | +0.028 |
pack | +0.027 |
Neg logit contributions | |
aw | -0.021 |
Kai | -0.021 |
Rex | -0.020 |
Leo | -0.020 |
named | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
aw | +0.085 |
Leo | +0.083 |
Kai | +0.083 |
icks | +0.083 |
Rex | +0.080 |
Neg logit contributions | |
ge | -0.094 |
igsaw | -0.086 |
chie | -0.085 |
ilda | -0.080 |
pack | -0.078 |
Token | no |
Token ID | 645 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
Leo | +0.016 |
Kai | +0.016 |
Rex | +0.016 |
icks | +0.015 |
aw | +0.015 |
Neg logit contributions | |
ge | -0.021 |
igsaw | -0.020 |
chie | -0.019 |
ilda | -0.018 |
pack | -0.017 |
Token | more |
Token ID | 517 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
Rex | +0.050 |
bye | +0.049 |
Kai | +0.049 |
Leo | +0.048 |
named | +0.048 |
Neg logit contributions | |
igsaw | -0.066 |
ge | -0.065 |
ilda | -0.060 |
chie | -0.058 |
pack | -0.057 |
Token | qu |
Token ID | 627 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
ge | +0.023 |
igsaw | +0.022 |
chie | +0.020 |
ilda | +0.020 |
pack | +0.019 |
Neg logit contributions | |
Rex | -0.019 |
Leo | -0.019 |
Kai | -0.019 |
icks | -0.019 |
aw | -0.019 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
ge | +0.068 |
ilda | +0.058 |
igsaw | +0.055 |
Emmy | +0.049 |
Smith | +0.048 |
Neg logit contributions | |
aw | -0.100 |
icks | -0.095 |
named | -0.083 |
icked | -0.079 |
Rex | -0.076 |
Token | ling |
Token ID | 1359 |
Feature activation | +3.16e-03 |
Pos logit contributions | |
igsaw | +0.250 |
ge | +0.227 |
ilda | +0.217 |
enny | +0.207 |
ott | +0.205 |
Neg logit contributions | |
icks | -0.160 |
aw | -0.159 |
thank | -0.149 |
marsh | -0.146 |
bye | -0.145 |
Token | ! |
Token ID | 0 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
ge | +0.006 |
igsaw | +0.005 |
chie | +0.005 |
ilda | +0.005 |
pack | +0.004 |
Neg logit contributions | |
Kai | -0.006 |
Leo | -0.006 |
Rex | -0.006 |
icks | -0.005 |
aw | -0.005 |
Token | Let |
Token ID | 3914 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
ge | +0.024 |
igsaw | +0.023 |
chie | +0.022 |
ilda | +0.021 |
pack | +0.020 |
Neg logit contributions | |
Kai | -0.022 |
Leo | -0.022 |
Rex | -0.021 |
icks | -0.021 |
aw | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | +2.20e-03 |
Pos logit contributions | |
Rex | +0.002 |
Leo | +0.002 |
Kai | +0.002 |
aw | +0.002 |
bye | +0.002 |
Neg logit contributions | |
ge | -0.002 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.001 |
pack | -0.001 |
Token | find |
Token ID | 1064 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.004 |
chie | +0.003 |
ilda | +0.003 |
pack | +0.003 |
Neg logit contributions | |
Kai | -0.004 |
Leo | -0.004 |
Rex | -0.004 |
aw | -0.004 |
icks | -0.004 |
Token | Sharing |
Token ID | 36644 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ge | +0.007 |
igsaw | +0.007 |
chie | +0.006 |
ilda | +0.006 |
spe | +0.006 |
Neg logit contributions | |
Kai | -0.004 |
icks | -0.004 |
Leo | -0.004 |
marsh | -0.004 |
slit | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ge | +0.038 |
igsaw | +0.036 |
chie | +0.033 |
ilda | +0.032 |
pack | +0.031 |
Neg logit contributions | |
Kai | -0.029 |
Leo | -0.029 |
Rex | -0.029 |
icks | -0.028 |
aw | -0.028 |
Token | better |
Token ID | 1365 |
Feature activation | +6.55e-03 |
Pos logit contributions | |
Kai | +0.044 |
Leo | +0.044 |
icks | +0.043 |
Rex | +0.043 |
aw | +0.042 |
Neg logit contributions | |
ge | -0.043 |
igsaw | -0.041 |
chie | -0.038 |
ilda | -0.037 |
pack | -0.035 |
Token | than |
Token ID | 621 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ge | +0.014 |
igsaw | +0.013 |
chie | +0.013 |
ilda | +0.012 |
pack | +0.012 |
Neg logit contributions | |
Rex | -0.009 |
Leo | -0.009 |
Kai | -0.009 |
icks | -0.009 |
aw | -0.009 |
Token | qu |
Token ID | 627 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
Leo | +0.021 |
Rex | +0.021 |
Kai | +0.020 |
named | +0.020 |
icks | +0.020 |
Neg logit contributions | |
ge | -0.022 |
igsaw | -0.021 |
ilda | -0.019 |
chie | -0.019 |
ini | -0.019 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ge | +0.044 |
ilda | +0.039 |
igsaw | +0.037 |
chie | +0.030 |
pack | +0.030 |
Neg logit contributions | |
aw | -0.088 |
icks | -0.083 |
named | -0.075 |
icked | -0.075 |
agged | -0.072 |
Token | ling |
Token ID | 1359 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
igsaw | +0.266 |
ge | +0.238 |
ilda | +0.236 |
chie | +0.227 |
ress | +0.227 |
Neg logit contributions | |
aw | -0.133 |
icks | -0.131 |
horns | -0.116 |
sorry | -0.114 |
Leo | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
Kai | +0.008 |
Leo | +0.008 |
Rex | +0.008 |
icks | +0.008 |
aw | +0.008 |
Neg logit contributions | |
ge | -0.011 |
igsaw | -0.010 |
chie | -0.010 |
ilda | -0.009 |
spe | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
Kai | +0.005 |
icks | +0.004 |
Leo | +0.004 |
slit | +0.004 |
marsh | +0.004 |
Neg logit contributions | |
ge | -0.007 |
igsaw | -0.007 |
chie | -0.006 |
ilda | -0.006 |
pack | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -1.31e-03 |
Pos logit contributions | |
Kai | +0.016 |
Leo | +0.015 |
Rex | +0.015 |
icks | +0.015 |
marsh | +0.015 |
Neg logit contributions | |
ge | -0.020 |
igsaw | -0.018 |
chie | -0.018 |
ilda | -0.017 |
spe | -0.017 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
Kai | +0.002 |
ses | +0.002 |
Rex | +0.002 |
Leo | +0.002 |
marsh | +0.002 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.003 |
chie | -0.002 |
ilda | -0.002 |
spe | -0.002 |
Token | both |
Token ID | 1111 |
Feature activation | +5.95e-03 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.017 |
chie | +0.016 |
ilda | +0.015 |
spe | +0.015 |
Neg logit contributions | |
icks | -0.014 |
Kai | -0.013 |
aw | -0.013 |
Leo | -0.013 |
Rex | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +9.37e-03 |
Pos logit contributions | |
ge | +0.011 |
igsaw | +0.011 |
chie | +0.010 |
ilda | +0.010 |
pack | +0.009 |
Neg logit contributions | |
Leo | -0.010 |
Kai | -0.010 |
Rex | -0.010 |
icks | -0.009 |
aw | -0.009 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
ge | +0.017 |
igsaw | +0.017 |
chie | +0.016 |
ilda | +0.015 |
pack | +0.014 |
Neg logit contributions | |
Kai | -0.015 |
icks | -0.015 |
Leo | -0.015 |
Rex | -0.015 |
aw | -0.015 |
Token | stopped |
Token ID | 5025 |
Feature activation | +9.79e-03 |
Pos logit contributions | |
ge | +0.026 |
igsaw | +0.023 |
chie | +0.023 |
ilda | +0.023 |
spe | +0.021 |
Neg logit contributions | |
Kai | -0.020 |
Leo | -0.020 |
Rex | -0.020 |
icks | -0.019 |
ses | -0.019 |
Token | qu |
Token ID | 627 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ge | +0.019 |
igsaw | +0.018 |
chie | +0.017 |
ilda | +0.016 |
pack | +0.015 |
Neg logit contributions | |
Leo | -0.016 |
Kai | -0.016 |
Rex | -0.016 |
icks | -0.015 |
aw | -0.015 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ge | +0.063 |
ilda | +0.053 |
igsaw | +0.051 |
spe | +0.047 |
chie | +0.046 |
Neg logit contributions | |
aw | -0.082 |
icks | -0.071 |
named | -0.065 |
marsh | -0.064 |
Rex | -0.063 |
Token | ling |
Token ID | 1359 |
Feature activation | +6.93e-04 |
Pos logit contributions | |
igsaw | +0.277 |
ge | +0.237 |
enny | +0.236 |
ilda | +0.231 |
chie | +0.227 |
Neg logit contributions | |
aw | -0.143 |
slit | -0.127 |
marsh | -0.126 |
then | -0.122 |
goodbye | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +2.73e-03 |
Pos logit contributions | |
ge | +0.001 |
igsaw | +0.001 |
chie | +0.001 |
ilda | +0.001 |
spe | +0.001 |
Neg logit contributions | |
Kai | -0.001 |
Leo | -0.001 |
Rex | -0.001 |
icks | -0.001 |
ses | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
igsaw | +0.006 |
ge | +0.005 |
chie | +0.005 |
ilda | +0.005 |
spe | +0.005 |
Neg logit contributions | |
Kai | -0.004 |
icks | -0.004 |
Leo | -0.004 |
aw | -0.004 |
Rex | -0.004 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
ge | +0.022 |
chie | +0.019 |
ilda | +0.018 |
igsaw | +0.018 |
spe | +0.018 |
Neg logit contributions | |
icks | -0.020 |
Kai | -0.020 |
ses | -0.020 |
Rex | -0.020 |
Leo | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ge | +0.024 |
igsaw | +0.022 |
chie | +0.020 |
ilda | +0.019 |
pack | +0.018 |
Neg logit contributions | |
Leo | -0.029 |
Kai | -0.029 |
Rex | -0.028 |
icks | -0.028 |
aw | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
igsaw | +0.041 |
ge | +0.040 |
chie | +0.038 |
ilda | +0.036 |
ic | +0.034 |
Neg logit contributions | |
named | -0.028 |
Rex | -0.027 |
Leo | -0.027 |
Kai | -0.026 |
icks | -0.026 |
Token | their |
Token ID | 511 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ge | +0.030 |
igsaw | +0.028 |
chie | +0.026 |
ilda | +0.026 |
pack | +0.024 |
Neg logit contributions | |
Rex | -0.024 |
Leo | -0.024 |
Kai | -0.024 |
named | -0.023 |
icks | -0.023 |
Token | children |
Token ID | 1751 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
ge | +0.047 |
igsaw | +0.044 |
chie | +0.041 |
ilda | +0.040 |
pack | +0.038 |
Neg logit contributions | |
Leo | -0.041 |
Rex | -0.041 |
Kai | -0.041 |
icks | -0.039 |
aw | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ge | +0.079 |
igsaw | +0.078 |
chie | +0.073 |
ilda | +0.070 |
ini | +0.066 |
Neg logit contributions | |
Rex | -0.052 |
Leo | -0.052 |
Kai | -0.051 |
named | -0.051 |
icks | -0.051 |
Token | qu |
Token ID | 627 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ge | +0.042 |
igsaw | +0.039 |
chie | +0.037 |
ilda | +0.036 |
pack | +0.034 |
Neg logit contributions | |
icks | -0.032 |
Kai | -0.031 |
Leo | -0.031 |
aw | -0.030 |
Rex | -0.030 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ge | +0.057 |
igsaw | +0.049 |
ilda | +0.046 |
chie | +0.041 |
spe | +0.040 |
Neg logit contributions | |
aw | -0.077 |
icks | -0.067 |
named | -0.064 |
Rex | -0.060 |
aver | -0.060 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
igsaw | +0.313 |
enny | +0.262 |
ge | +0.257 |
chie | +0.250 |
Smith | +0.248 |
Neg logit contributions | |
aw | -0.112 |
ped | -0.095 |
horns | -0.093 |
marsh | -0.091 |
icks | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
ge | +0.002 |
igsaw | +0.002 |
chie | +0.002 |
ilda | +0.002 |
pack | +0.002 |
Neg logit contributions | |
Leo | -0.002 |
Kai | -0.002 |
Rex | -0.002 |
icks | -0.002 |
aw | -0.001 |
Token | |
Token ID | 220 |
Feature activation | +3.51e-02 |
Pos logit contributions | |
ge | +0.024 |
igsaw | +0.022 |
chie | +0.021 |
ilda | +0.020 |
ic | +0.020 |
Neg logit contributions | |
Rex | -0.010 |
Leo | -0.009 |
Kai | -0.009 |
named | -0.009 |
Spot | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ge | +0.085 |
igsaw | +0.081 |
chie | +0.078 |
ilda | +0.073 |
pack | +0.070 |
Neg logit contributions | |
Rex | -0.042 |
Leo | -0.042 |
Kai | -0.041 |
icks | -0.039 |
named | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ge | +0.047 |
igsaw | +0.046 |
chie | +0.044 |
ilda | +0.042 |
ic | +0.040 |
Neg logit contributions | |
Rex | -0.019 |
Leo | -0.019 |
Kai | -0.018 |
named | -0.018 |
Spot | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-04 |
Pos logit contributions | |
ge | +0.006 |
igsaw | +0.005 |
chie | +0.005 |
ilda | +0.005 |
hr | +0.005 |
Neg logit contributions | |
icks | -0.005 |
Kai | -0.005 |
aw | -0.005 |
Rex | -0.005 |
Leo | -0.005 |
Token | birds |
Token ID | 10087 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
ge | +0.000 |
igsaw | +0.000 |
chie | +0.000 |
ilda | +0.000 |
ini | +0.000 |
Neg logit contributions | |
icks | -0.000 |
Leo | -0.000 |
Kai | -0.000 |
Rex | -0.000 |
aw | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
Leo | +0.005 |
Kai | +0.005 |
Rex | +0.005 |
icks | +0.005 |
aw | +0.005 |
Neg logit contributions | |
ge | -0.008 |
igsaw | -0.007 |
chie | -0.007 |
ilda | -0.007 |
pack | -0.006 |
Token | only |
Token ID | 691 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
ge | +0.023 |
igsaw | +0.022 |
chie | +0.021 |
ilda | +0.020 |
pack | +0.019 |
Neg logit contributions | |
Leo | -0.020 |
Kai | -0.020 |
Rex | -0.020 |
icks | -0.020 |
aw | -0.019 |
Token | qu |
Token ID | 627 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.010 |
ilda | +0.009 |
chie | +0.009 |
pack | +0.008 |
Neg logit contributions | |
Leo | -0.008 |
Rex | -0.008 |
Kai | -0.007 |
named | -0.007 |
icks | -0.007 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
ge | +0.052 |
ilda | +0.046 |
igsaw | +0.043 |
recipe | +0.040 |
spe | +0.039 |
Neg logit contributions | |
aw | -0.093 |
icks | -0.087 |
icked | -0.080 |
named | -0.078 |
agged | -0.078 |
Token | ling |
Token ID | 1359 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
igsaw | +0.289 |
ilda | +0.250 |
enny | +0.242 |
ge | +0.241 |
ress | +0.239 |
Neg logit contributions | |
aw | -0.114 |
icks | -0.102 |
marsh | -0.102 |
slit | -0.100 |
named | -0.098 |
Token | like |
Token ID | 588 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
Kai | +0.003 |
Leo | +0.003 |
Rex | +0.003 |
icks | +0.003 |
ses | +0.003 |
Neg logit contributions | |
ge | -0.004 |
igsaw | -0.004 |
chie | -0.003 |
ilda | -0.003 |
spe | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
icks | +0.030 |
Kai | +0.029 |
aw | +0.029 |
Leo | +0.028 |
Rex | +0.028 |
Neg logit contributions | |
ge | -0.036 |
igsaw | -0.033 |
chie | -0.032 |
ilda | -0.031 |
hr | -0.029 |
Token | children |
Token ID | 1751 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
ge | +0.020 |
igsaw | +0.019 |
chie | +0.018 |
ilda | +0.017 |
pack | +0.016 |
Neg logit contributions | |
Leo | -0.015 |
Kai | -0.015 |
Rex | -0.015 |
icks | -0.015 |
aw | -0.014 |
Token | do |
Token ID | 466 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
ge | +0.070 |
igsaw | +0.065 |
chie | +0.062 |
ilda | +0.060 |
pack | +0.057 |
Neg logit contributions | |
Kai | -0.045 |
Leo | -0.045 |
Rex | -0.045 |
icks | -0.044 |
aw | -0.043 |
Token | sharing |
Token ID | 7373 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
ge | +0.001 |
igsaw | +0.000 |
chie | +0.000 |
ilda | +0.000 |
pack | +0.000 |
Neg logit contributions | |
Kai | -0.000 |
icks | -0.000 |
Leo | -0.000 |
Rex | -0.000 |
aw | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
Leo | +0.004 |
Rex | +0.004 |
Kai | +0.004 |
icks | +0.004 |
aw | +0.003 |
Neg logit contributions | |
ge | -0.005 |
igsaw | -0.005 |
chie | -0.005 |
ilda | -0.004 |
pack | -0.004 |
Token | important |
Token ID | 1593 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
Kai | +0.042 |
Leo | +0.042 |
Rex | +0.041 |
icks | +0.040 |
aw | +0.040 |
Neg logit contributions | |
ge | -0.049 |
igsaw | -0.046 |
chie | -0.043 |
ilda | -0.042 |
pack | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ge | +0.045 |
igsaw | +0.043 |
chie | +0.040 |
ilda | +0.039 |
pack | +0.037 |
Neg logit contributions | |
Leo | -0.030 |
Kai | -0.030 |
Rex | -0.030 |
icks | -0.029 |
aw | -0.028 |
Token | qu |
Token ID | 627 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
ge | +0.031 |
igsaw | +0.030 |
chie | +0.028 |
ilda | +0.027 |
pack | +0.025 |
Neg logit contributions | |
Rex | -0.020 |
Leo | -0.020 |
Kai | -0.019 |
icks | -0.019 |
named | -0.019 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ge | +0.043 |
ilda | +0.035 |
igsaw | +0.032 |
chie | +0.028 |
hr | +0.026 |
Neg logit contributions | |
aw | -0.077 |
icks | -0.076 |
named | -0.069 |
icked | -0.067 |
Rex | -0.065 |
Token | lling |
Token ID | 2680 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
igsaw | +0.296 |
ge | +0.274 |
ilda | +0.259 |
chie | +0.251 |
ress | +0.247 |
Neg logit contributions | |
aw | -0.103 |
icks | -0.100 |
lived | -0.089 |
named | -0.084 |
icked | -0.083 |
Token | is |
Token ID | 318 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
ge | +0.155 |
igsaw | +0.147 |
chie | +0.138 |
ilda | +0.134 |
pack | +0.128 |
Neg logit contributions | |
Leo | -0.098 |
Rex | -0.098 |
icks | -0.098 |
Kai | -0.096 |
aw | -0.094 |
Token | not |
Token ID | 407 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
Kai | +0.052 |
Leo | +0.051 |
aw | +0.050 |
Rex | +0.050 |
icks | +0.049 |
Neg logit contributions | |
ge | -0.056 |
igsaw | -0.050 |
chie | -0.048 |
ilda | -0.046 |
pack | -0.044 |
Token | good |
Token ID | 922 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
igsaw | +0.028 |
ge | +0.028 |
ilda | +0.026 |
ini | +0.025 |
chie | +0.025 |
Neg logit contributions | |
named | -0.018 |
Rex | -0.018 |
Leo | -0.017 |
thank | -0.017 |
Spot | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.017 |
chie | +0.017 |
ilda | +0.016 |
pack | +0.015 |
Neg logit contributions | |
icks | -0.010 |
Rex | -0.010 |
Leo | -0.010 |
thank | -0.009 |
bye | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
Kai | +0.007 |
named | +0.007 |
icks | +0.007 |
Leo | +0.007 |
Rover | +0.007 |
Neg logit contributions | |
ge | -0.009 |
igsaw | -0.008 |
chie | -0.008 |
ilda | -0.008 |
pack | -0.008 |
Token | snow |
Token ID | 6729 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
Leo | +0.043 |
Kai | +0.043 |
Rex | +0.043 |
icks | +0.042 |
aw | +0.041 |
Neg logit contributions | |
ge | -0.058 |
igsaw | -0.054 |
chie | -0.051 |
ilda | -0.049 |
pack | -0.047 |
Token | man |
Token ID | 805 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
Kai | +0.101 |
icks | +0.100 |
Rover | +0.100 |
Leo | +0.099 |
aw | +0.098 |
Neg logit contributions | |
ge | -0.076 |
igsaw | -0.062 |
ic | -0.062 |
pack | -0.060 |
chie | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
Leo | +0.073 |
Kai | +0.073 |
Rex | +0.073 |
icks | +0.071 |
aw | +0.069 |
Neg logit contributions | |
ge | -0.098 |
igsaw | -0.092 |
chie | -0.087 |
ilda | -0.084 |
pack | -0.079 |
Token | a |
Token ID | 257 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
aw | +0.031 |
icks | +0.030 |
Kai | +0.029 |
Rover | +0.028 |
agged | +0.028 |
Neg logit contributions | |
ge | -0.027 |
igsaw | -0.022 |
ilda | -0.022 |
pack | -0.022 |
spe | -0.021 |
Token | snowball |
Token ID | 46275 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
icks | +0.053 |
icked | +0.052 |
aw | +0.051 |
Kai | +0.050 |
Leo | +0.050 |
Neg logit contributions | |
ge | -0.064 |
igsaw | -0.062 |
solution | -0.056 |
chie | -0.056 |
mess | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
Kai | +0.144 |
Rover | +0.140 |
Leo | +0.140 |
aw | +0.139 |
Dod | +0.137 |
Neg logit contributions | |
ge | -0.200 |
igsaw | -0.171 |
mess | -0.164 |
chie | -0.162 |
pack | -0.160 |
Token | a |
Token ID | 257 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
icks | +0.032 |
Kai | +0.032 |
aw | +0.031 |
hawk | +0.030 |
ses | +0.030 |
Neg logit contributions | |
ge | -0.026 |
pack | -0.022 |
cost | -0.022 |
igsaw | -0.021 |
ilda | -0.021 |
Token | snow |
Token ID | 6729 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
icks | +0.055 |
icked | +0.054 |
Kai | +0.052 |
aw | +0.052 |
Leo | +0.052 |
Neg logit contributions | |
igsaw | -0.066 |
ge | -0.066 |
chie | -0.060 |
solution | -0.059 |
mess | -0.058 |
Token | angel |
Token ID | 18304 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
icks | +0.103 |
Kai | +0.101 |
Leo | +0.100 |
Rover | +0.100 |
aw | +0.099 |
Neg logit contributions | |
ge | -0.069 |
ic | -0.057 |
igsaw | -0.053 |
pack | -0.052 |
chie | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -6.44e-03 |
Pos logit contributions | |
Kai | +0.053 |
Leo | +0.052 |
icks | +0.051 |
Rex | +0.051 |
Rover | +0.050 |
Neg logit contributions | |
ge | -0.055 |
igsaw | -0.047 |
chie | -0.046 |
ilda | -0.044 |
pack | -0.043 |
Token | favorite |
Token ID | 4004 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
Kai | +0.019 |
Leo | +0.019 |
icks | +0.019 |
Rex | +0.019 |
aw | +0.018 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.015 |
chie | -0.014 |
ilda | -0.013 |
pack | -0.012 |
Token | songs |
Token ID | 7259 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
Kai | +0.003 |
Leo | +0.003 |
icks | +0.003 |
Rex | +0.003 |
aw | +0.002 |
Neg logit contributions | |
ge | -0.002 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
pack | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -6.00e-03 |
Pos logit contributions | |
Kai | +0.019 |
icks | +0.018 |
Leo | +0.018 |
Rex | +0.018 |
ses | +0.017 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.021 |
ilda | -0.021 |
chie | -0.020 |
re | -0.019 |
Token | sang |
Token ID | 25889 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
icks | +0.010 |
aw | +0.010 |
Kai | +0.009 |
ses | +0.009 |
icked | +0.009 |
Neg logit contributions | |
ge | -0.011 |
ilda | -0.009 |
igsaw | -0.009 |
spe | -0.009 |
any | -0.009 |
Token | as |
Token ID | 355 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ses | +0.020 |
Kai | +0.020 |
icks | +0.020 |
sed | +0.019 |
slit | +0.019 |
Neg logit contributions | |
ge | -0.027 |
igsaw | -0.025 |
ilda | -0.024 |
chie | -0.023 |
very | -0.022 |
Token | loud |
Token ID | 7812 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
icks | +0.036 |
Kai | +0.035 |
ses | +0.035 |
Leo | +0.034 |
sed | +0.034 |
Neg logit contributions | |
ge | -0.052 |
igsaw | -0.049 |
ilda | -0.045 |
chie | -0.044 |
spe | -0.043 |
Token | as |
Token ID | 355 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
icks | +0.166 |
Kai | +0.158 |
ses | +0.158 |
Leo | +0.156 |
Dod | +0.155 |
Neg logit contributions | |
ge | -0.170 |
igsaw | -0.155 |
ilda | -0.144 |
chie | -0.135 |
very | -0.129 |
Token | they |
Token ID | 484 |
Feature activation | +4.11e-03 |
Pos logit contributions | |
icks | +0.026 |
ses | +0.025 |
sed | +0.024 |
aw | +0.024 |
ear | +0.023 |
Neg logit contributions | |
ge | -0.033 |
igsaw | -0.030 |
ilda | -0.028 |
chie | -0.027 |
spe | -0.027 |
Token | could |
Token ID | 714 |
Feature activation | -6.21e-03 |
Pos logit contributions | |
ge | +0.008 |
ilda | +0.007 |
chie | +0.007 |
igsaw | +0.006 |
re | +0.006 |
Neg logit contributions | |
icks | -0.006 |
Kai | -0.006 |
Leo | -0.006 |
ses | -0.006 |
Rex | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
Kai | +0.010 |
Leo | +0.010 |
Rex | +0.010 |
aw | +0.010 |
icks | +0.010 |
Neg logit contributions | |
ge | -0.012 |
igsaw | -0.011 |
chie | -0.010 |
ilda | -0.010 |
pack | -0.009 |
Token | but |
Token ID | 475 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
ge | +0.006 |
igsaw | +0.005 |
chie | +0.005 |
ilda | +0.005 |
pack | +0.005 |
Neg logit contributions | |
icks | -0.005 |
Kai | -0.005 |
aw | -0.005 |
Leo | -0.005 |
Rex | -0.004 |
Token | top |
Token ID | 1353 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
icks | +0.068 |
bye | +0.066 |
Kai | +0.066 |
sed | +0.066 |
ses | +0.065 |
Neg logit contributions | |
ge | -0.065 |
igsaw | -0.063 |
ilda | -0.053 |
chie | -0.053 |
pack | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
Leo | +0.070 |
Rex | +0.069 |
Kai | +0.069 |
icks | +0.068 |
aw | +0.067 |
Neg logit contributions | |
ge | -0.086 |
igsaw | -0.081 |
chie | -0.077 |
ilda | -0.074 |
pack | -0.070 |
Token | They |
Token ID | 1119 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
hawk | +0.029 |
Kai | +0.027 |
slit | +0.027 |
aw | +0.026 |
haw | +0.025 |
Neg logit contributions | |
igsaw | -0.020 |
Gr | -0.016 |
arre | -0.015 |
Emmy | -0.014 |
care | -0.014 |
Token | used |
Token ID | 973 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
Kai | +0.033 |
icks | +0.032 |
Rex | +0.032 |
Leo | +0.032 |
bye | +0.031 |
Neg logit contributions | |
ge | -0.037 |
igsaw | -0.031 |
ilda | -0.031 |
chie | -0.030 |
spe | -0.030 |
Token | their |
Token ID | 511 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
Kai | +0.032 |
aw | +0.031 |
bye | +0.031 |
Dod | +0.030 |
named | +0.030 |
Neg logit contributions | |
ge | -0.037 |
igsaw | -0.035 |
chie | -0.032 |
pack | -0.029 |
spe | -0.029 |
Token | sword |
Token ID | 8429 |
Feature activation | -9.98e-02 |
Pos logit contributions | |
Kai | +0.037 |
Dod | +0.037 |
aw | +0.037 |
Rover | +0.036 |
Rex | +0.036 |
Neg logit contributions | |
ge | -0.044 |
igsaw | -0.044 |
chie | -0.043 |
solution | -0.038 |
project | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
Kai | +0.180 |
Leo | +0.177 |
Rex | +0.176 |
aw | +0.174 |
icks | +0.173 |
Neg logit contributions | |
ge | -0.171 |
igsaw | -0.155 |
chie | -0.143 |
ilda | -0.140 |
pack | -0.131 |
Token | fight |
Token ID | 1907 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
aw | +0.017 |
Kai | +0.016 |
icks | +0.016 |
Rex | +0.016 |
Leo | +0.016 |
Neg logit contributions | |
ge | -0.015 |
igsaw | -0.013 |
chie | -0.012 |
pack | -0.012 |
ilda | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
Kai | +0.009 |
Dod | +0.009 |
icks | +0.008 |
named | +0.008 |
ses | +0.008 |
Neg logit contributions | |
ge | -0.010 |
igsaw | -0.009 |
ilda | -0.008 |
chie | -0.008 |
solution | -0.008 |
Token | bad |
Token ID | 2089 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
Leo | +0.014 |
Kai | +0.014 |
Rex | +0.014 |
icks | +0.013 |
aw | +0.013 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.015 |
chie | -0.014 |
ilda | -0.014 |
pack | -0.013 |
Token | guys |
Token ID | 3730 |
Feature activation | +6.70e-03 |
Pos logit contributions | |
ge | +0.007 |
igsaw | +0.007 |
chie | +0.006 |
ilda | +0.006 |
pack | +0.005 |
Neg logit contributions | |
Kai | -0.007 |
Leo | -0.007 |
Rex | -0.006 |
icks | -0.006 |
aw | -0.006 |
Token | You |
Token ID | 921 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
igsaw | +0.018 |
ge | +0.017 |
chie | +0.017 |
enny | +0.015 |
ilda | +0.015 |
Neg logit contributions | |
aw | -0.024 |
slit | -0.024 |
marsh | -0.023 |
Kai | -0.023 |
hawk | -0.023 |
Token | can |
Token ID | 460 |
Feature activation | +3.07e-03 |
Pos logit contributions | |
Leo | +0.019 |
Rex | +0.018 |
Kai | +0.018 |
icks | +0.018 |
named | +0.018 |
Neg logit contributions | |
ge | -0.041 |
igsaw | -0.039 |
chie | -0.036 |
ilda | -0.036 |
ic | -0.034 |
Token | be |
Token ID | 307 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ge | +0.006 |
igsaw | +0.006 |
chie | +0.005 |
ilda | +0.005 |
pack | +0.005 |
Neg logit contributions | |
Leo | -0.005 |
Kai | -0.005 |
Rex | -0.005 |
icks | -0.005 |
aw | -0.005 |
Token | my |
Token ID | 616 |
Feature activation | +3.24e-03 |
Pos logit contributions | |
Kai | +0.025 |
Leo | +0.024 |
Rex | +0.024 |
icks | +0.024 |
aw | +0.023 |
Neg logit contributions | |
ge | -0.034 |
igsaw | -0.032 |
chie | -0.030 |
ilda | -0.029 |
pack | -0.027 |
Token | side |
Token ID | 1735 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ge | +0.006 |
igsaw | +0.005 |
chie | +0.005 |
ilda | +0.005 |
pack | +0.004 |
Neg logit contributions | |
Leo | -0.006 |
Kai | -0.006 |
Rex | -0.006 |
icks | -0.006 |
aw | -0.006 |
Token | kick |
Token ID | 24585 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
Kai | +0.023 |
Leo | +0.023 |
Rex | +0.023 |
icks | +0.022 |
aw | +0.022 |
Neg logit contributions | |
ge | -0.025 |
igsaw | -0.023 |
chie | -0.022 |
ilda | -0.021 |
pack | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e-03 |
Pos logit contributions | |
Kai | +0.181 |
icks | +0.176 |
ses | +0.175 |
sed | +0.173 |
slit | +0.172 |
Neg logit contributions | |
ge | -0.157 |
chie | -0.136 |
igsaw | -0.135 |
ilda | -0.135 |
ic | -0.128 |
Token | and |
Token ID | 290 |
Feature activation | -7.31e-03 |
Pos logit contributions | |
icks | +0.002 |
Kai | +0.002 |
aw | +0.002 |
Leo | +0.002 |
marsh | +0.002 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
spe | -0.002 |
Token | we |
Token ID | 356 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
Kai | +0.012 |
aw | +0.012 |
icks | +0.012 |
Leo | +0.012 |
Rex | +0.012 |
Neg logit contributions | |
ge | -0.014 |
igsaw | -0.012 |
chie | -0.012 |
ilda | -0.011 |
pack | -0.011 |
Token | 'll |
Token ID | 1183 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
ge | +0.030 |
igsaw | +0.029 |
chie | +0.027 |
ilda | +0.027 |
pack | +0.025 |
Neg logit contributions | |
Leo | -0.015 |
Rex | -0.015 |
Kai | -0.015 |
icks | -0.014 |
named | -0.014 |
Token | save |
Token ID | 3613 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
Leo | +0.021 |
Kai | +0.021 |
Rex | +0.021 |
icks | +0.020 |
aw | +0.020 |
Neg logit contributions | |
ge | -0.022 |
igsaw | -0.020 |
chie | -0.019 |
ilda | -0.018 |
pack | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -6.76e-03 |
Pos logit contributions | |
Kai | +0.004 |
Leo | +0.003 |
Rex | +0.003 |
icks | +0.003 |
aw | +0.003 |
Neg logit contributions | |
ge | -0.006 |
igsaw | -0.005 |
chie | -0.005 |
ilda | -0.005 |
pack | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
Leo | +0.009 |
Rex | +0.009 |
icks | +0.009 |
Kai | +0.008 |
named | +0.008 |
Neg logit contributions | |
ge | -0.015 |
igsaw | -0.014 |
chie | -0.014 |
ilda | -0.013 |
ini | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
Leo | +0.011 |
Rex | +0.011 |
Kai | +0.011 |
icks | +0.011 |
aw | +0.011 |
Neg logit contributions | |
ge | -0.018 |
igsaw | -0.016 |
chie | -0.016 |
ilda | -0.015 |
pack | -0.014 |
Token | used |
Token ID | 973 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
Kai | +0.029 |
Leo | +0.029 |
Rex | +0.028 |
icks | +0.028 |
aw | +0.027 |
Neg logit contributions | |
ge | -0.041 |
igsaw | -0.038 |
chie | -0.037 |
ilda | -0.036 |
pack | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
Kai | +0.028 |
Leo | +0.027 |
Rex | +0.027 |
aw | +0.027 |
icks | +0.027 |
Neg logit contributions | |
ge | -0.036 |
igsaw | -0.034 |
chie | -0.032 |
ilda | -0.031 |
pack | -0.029 |
Token | sword |
Token ID | 8429 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
aw | +0.036 |
Kai | +0.035 |
Dod | +0.033 |
icks | +0.033 |
Rover | +0.032 |
Neg logit contributions | |
ge | -0.047 |
igsaw | -0.046 |
chie | -0.044 |
ilda | -0.041 |
solution | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | +2.91e-04 |
Pos logit contributions | |
Kai | +0.196 |
Leo | +0.195 |
Rex | +0.194 |
icks | +0.191 |
aw | +0.190 |
Neg logit contributions | |
ge | -0.155 |
igsaw | -0.142 |
chie | -0.130 |
ilda | -0.126 |
pack | -0.117 |
Token | cut |
Token ID | 2005 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
ge | +0.000 |
igsaw | +0.000 |
chie | +0.000 |
ilda | +0.000 |
pack | +0.000 |
Neg logit contributions | |
Kai | -0.001 |
Leo | -0.001 |
Rex | -0.001 |
icks | -0.001 |
aw | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
Kai | +0.040 |
Leo | +0.039 |
icks | +0.039 |
Rex | +0.039 |
named | +0.038 |
Neg logit contributions | |
ge | -0.053 |
igsaw | -0.050 |
chie | -0.046 |
ilda | -0.045 |
pack | -0.042 |
Token | shape |
Token ID | 5485 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
Kai | +0.019 |
aw | +0.018 |
Leo | +0.018 |
Rex | +0.018 |
icks | +0.018 |
Neg logit contributions | |
ge | -0.019 |
igsaw | -0.017 |
chie | -0.016 |
ilda | -0.016 |
pack | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
Kai | +0.057 |
Leo | +0.056 |
Rex | +0.056 |
named | +0.055 |
icks | +0.055 |
Neg logit contributions | |
ge | -0.076 |
igsaw | -0.071 |
chie | -0.066 |
ilda | -0.064 |
pack | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
icks | +0.005 |
aw | +0.005 |
slit | +0.005 |
ses | +0.005 |
ear | +0.005 |
Neg logit contributions | |
ge | -0.004 |
igsaw | -0.004 |
ilda | -0.004 |
re | -0.003 |
pack | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +7.54e-03 |
Pos logit contributions | |
ge | +0.017 |
igsaw | +0.014 |
ilda | +0.014 |
pack | +0.013 |
chie | +0.013 |
Neg logit contributions | |
ses | -0.017 |
ear | -0.017 |
sed | -0.017 |
icks | -0.017 |
goodbye | -0.016 |
Token | She |
Token ID | 3347 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
ge | +0.016 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.014 |
pack | +0.014 |
Neg logit contributions | |
Leo | -0.010 |
Kai | -0.010 |
Rex | -0.010 |
icks | -0.010 |
aw | -0.010 |
Token | throws |
Token ID | 12542 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
Kai | +0.055 |
Rex | +0.053 |
Dod | +0.053 |
Leo | +0.051 |
Rover | +0.051 |
Neg logit contributions | |
ge | -0.057 |
igsaw | -0.052 |
ilda | -0.050 |
arre | -0.049 |
pack | -0.049 |
Token | a |
Token ID | 257 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
sed | +0.057 |
ses | +0.054 |
Kai | +0.053 |
icks | +0.053 |
slit | +0.052 |
Neg logit contributions | |
ge | -0.031 |
igsaw | -0.026 |
chie | -0.024 |
pieces | -0.024 |
price | -0.022 |
Token | snowball |
Token ID | 46275 |
Feature activation | -9.89e-02 |
Pos logit contributions | |
Kai | +0.032 |
Leo | +0.032 |
Rex | +0.031 |
icks | +0.031 |
aw | +0.030 |
Neg logit contributions | |
ge | -0.038 |
igsaw | -0.035 |
chie | -0.033 |
ilda | -0.030 |
pack | -0.029 |
Token | at |
Token ID | 379 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Kai | +0.190 |
Dod | +0.182 |
marsh | +0.180 |
Rover | +0.178 |
Leo | +0.173 |
Neg logit contributions | |
ge | -0.150 |
chie | -0.119 |
igsaw | -0.118 |
pack | -0.105 |
re | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
icks | +0.040 |
aw | +0.039 |
Kai | +0.039 |
named | +0.038 |
slit | +0.038 |
Neg logit contributions | |
ge | -0.048 |
igsaw | -0.044 |
chie | -0.041 |
ilda | -0.041 |
pack | -0.038 |
Token | bird |
Token ID | 6512 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
icks | +0.006 |
Kai | +0.006 |
Leo | +0.006 |
Rex | +0.006 |
Rover | +0.006 |
Neg logit contributions | |
ge | -0.007 |
igsaw | -0.007 |
chie | -0.007 |
ilda | -0.006 |
ini | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.14e-03 |
Pos logit contributions | |
Kai | +0.084 |
Rover | +0.079 |
marsh | +0.079 |
ses | +0.077 |
sed | +0.077 |
Neg logit contributions | |
ge | -0.063 |
chie | -0.048 |
igsaw | -0.046 |
re | -0.044 |
y | -0.044 |
Token | The |
Token ID | 383 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
aver | +0.006 |
hawk | +0.006 |
aw | +0.005 |
slit | +0.005 |
named | +0.005 |
Neg logit contributions | |
igsaw | -0.004 |
ge | -0.004 |
care | -0.004 |
Gr | -0.004 |
Smith | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ge | +0.027 |
igsaw | +0.024 |
chie | +0.023 |
ilda | +0.022 |
pack | +0.021 |
Neg logit contributions | |
Kai | -0.023 |
icks | -0.022 |
Leo | -0.022 |
named | -0.022 |
Rex | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -7.70e-03 |
Pos logit contributions | |
Kai | +0.028 |
Leo | +0.028 |
Rex | +0.027 |
aw | +0.027 |
icks | +0.027 |
Neg logit contributions | |
ge | -0.034 |
igsaw | -0.031 |
chie | -0.029 |
ilda | -0.028 |
pack | -0.027 |
Token | He |
Token ID | 679 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
icks | +0.013 |
aw | +0.013 |
slit | +0.013 |
sed | +0.013 |
hawk | +0.013 |
Neg logit contributions | |
ge | -0.013 |
igsaw | -0.013 |
ilda | -0.012 |
pack | -0.011 |
chie | -0.010 |
Token | used |
Token ID | 973 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
icks | +0.054 |
Kai | +0.050 |
bye | +0.050 |
marsh | +0.049 |
goodbye | +0.049 |
Neg logit contributions | |
ge | -0.054 |
spe | -0.043 |
ilda | -0.043 |
hr | -0.041 |
pack | -0.041 |
Token | his |
Token ID | 465 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
aw | +0.021 |
Kai | +0.021 |
named | +0.020 |
bye | +0.020 |
icks | +0.020 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.022 |
chie | -0.020 |
ilda | -0.019 |
pack | -0.019 |
Token | sword |
Token ID | 8429 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
aw | +0.054 |
Dod | +0.049 |
Kai | +0.049 |
named | +0.048 |
Rex | +0.046 |
Neg logit contributions | |
ge | -0.057 |
igsaw | -0.056 |
chie | -0.052 |
solution | -0.049 |
project | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
Kai | +0.182 |
Leo | +0.179 |
Rex | +0.176 |
marsh | +0.175 |
Dod | +0.174 |
Neg logit contributions | |
ge | -0.170 |
igsaw | -0.148 |
chie | -0.138 |
ilda | -0.136 |
pack | -0.127 |
Token | his |
Token ID | 465 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
aw | +0.017 |
icks | +0.016 |
Kai | +0.016 |
Dod | +0.016 |
Rover | +0.015 |
Neg logit contributions | |
ge | -0.018 |
igsaw | -0.015 |
ilda | -0.015 |
spe | -0.014 |
chie | -0.014 |
Token | shield |
Token ID | 7614 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
aw | +0.038 |
Dod | +0.036 |
Kai | +0.035 |
named | +0.034 |
Rover | +0.033 |
Neg logit contributions | |
ge | -0.048 |
igsaw | -0.044 |
chie | -0.044 |
solution | -0.041 |
project | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +7.15e-04 |
Pos logit contributions | |
Kai | +0.108 |
Leo | +0.106 |
Dod | +0.104 |
Rex | +0.103 |
aw | +0.103 |
Neg logit contributions | |
ge | -0.096 |
igsaw | -0.078 |
chie | -0.075 |
ilda | -0.073 |
pack | -0.071 |
Token | made |
Token ID | 925 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
ge | +0.001 |
ilda | +0.001 |
igsaw | +0.001 |
spe | +0.001 |
solution | +0.001 |
Neg logit contributions | |
aw | -0.001 |
Kai | -0.001 |
icks | -0.001 |
Dod | -0.001 |
ses | -0.001 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
ge | +0.053 |
igsaw | +0.050 |
chie | +0.047 |
ilda | +0.046 |
pack | +0.043 |
Neg logit contributions | |
Kai | -0.038 |
Leo | -0.038 |
Rex | -0.037 |
icks | -0.037 |
aw | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ge | +0.051 |
igsaw | +0.048 |
chie | +0.044 |
ilda | +0.044 |
pack | +0.041 |
Neg logit contributions | |
Kai | -0.040 |
icks | -0.040 |
Leo | -0.039 |
Rex | -0.039 |
aw | -0.038 |
Token | share |
Token ID | 2648 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
ge | +0.028 |
igsaw | +0.026 |
chie | +0.025 |
ilda | +0.024 |
pack | +0.022 |
Neg logit contributions | |
Kai | -0.024 |
Rex | -0.024 |
Leo | -0.023 |
aw | -0.023 |
icks | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
Kai | +0.027 |
Leo | +0.027 |
Rex | +0.027 |
icks | +0.026 |
aw | +0.025 |
Neg logit contributions | |
ge | -0.039 |
igsaw | -0.036 |
chie | -0.034 |
ilda | -0.033 |
pack | -0.031 |
Token | showed |
Token ID | 3751 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ge | +0.026 |
igsaw | +0.024 |
chie | +0.023 |
ilda | +0.022 |
pack | +0.021 |
Neg logit contributions | |
Leo | -0.020 |
Kai | -0.020 |
Rex | -0.020 |
icks | -0.019 |
aw | -0.019 |
Token | bear |
Token ID | 6842 |
Feature activation | -9.82e-02 |
Pos logit contributions | |
ge | +0.042 |
igsaw | +0.040 |
chie | +0.038 |
ilda | +0.038 |
ic | +0.035 |
Neg logit contributions | |
icks | -0.025 |
ses | -0.024 |
Kai | -0.024 |
Leo | -0.024 |
slit | -0.024 |
Token | all |
Token ID | 477 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
Kai | +0.140 |
Leo | +0.139 |
Rex | +0.137 |
icks | +0.137 |
aw | +0.133 |
Neg logit contributions | |
ge | -0.205 |
igsaw | -0.193 |
chie | -0.182 |
ilda | -0.176 |
pack | -0.167 |
Token | about |
Token ID | 546 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
ge | +0.075 |
igsaw | +0.071 |
chie | +0.069 |
ilda | +0.066 |
pack | +0.063 |
Neg logit contributions | |
Leo | -0.050 |
Rex | -0.049 |
Kai | -0.048 |
icks | -0.048 |
aw | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
ge | +0.042 |
igsaw | +0.039 |
chie | +0.037 |
ilda | +0.036 |
pack | +0.034 |
Neg logit contributions | |
Kai | -0.029 |
Leo | -0.028 |
Rex | -0.028 |
icks | -0.028 |
aw | -0.028 |
Token | different |
Token ID | 1180 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
ge | +0.051 |
igsaw | +0.047 |
chie | +0.044 |
ilda | +0.043 |
pack | +0.041 |
Neg logit contributions | |
Leo | -0.037 |
Rex | -0.036 |
Kai | -0.035 |
ear | -0.034 |
icks | -0.034 |
Token | kinds |
Token ID | 6982 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
ge | +0.154 |
igsaw | +0.143 |
ilda | +0.138 |
chie | +0.133 |
pack | +0.130 |
Neg logit contributions | |
Leo | -0.111 |
aw | -0.105 |
ear | -0.105 |
Rex | -0.104 |
icks | -0.103 |
Token | made |
Token ID | 925 |
Feature activation | +9.02e-03 |
Pos logit contributions | |
ge | +0.018 |
any | +0.015 |
chie | +0.014 |
ilda | +0.014 |
re | +0.014 |
Neg logit contributions | |
icks | -0.019 |
ses | -0.019 |
Kai | -0.019 |
aw | -0.019 |
sed | -0.018 |
Token | snow |
Token ID | 6729 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.016 |
chie | +0.016 |
ic | +0.016 |
pack | +0.016 |
Neg logit contributions | |
ses | -0.012 |
Kai | -0.012 |
icks | -0.012 |
sed | -0.012 |
named | -0.012 |
Token | men |
Token ID | 3653 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
Kai | +0.060 |
Leo | +0.059 |
icks | +0.059 |
named | +0.059 |
Rex | +0.058 |
Neg logit contributions | |
ge | -0.075 |
igsaw | -0.067 |
chie | -0.065 |
ilda | -0.062 |
pack | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +8.20e-05 |
Pos logit contributions | |
Kai | +0.030 |
Leo | +0.029 |
Rex | +0.029 |
icks | +0.028 |
aw | +0.028 |
Neg logit contributions | |
ge | -0.046 |
igsaw | -0.042 |
chie | -0.040 |
ilda | -0.039 |
pack | -0.039 |
Token | had |
Token ID | 550 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
ge | +0.000 |
any | +0.000 |
pack | +0.000 |
re | +0.000 |
work | +0.000 |
Neg logit contributions | |
icks | -0.000 |
aw | -0.000 |
ses | -0.000 |
Kai | -0.000 |
agged | -0.000 |
Token | snowball |
Token ID | 46275 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
ge | +0.007 |
igsaw | +0.006 |
chie | +0.006 |
pack | +0.006 |
re | +0.006 |
Neg logit contributions | |
Kai | -0.007 |
icks | -0.007 |
ses | -0.007 |
ear | -0.007 |
bye | -0.007 |
Token | fights |
Token ID | 11418 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
Kai | +0.146 |
ear | +0.145 |
Leo | +0.141 |
Rover | +0.140 |
hawk | +0.137 |
Neg logit contributions | |
ge | -0.192 |
igsaw | -0.170 |
re | -0.164 |
chie | -0.157 |
ilda | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
Kai | +0.031 |
ses | +0.030 |
icks | +0.030 |
sed | +0.030 |
bye | +0.030 |
Neg logit contributions | |
ge | -0.020 |
igsaw | -0.015 |
pack | -0.014 |
solution | -0.014 |
spe | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
icks | +0.015 |
aw | +0.015 |
hawk | +0.014 |
Kai | +0.014 |
slit | +0.014 |
Neg logit contributions | |
ge | -0.012 |
igsaw | -0.011 |
ilda | -0.010 |
any | -0.010 |
re | -0.010 |
Token | used |
Token ID | 973 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
ge | +0.017 |
any | +0.013 |
re | +0.013 |
ilda | +0.013 |
chie | +0.013 |
Neg logit contributions | |
icks | -0.019 |
aw | -0.019 |
Kai | -0.019 |
ses | -0.019 |
bye | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | -8.03e-03 |
Pos logit contributions | |
aw | +0.017 |
bye | +0.017 |
Kai | +0.017 |
icks | +0.016 |
ses | +0.016 |
Neg logit contributions | |
ge | -0.017 |
igsaw | -0.015 |
chie | -0.014 |
pack | -0.014 |
solution | -0.013 |
Token | use |
Token ID | 779 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
Kai | +0.032 |
aw | +0.032 |
Leo | +0.031 |
Rex | +0.031 |
icks | +0.031 |
Neg logit contributions | |
ge | -0.032 |
igsaw | -0.030 |
chie | -0.028 |
ilda | -0.026 |
pack | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
Kai | +0.032 |
aw | +0.032 |
bye | +0.032 |
Dod | +0.031 |
named | +0.031 |
Neg logit contributions | |
ge | -0.036 |
igsaw | -0.033 |
chie | -0.030 |
pack | -0.028 |
ilda | -0.028 |
Token | stick |
Token ID | 4859 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
Kai | +0.022 |
Leo | +0.022 |
Rex | +0.022 |
aw | +0.021 |
icks | +0.021 |
Neg logit contributions | |
ge | -0.028 |
igsaw | -0.027 |
chie | -0.025 |
ilda | -0.024 |
pack | -0.023 |
Token | as |
Token ID | 355 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
Kai | +0.083 |
Leo | +0.082 |
Rex | +0.081 |
icks | +0.079 |
aw | +0.079 |
Neg logit contributions | |
ge | -0.078 |
igsaw | -0.071 |
chie | -0.066 |
ilda | -0.063 |
pack | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
Kai | +0.040 |
aw | +0.039 |
ear | +0.039 |
icks | +0.039 |
Dod | +0.038 |
Neg logit contributions | |
ge | -0.046 |
igsaw | -0.042 |
pack | -0.037 |
chie | -0.037 |
spe | -0.036 |
Token | sword |
Token ID | 8429 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
Kai | +0.067 |
Leo | +0.067 |
Rex | +0.066 |
aw | +0.065 |
icks | +0.065 |
Neg logit contributions | |
ge | -0.075 |
igsaw | -0.072 |
chie | -0.066 |
ilda | -0.061 |
pack | -0.059 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Kai | +0.155 |
Leo | +0.153 |
Dod | +0.150 |
Rex | +0.149 |
marsh | +0.148 |
Neg logit contributions | |
ge | -0.188 |
igsaw | -0.156 |
chie | -0.152 |
ilda | -0.150 |
re | -0.145 |
Token | a |
Token ID | 257 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
aw | +0.035 |
icks | +0.034 |
Kai | +0.034 |
Dod | +0.033 |
bye | +0.032 |
Neg logit contributions | |
ge | -0.038 |
igsaw | -0.033 |
chie | -0.032 |
pack | -0.030 |
hr | -0.029 |
Token | fl |
Token ID | 781 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
Kai | +0.062 |
icks | +0.061 |
Leo | +0.061 |
aw | +0.061 |
Rex | +0.060 |
Neg logit contributions | |
ge | -0.073 |
igsaw | -0.071 |
chie | -0.066 |
ilda | -0.060 |
solution | -0.059 |
Token | ute |
Token ID | 1133 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
Leo | +0.055 |
Kai | +0.055 |
Rex | +0.054 |
marsh | +0.053 |
named | +0.053 |
Neg logit contributions | |
ge | -0.052 |
igsaw | -0.049 |
chie | -0.048 |
pack | -0.041 |
ilda | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
Kai | +0.100 |
Dod | +0.099 |
Leo | +0.097 |
aw | +0.094 |
Rover | +0.094 |
Neg logit contributions | |
ge | -0.123 |
igsaw | -0.109 |
chie | -0.105 |
ilda | -0.100 |
pack | -0.097 |
Token | together |
Token ID | 1978 |
Feature activation | +8.97e-03 |
Pos logit contributions | |
icks | +0.040 |
Kai | +0.039 |
ses | +0.039 |
named | +0.038 |
Rex | +0.037 |
Neg logit contributions | |
ge | -0.045 |
igsaw | -0.041 |
chie | -0.040 |
ilda | -0.037 |
spe | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
ge | +0.017 |
igsaw | +0.015 |
chie | +0.014 |
ilda | +0.014 |
spe | +0.013 |
Neg logit contributions | |
Kai | -0.015 |
icks | -0.015 |
Rex | -0.015 |
Leo | -0.014 |
aw | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
icks | +0.024 |
aw | +0.023 |
Kai | +0.023 |
ses | +0.023 |
slit | +0.022 |
Neg logit contributions | |
igsaw | -0.032 |
ge | -0.031 |
ilda | -0.028 |
chie | -0.028 |
very | -0.026 |
Token | roared |
Token ID | 45615 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
icks | +0.015 |
Kai | +0.014 |
ses | +0.014 |
bye | +0.013 |
Rex | +0.013 |
Neg logit contributions | |
ge | -0.017 |
chie | -0.015 |
spe | -0.014 |
ilda | -0.014 |
igsaw | -0.014 |
Token | as |
Token ID | 355 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
icks | +0.042 |
Kai | +0.041 |
ses | +0.040 |
marsh | +0.040 |
named | +0.039 |
Neg logit contributions | |
ge | -0.046 |
igsaw | -0.041 |
chie | -0.040 |
ilda | -0.037 |
spe | -0.036 |
Token | loud |
Token ID | 7812 |
Feature activation | -9.61e-02 |
Pos logit contributions | |
icks | +0.047 |
ses | +0.043 |
aw | +0.043 |
Kai | +0.042 |
sed | +0.042 |
Neg logit contributions | |
ge | -0.058 |
igsaw | -0.054 |
chie | -0.051 |
ilda | -0.050 |
spe | -0.049 |
Token | as |
Token ID | 355 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
icks | +0.179 |
ses | +0.162 |
ear | +0.161 |
Dod | +0.160 |
Kai | +0.160 |
Neg logit contributions | |
ge | -0.152 |
igsaw | -0.133 |
chie | -0.118 |
ilda | -0.115 |
hr | -0.111 |
Token | they |
Token ID | 484 |
Feature activation | +7.75e-03 |
Pos logit contributions | |
icks | +0.029 |
ses | +0.027 |
aw | +0.027 |
sed | +0.027 |
ear | +0.026 |
Neg logit contributions | |
ge | -0.032 |
igsaw | -0.030 |
chie | -0.027 |
ilda | -0.027 |
spe | -0.026 |
Token | could |
Token ID | 714 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
ge | +0.014 |
chie | +0.012 |
re | +0.011 |
spe | +0.011 |
ilda | +0.011 |
Neg logit contributions | |
icks | -0.013 |
ses | -0.012 |
Kai | -0.012 |
bye | -0.012 |
marsh | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
aw | +0.006 |
Kai | +0.006 |
Rex | +0.006 |
icks | +0.006 |
Leo | +0.006 |
Neg logit contributions | |
ge | -0.008 |
igsaw | -0.006 |
chie | -0.006 |
ilda | -0.006 |
pack | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -9.72e-03 |
Pos logit contributions | |
icks | +0.017 |
hawk | +0.016 |
bye | +0.016 |
aw | +0.016 |
slit | +0.016 |
Neg logit contributions | |
igsaw | -0.017 |
ge | -0.017 |
ilda | -0.015 |
chie | -0.015 |
Emmy | -0.014 |
Token | snow |
Token ID | 6729 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
Rex | +0.035 |
Leo | +0.035 |
Kai | +0.035 |
icks | +0.033 |
aw | +0.033 |
Neg logit contributions | |
ge | -0.045 |
igsaw | -0.042 |
chie | -0.039 |
ilda | -0.038 |
pack | -0.036 |
Token | man |
Token ID | 805 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
icks | +0.093 |
Kai | +0.092 |
aw | +0.091 |
Rover | +0.090 |
Leo | +0.090 |
Neg logit contributions | |
ge | -0.072 |
igsaw | -0.061 |
chie | -0.059 |
ic | -0.059 |
pack | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
Kai | +0.062 |
Leo | +0.061 |
Rex | +0.060 |
icks | +0.060 |
aw | +0.058 |
Neg logit contributions | |
ge | -0.084 |
igsaw | -0.078 |
chie | -0.073 |
ilda | -0.072 |
pack | -0.069 |
Token | had |
Token ID | 550 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
icks | +0.019 |
aw | +0.018 |
Kai | +0.017 |
ses | +0.017 |
sed | +0.016 |
Neg logit contributions | |
ge | -0.021 |
ilda | -0.019 |
igsaw | -0.019 |
chie | -0.018 |
any | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
Kai | +0.004 |
icks | +0.003 |
ses | +0.003 |
Leo | +0.003 |
Rex | +0.003 |
Neg logit contributions | |
ge | -0.004 |
igsaw | -0.004 |
chie | -0.004 |
ilda | -0.004 |
pack | -0.003 |
Token | snowball |
Token ID | 46275 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
icks | +0.038 |
icked | +0.037 |
Leo | +0.036 |
Kai | +0.036 |
aw | +0.036 |
Neg logit contributions | |
igsaw | -0.038 |
ge | -0.037 |
solution | -0.035 |
mess | -0.033 |
chie | -0.033 |
Token | fight |
Token ID | 1907 |
Feature activation | +9.44e-03 |
Pos logit contributions | |
Kai | +0.148 |
Leo | +0.142 |
Rover | +0.141 |
Dod | +0.140 |
aw | +0.138 |
Neg logit contributions | |
ge | -0.180 |
igsaw | -0.163 |
chie | -0.151 |
re | -0.149 |
ilda | -0.147 |
Token | with |
Token ID | 351 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.017 |
chie | +0.015 |
ilda | +0.015 |
pack | +0.014 |
Neg logit contributions | |
Kai | -0.015 |
Leo | -0.015 |
icks | -0.015 |
Rex | -0.015 |
aw | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
ses | +0.021 |
sed | +0.021 |
icks | +0.021 |
bye | +0.021 |
Kai | +0.020 |
Neg logit contributions | |
ge | -0.018 |
igsaw | -0.017 |
ilda | -0.015 |
chie | -0.015 |
ic | -0.014 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
icks | +0.042 |
aw | +0.042 |
Kai | +0.041 |
Leo | +0.040 |
Rover | +0.040 |
Neg logit contributions | |
ge | -0.043 |
igsaw | -0.036 |
chie | -0.035 |
ilda | -0.035 |
re | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
Leo | +0.035 |
Kai | +0.035 |
Rex | +0.035 |
icks | +0.034 |
aw | +0.033 |
Neg logit contributions | |
ge | -0.048 |
igsaw | -0.046 |
chie | -0.043 |
ilda | -0.041 |
pack | -0.039 |
Token | snow |
Token ID | 6729 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
Kai | +0.031 |
Leo | +0.031 |
icks | +0.030 |
Rex | +0.030 |
aw | +0.029 |
Neg logit contributions | |
ge | -0.040 |
igsaw | -0.038 |
chie | -0.035 |
ilda | -0.034 |
pack | -0.033 |
Token | man |
Token ID | 805 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
icks | +0.081 |
Kai | +0.081 |
Rover | +0.078 |
Leo | +0.078 |
Rex | +0.076 |
Neg logit contributions | |
ge | -0.065 |
igsaw | -0.057 |
ic | -0.055 |
pack | -0.053 |
chie | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
Kai | +0.071 |
Leo | +0.070 |
Rex | +0.070 |
icks | +0.069 |
aw | +0.067 |
Neg logit contributions | |
ge | -0.083 |
igsaw | -0.076 |
chie | -0.071 |
ilda | -0.070 |
pack | -0.066 |
Token | had |
Token ID | 550 |
Feature activation | -5.72e-04 |
Pos logit contributions | |
icks | +0.019 |
aw | +0.019 |
Kai | +0.018 |
ses | +0.018 |
Leo | +0.017 |
Neg logit contributions | |
ge | -0.020 |
ilda | -0.018 |
any | -0.016 |
pack | -0.016 |
igsaw | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
Kai | +0.001 |
icks | +0.001 |
ses | +0.001 |
Leo | +0.001 |
Rex | +0.001 |
Neg logit contributions | |
ge | -0.001 |
igsaw | -0.001 |
chie | -0.001 |
ilda | -0.001 |
pack | -0.001 |
Token | snowball |
Token ID | 46275 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
icks | +0.031 |
icked | +0.030 |
Kai | +0.029 |
Leo | +0.029 |
aw | +0.029 |
Neg logit contributions | |
igsaw | -0.028 |
ge | -0.027 |
solution | -0.025 |
chie | -0.025 |
mess | -0.024 |
Token | fight |
Token ID | 1907 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
Kai | +0.160 |
Leo | +0.152 |
Rover | +0.152 |
Dod | +0.149 |
aw | +0.148 |
Neg logit contributions | |
ge | -0.166 |
igsaw | -0.149 |
mess | -0.136 |
re | -0.134 |
ilda | -0.131 |
Token | with |
Token ID | 351 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
ge | +0.020 |
igsaw | +0.019 |
chie | +0.017 |
ilda | +0.017 |
pack | +0.016 |
Neg logit contributions | |
Kai | -0.017 |
Leo | -0.017 |
Rex | -0.017 |
icks | -0.016 |
aw | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ses | +0.026 |
icks | +0.025 |
sed | +0.025 |
Kai | +0.025 |
bye | +0.025 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.022 |
ilda | -0.020 |
chie | -0.020 |
hr | -0.018 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
icks | +0.035 |
aw | +0.034 |
Leo | +0.033 |
Kai | +0.033 |
Rover | +0.033 |
Neg logit contributions | |
ge | -0.036 |
chie | -0.030 |
igsaw | -0.029 |
ilda | -0.029 |
re | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
Leo | +0.031 |
Rex | +0.031 |
Kai | +0.030 |
icks | +0.030 |
aw | +0.029 |
Neg logit contributions | |
ge | -0.044 |
igsaw | -0.042 |
chie | -0.039 |
ilda | -0.038 |
pack | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
Leo | +0.022 |
Kai | +0.022 |
Rex | +0.022 |
icks | +0.022 |
aw | +0.021 |
Neg logit contributions | |
ge | -0.030 |
igsaw | -0.028 |
chie | -0.026 |
ilda | -0.026 |
pack | -0.024 |
Token | They |
Token ID | 1119 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
icks | +0.005 |
slit | +0.005 |
aw | +0.005 |
marsh | +0.004 |
Kai | +0.004 |
Neg logit contributions | |
ge | -0.006 |
igsaw | -0.006 |
chie | -0.005 |
ilda | -0.005 |
spe | -0.005 |
Token | whist |
Token ID | 32262 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
icks | +0.014 |
Leo | +0.014 |
Kai | +0.014 |
Rex | +0.014 |
ses | +0.014 |
Neg logit contributions | |
ge | -0.016 |
chie | -0.013 |
ilda | -0.013 |
spe | -0.012 |
pack | -0.012 |
Token | led |
Token ID | 992 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
Kai | +0.017 |
Leo | +0.017 |
Rex | +0.017 |
icks | +0.016 |
named | +0.016 |
Neg logit contributions | |
ge | -0.023 |
igsaw | -0.021 |
chie | -0.020 |
ilda | -0.019 |
ic | -0.018 |
Token | as |
Token ID | 355 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
icks | +0.015 |
ses | +0.014 |
sed | +0.014 |
Kai | +0.014 |
Dod | +0.014 |
Neg logit contributions | |
ge | -0.010 |
spe | -0.008 |
chie | -0.007 |
upon | -0.007 |
igsaw | -0.007 |
Token | loud |
Token ID | 7812 |
Feature activation | -9.57e-02 |
Pos logit contributions | |
icks | +0.041 |
aw | +0.038 |
sed | +0.037 |
ses | +0.037 |
ear | +0.036 |
Neg logit contributions | |
ge | -0.036 |
spe | -0.031 |
igsaw | -0.030 |
ilda | -0.029 |
chie | -0.028 |
Token | as |
Token ID | 355 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
icks | +0.189 |
Dod | +0.176 |
ses | +0.176 |
Leo | +0.173 |
Kai | +0.172 |
Neg logit contributions | |
ge | -0.138 |
igsaw | -0.104 |
ilda | -0.097 |
chie | -0.097 |
hr | -0.094 |
Token | they |
Token ID | 484 |
Feature activation | +3.68e-03 |
Pos logit contributions | |
icks | +0.020 |
ses | +0.019 |
aw | +0.019 |
sed | +0.018 |
ear | +0.018 |
Neg logit contributions | |
ge | -0.017 |
igsaw | -0.014 |
ilda | -0.014 |
spe | -0.014 |
chie | -0.013 |
Token | could |
Token ID | 714 |
Feature activation | +4.88e-04 |
Pos logit contributions | |
ge | +0.007 |
chie | +0.006 |
re | +0.006 |
spe | +0.005 |
ilda | +0.005 |
Neg logit contributions | |
icks | -0.006 |
Kai | -0.006 |
ses | -0.006 |
Leo | -0.006 |
Rex | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
ge | +0.001 |
chie | +0.001 |
igsaw | +0.001 |
ilda | +0.001 |
re | +0.001 |
Neg logit contributions | |
aw | -0.001 |
Kai | -0.001 |
Leo | -0.001 |
Rex | -0.001 |
icks | -0.001 |
Token | making |
Token ID | 1642 |
Feature activation | +1.21e-04 |
Pos logit contributions | |
ge | +0.002 |
igsaw | +0.002 |
chie | +0.002 |
ilda | +0.002 |
hr | +0.002 |
Neg logit contributions | |
icks | -0.002 |
Kai | -0.002 |
aw | -0.002 |
Leo | -0.002 |
Rex | -0.002 |
Token | snow |
Token ID | 6729 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
ge | +0.015 |
igsaw | +0.014 |
chie | +0.014 |
ilda | +0.013 |
pack | +0.013 |
Neg logit contributions | |
Leo | -0.006 |
Kai | -0.006 |
Rex | -0.006 |
icks | -0.006 |
aw | -0.006 |
Token | man |
Token ID | 805 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
Kai | +0.053 |
Leo | +0.052 |
Rex | +0.052 |
icks | +0.051 |
aw | +0.051 |
Neg logit contributions | |
ge | -0.058 |
igsaw | -0.054 |
chie | -0.050 |
ilda | -0.049 |
pack | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | +6.05e-04 |
Pos logit contributions | |
named | +0.041 |
Leo | +0.040 |
Rex | +0.040 |
icks | +0.036 |
Kai | +0.036 |
Neg logit contributions | |
ge | -0.076 |
igsaw | -0.075 |
chie | -0.073 |
ilda | -0.069 |
spe | -0.065 |
Token | have |
Token ID | 423 |
Feature activation | +4.62e-03 |
Pos logit contributions | |
ge | +0.001 |
igsaw | +0.001 |
chie | +0.001 |
ilda | +0.001 |
pack | +0.001 |
Neg logit contributions | |
aw | -0.001 |
icks | -0.001 |
Kai | -0.001 |
Leo | -0.001 |
ses | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -8.52e-03 |
Pos logit contributions | |
ge | +0.008 |
igsaw | +0.008 |
chie | +0.008 |
pack | +0.007 |
ilda | +0.007 |
Neg logit contributions | |
Kai | -0.007 |
icks | -0.007 |
ses | -0.007 |
bye | -0.007 |
Leo | -0.007 |
Token | snowball |
Token ID | 46275 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
aw | +0.013 |
icks | +0.013 |
Kai | +0.013 |
Leo | +0.012 |
icked | +0.012 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.016 |
solution | -0.014 |
pack | -0.014 |
project | -0.014 |
Token | fight |
Token ID | 1907 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
Kai | +0.165 |
aw | +0.160 |
Leo | +0.159 |
Rover | +0.158 |
Dod | +0.156 |
Neg logit contributions | |
ge | -0.164 |
igsaw | -0.149 |
chie | -0.133 |
ilda | -0.129 |
pack | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | -5.80e-04 |
Pos logit contributions | |
ge | +0.026 |
igsaw | +0.024 |
chie | +0.022 |
ilda | +0.021 |
pack | +0.021 |
Neg logit contributions | |
Kai | -0.021 |
Leo | -0.021 |
Rex | -0.020 |
icks | -0.020 |
aw | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
Leo | +0.001 |
Rex | +0.001 |
Kai | +0.001 |
icks | +0.001 |
named | +0.001 |
Neg logit contributions | |
ge | -0.001 |
igsaw | -0.001 |
chie | -0.001 |
ilda | -0.001 |
pack | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.010 |
chie | +0.009 |
ilda | +0.009 |
ini | +0.009 |
Neg logit contributions | |
Leo | -0.006 |
Rex | -0.006 |
Kai | -0.006 |
named | -0.006 |
icks | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
bye | +0.010 |
icks | +0.009 |
sed | +0.009 |
named | +0.009 |
Kai | +0.009 |
Neg logit contributions | |
ge | -0.008 |
chie | -0.007 |
igsaw | -0.006 |
pieces | -0.006 |
pack | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ge | +0.094 |
igsaw | +0.081 |
chie | +0.081 |
ilda | +0.079 |
spe | +0.074 |
Neg logit contributions | |
icks | -0.087 |
Kai | -0.086 |
Leo | -0.085 |
Rex | -0.085 |
ses | -0.083 |
Token | brave |
Token ID | 14802 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
Kai | +0.021 |
Leo | +0.020 |
icks | +0.020 |
Rex | +0.020 |
aw | +0.020 |
Neg logit contributions | |
ge | -0.020 |
chie | -0.018 |
igsaw | -0.017 |
ilda | -0.016 |
pack | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
Leo | +0.018 |
Kai | +0.018 |
Rex | +0.018 |
icks | +0.017 |
aw | +0.017 |
Neg logit contributions | |
ge | -0.034 |
igsaw | -0.032 |
chie | -0.031 |
ilda | -0.030 |
pack | -0.029 |
Token | used |
Token ID | 973 |
Feature activation | -6.46e-04 |
Pos logit contributions | |
ge | +0.014 |
chie | +0.013 |
igsaw | +0.013 |
ilda | +0.012 |
spe | +0.012 |
Neg logit contributions | |
icks | -0.011 |
Kai | -0.010 |
ses | -0.010 |
Leo | -0.010 |
marsh | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
aw | +0.001 |
Kai | +0.001 |
ses | +0.001 |
icks | +0.001 |
bye | +0.001 |
Neg logit contributions | |
ge | -0.001 |
igsaw | -0.001 |
chie | -0.001 |
ilda | -0.001 |
pack | -0.001 |
Token | sword |
Token ID | 8429 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
aw | +0.043 |
Kai | +0.040 |
icks | +0.039 |
Leo | +0.038 |
Rex | +0.038 |
Neg logit contributions | |
igsaw | -0.041 |
ge | -0.040 |
chie | -0.038 |
solution | -0.035 |
ilda | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
Kai | +0.185 |
Leo | +0.184 |
Rex | +0.183 |
icks | +0.180 |
aw | +0.179 |
Neg logit contributions | |
ge | -0.152 |
igsaw | -0.137 |
chie | -0.128 |
ilda | -0.122 |
pack | -0.113 |
Token | scare |
Token ID | 19437 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
ge | +0.014 |
igsaw | +0.012 |
chie | +0.012 |
pack | +0.011 |
ilda | +0.011 |
Neg logit contributions | |
aw | -0.012 |
icks | -0.012 |
Kai | -0.011 |
Leo | -0.011 |
Rex | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
icks | +0.037 |
ses | +0.036 |
Kai | +0.036 |
sed | +0.036 |
Leo | +0.035 |
Neg logit contributions | |
ge | -0.048 |
igsaw | -0.044 |
chie | -0.043 |
ilda | -0.041 |
pack | -0.038 |
Token | ogre |
Token ID | 47656 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
ge | +0.021 |
igsaw | +0.020 |
chie | +0.019 |
ilda | +0.019 |
ini | +0.018 |
Neg logit contributions | |
icks | -0.015 |
Kai | -0.015 |
Leo | -0.015 |
Rex | -0.014 |
aw | -0.014 |
Token | away |
Token ID | 1497 |
Feature activation | +3.29e-04 |
Pos logit contributions | |
Leo | +0.022 |
Rex | +0.022 |
Kai | +0.021 |
icks | +0.021 |
named | +0.021 |
Neg logit contributions | |
ge | -0.028 |
igsaw | -0.027 |
chie | -0.025 |
ilda | -0.025 |
ini | -0.023 |
Token | man |
Token ID | 805 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
Kai | +0.081 |
icks | +0.080 |
Leo | +0.078 |
Rover | +0.078 |
aw | +0.077 |
Neg logit contributions | |
ge | -0.073 |
igsaw | -0.065 |
chie | -0.060 |
pack | -0.059 |
ic | -0.059 |
Token | together |
Token ID | 1978 |
Feature activation | +6.12e-03 |
Pos logit contributions | |
Kai | +0.055 |
Leo | +0.054 |
Rex | +0.053 |
icks | +0.053 |
aw | +0.051 |
Neg logit contributions | |
ge | -0.080 |
igsaw | -0.074 |
chie | -0.069 |
ilda | -0.068 |
pack | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -6.66e-03 |
Pos logit contributions | |
ge | +0.011 |
igsaw | +0.009 |
pack | +0.008 |
ilda | +0.008 |
re | +0.008 |
Neg logit contributions | |
Kai | -0.011 |
bye | -0.011 |
Rex | -0.011 |
ses | -0.011 |
icks | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -6.22e-04 |
Pos logit contributions | |
icks | +0.011 |
aw | +0.010 |
Kai | +0.010 |
ses | +0.010 |
Leo | +0.009 |
Neg logit contributions | |
ge | -0.012 |
igsaw | -0.011 |
ilda | -0.011 |
spe | -0.010 |
pack | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
Kai | +0.001 |
Leo | +0.001 |
Rex | +0.001 |
icks | +0.001 |
named | +0.001 |
Neg logit contributions | |
ge | -0.001 |
igsaw | -0.001 |
chie | -0.001 |
ilda | -0.001 |
pack | -0.001 |
Token | snowball |
Token ID | 46275 |
Feature activation | -9.45e-02 |
Pos logit contributions | |
icks | +0.043 |
icked | +0.042 |
Kai | +0.041 |
aw | +0.041 |
Leo | +0.041 |
Neg logit contributions | |
igsaw | -0.032 |
ge | -0.032 |
solution | -0.028 |
chie | -0.027 |
ilda | -0.026 |
Token | fight |
Token ID | 1907 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
Kai | +0.156 |
Leo | +0.150 |
Rover | +0.147 |
Dod | +0.146 |
aw | +0.145 |
Neg logit contributions | |
ge | -0.173 |
igsaw | -0.158 |
chie | -0.144 |
ilda | -0.139 |
re | -0.139 |
Token | . |
Token ID | 13 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
ge | +0.021 |
igsaw | +0.019 |
chie | +0.018 |
ilda | +0.018 |
pack | +0.017 |
Neg logit contributions | |
Kai | -0.018 |
Leo | -0.017 |
icks | -0.017 |
Rex | -0.017 |
aw | -0.017 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.87e-03 |
Pos logit contributions | |
aw | +0.012 |
icks | +0.012 |
Kai | +0.011 |
slit | +0.011 |
ear | +0.011 |
Neg logit contributions | |
igsaw | -0.018 |
ge | -0.017 |
ilda | -0.017 |
very | -0.015 |
Emmy | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | -2.66e-03 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.016 |
ilda | +0.016 |
chie | +0.016 |
pack | +0.015 |
Neg logit contributions | |
Kai | -0.017 |
icks | -0.016 |
Leo | -0.016 |
Rex | -0.016 |
aw | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ses | +0.005 |
marsh | +0.004 |
Kai | +0.004 |
aw | +0.004 |
Rex | +0.004 |
Neg logit contributions | |
ge | -0.004 |
igsaw | -0.004 |
chie | -0.004 |
ilda | -0.004 |
re | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +4.85e-03 |
Pos logit contributions | |
ge | +0.016 |
igsaw | +0.015 |
chie | +0.014 |
ilda | +0.013 |
pack | +0.013 |
Neg logit contributions | |
ses | -0.015 |
Kai | -0.015 |
sed | -0.015 |
goodbye | -0.015 |
aw | -0.015 |
Token | He |
Token ID | 1544 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
ge | +0.009 |
igsaw | +0.009 |
chie | +0.008 |
ilda | +0.008 |
pack | +0.007 |
Neg logit contributions | |
Kai | -0.008 |
Leo | -0.008 |
Rex | -0.008 |
icks | -0.008 |
aw | -0.008 |
Token | picked |
Token ID | 6497 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
Kai | +0.054 |
icks | +0.053 |
Leo | +0.053 |
marsh | +0.051 |
bye | +0.051 |
Neg logit contributions | |
ge | -0.063 |
ilda | -0.055 |
chie | -0.054 |
pack | -0.052 |
igsaw | -0.051 |
Token | up |
Token ID | 510 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
ge | +0.008 |
igsaw | +0.007 |
chie | +0.006 |
ilda | +0.006 |
ic | +0.005 |
Neg logit contributions | |
Kai | -0.016 |
named | -0.016 |
aw | -0.016 |
sed | -0.015 |
slit | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
ses | +0.083 |
sed | +0.082 |
icks | +0.082 |
Kai | +0.079 |
bye | +0.076 |
Neg logit contributions | |
ge | -0.066 |
igsaw | -0.065 |
chie | -0.058 |
spe | -0.051 |
ilda | -0.050 |
Token | snowball |
Token ID | 46275 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
Leo | +0.023 |
Kai | +0.023 |
Rex | +0.022 |
icks | +0.022 |
aw | +0.022 |
Neg logit contributions | |
ge | -0.028 |
igsaw | -0.026 |
chie | -0.025 |
ilda | -0.024 |
pack | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
Kai | +0.134 |
Leo | +0.132 |
Rex | +0.130 |
icks | +0.127 |
aw | +0.126 |
Neg logit contributions | |
ge | -0.201 |
igsaw | -0.187 |
chie | -0.176 |
ilda | -0.171 |
pack | -0.164 |
Token | threw |
Token ID | 9617 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
icks | +0.011 |
Kai | +0.011 |
ses | +0.011 |
ear | +0.011 |
aw | +0.010 |
Neg logit contributions | |
ge | -0.013 |
igsaw | -0.011 |
ilda | -0.011 |
pack | -0.011 |
hr | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
Kai | +0.032 |
named | +0.031 |
sed | +0.031 |
Dod | +0.030 |
bye | +0.030 |
Neg logit contributions | |
ge | -0.030 |
chie | -0.028 |
igsaw | -0.027 |
solution | -0.022 |
ic | -0.022 |
Token | at |
Token ID | 379 |
Feature activation | -9.61e-03 |
Pos logit contributions | |
Kai | +0.054 |
Dod | +0.051 |
Rover | +0.050 |
Leo | +0.050 |
marsh | +0.049 |
Neg logit contributions | |
ge | -0.052 |
igsaw | -0.044 |
chie | -0.043 |
pack | -0.039 |
spe | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -8.12e-03 |
Pos logit contributions | |
icks | +0.014 |
aw | +0.014 |
Kai | +0.014 |
bye | +0.014 |
goodbye | +0.013 |
Neg logit contributions | |
ge | -0.019 |
igsaw | -0.018 |
chie | -0.017 |
ilda | -0.016 |
pack | -0.015 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
Kai | +0.037 |
icks | +0.037 |
aw | +0.037 |
Leo | +0.036 |
Rex | +0.036 |
Neg logit contributions | |
igsaw | -0.048 |
ge | -0.047 |
chie | -0.046 |
ilda | -0.043 |
pack | -0.042 |
Token | armor |
Token ID | 8328 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
Leo | +0.036 |
Kai | +0.035 |
Rex | +0.035 |
icks | +0.034 |
Rover | +0.032 |
Neg logit contributions | |
igsaw | -0.055 |
ge | -0.055 |
chie | -0.051 |
ilda | -0.049 |
pack | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -7.54e-03 |
Pos logit contributions | |
Kai | +0.107 |
Leo | +0.105 |
Rex | +0.105 |
icks | +0.104 |
aw | +0.101 |
Neg logit contributions | |
ge | -0.169 |
igsaw | -0.155 |
chie | -0.146 |
ilda | -0.146 |
pack | -0.140 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
icks | +0.014 |
Kai | +0.013 |
Rex | +0.012 |
Leo | +0.012 |
ses | +0.012 |
Neg logit contributions | |
ge | -0.014 |
ilda | -0.011 |
pack | -0.011 |
igsaw | -0.011 |
chie | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
ses | +0.046 |
Kai | +0.046 |
sed | +0.045 |
icks | +0.044 |
Dod | +0.043 |
Neg logit contributions | |
ge | -0.044 |
igsaw | -0.043 |
chie | -0.037 |
ilda | -0.036 |
pack | -0.034 |
Token | sword |
Token ID | 8429 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
Kai | +0.039 |
aw | +0.039 |
icks | +0.038 |
Leo | +0.037 |
Rex | +0.036 |
Neg logit contributions | |
ge | -0.059 |
igsaw | -0.057 |
chie | -0.054 |
ilda | -0.052 |
pack | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Leo | +0.112 |
Kai | +0.111 |
Rex | +0.111 |
icks | +0.107 |
aw | +0.104 |
Neg logit contributions | |
ge | -0.222 |
igsaw | -0.211 |
chie | -0.201 |
ilda | -0.194 |
pack | -0.186 |
Token | headed |
Token ID | 9153 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
icks | +0.018 |
ses | +0.017 |
aw | +0.017 |
Kai | +0.017 |
Leo | +0.016 |
Neg logit contributions | |
ge | -0.020 |
ilda | -0.017 |
pack | -0.017 |
igsaw | -0.016 |
chie | -0.015 |
Token | out |
Token ID | 503 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
Kai | +0.011 |
Leo | +0.011 |
Rex | +0.011 |
aw | +0.011 |
icks | +0.010 |
Neg logit contributions | |
ge | -0.010 |
igsaw | -0.010 |
chie | -0.009 |
ilda | -0.008 |
pack | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -7.02e-03 |
Pos logit contributions | |
Leo | +0.044 |
Rex | +0.043 |
Kai | +0.043 |
icks | +0.042 |
named | +0.041 |
Neg logit contributions | |
ge | -0.047 |
igsaw | -0.045 |
chie | -0.042 |
ilda | -0.041 |
ini | -0.038 |
Token | As |
Token ID | 1081 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
Kai | +0.010 |
icks | +0.010 |
aw | +0.010 |
Leo | +0.010 |
Rex | +0.010 |
Neg logit contributions | |
ge | -0.014 |
igsaw | -0.014 |
ilda | -0.013 |
chie | -0.012 |
pack | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
Leo | +0.001 |
Kai | +0.001 |
Rex | +0.001 |
icks | +0.001 |
aw | +0.001 |
Neg logit contributions | |
ge | -0.002 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
pack | -0.002 |
Token | would |
Token ID | 561 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
aw | +0.029 |
Kai | +0.029 |
icks | +0.029 |
Leo | +0.028 |
bye | +0.028 |
Neg logit contributions | |
ge | -0.028 |
pack | -0.023 |
ilda | -0.023 |
chie | -0.022 |
spe | -0.022 |
Token | use |
Token ID | 779 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
aw | +0.086 |
Kai | +0.083 |
Rex | +0.079 |
Leo | +0.079 |
icks | +0.079 |
Neg logit contributions | |
ge | -0.084 |
chie | -0.073 |
igsaw | -0.072 |
pack | -0.071 |
ilda | -0.067 |
Token | his |
Token ID | 465 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
Kai | +0.017 |
aw | +0.017 |
Leo | +0.017 |
icks | +0.017 |
Dod | +0.017 |
Neg logit contributions | |
ge | -0.023 |
igsaw | -0.021 |
chie | -0.020 |
ilda | -0.019 |
pack | -0.018 |
Token | toy |
Token ID | 13373 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
aw | +0.039 |
Kai | +0.038 |
Leo | +0.036 |
icks | +0.036 |
Dod | +0.036 |
Neg logit contributions | |
igsaw | -0.040 |
ge | -0.040 |
chie | -0.039 |
ilda | -0.035 |
solution | -0.035 |
Token | sword |
Token ID | 8429 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
Kai | +0.093 |
Leo | +0.090 |
aw | +0.089 |
icks | +0.088 |
Dod | +0.087 |
Neg logit contributions | |
ge | -0.095 |
igsaw | -0.086 |
chie | -0.084 |
ilda | -0.079 |
pack | -0.078 |
Token | to |
Token ID | 284 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
Kai | +0.183 |
Leo | +0.183 |
Rex | +0.181 |
icks | +0.179 |
aw | +0.177 |
Neg logit contributions | |
ge | -0.149 |
igsaw | -0.135 |
chie | -0.125 |
ilda | -0.122 |
pack | -0.112 |
Token | fight |
Token ID | 1907 |
Feature activation | +5.70e-03 |
Pos logit contributions | |
ge | +0.011 |
igsaw | +0.010 |
chie | +0.009 |
pack | +0.009 |
ilda | +0.009 |
Neg logit contributions | |
aw | -0.013 |
Kai | -0.013 |
Leo | -0.012 |
icks | -0.012 |
Rex | -0.012 |
Token | off |
Token ID | 572 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ge | +0.012 |
igsaw | +0.011 |
chie | +0.011 |
ilda | +0.010 |
pack | +0.010 |
Neg logit contributions | |
Leo | -0.008 |
Rex | -0.008 |
Kai | -0.008 |
icks | -0.008 |
aw | -0.008 |
Token | imaginary |
Token ID | 26726 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
Kai | +0.019 |
icks | +0.019 |
Leo | +0.019 |
ses | +0.019 |
Rex | +0.019 |
Neg logit contributions | |
ge | -0.028 |
igsaw | -0.026 |
chie | -0.024 |
ilda | -0.024 |
pack | -0.022 |
Token | enemies |
Token ID | 5775 |
Feature activation | -4.55e-02 |
Pos logit contributions | |
Kai | +0.076 |
Leo | +0.075 |
Rex | +0.074 |
icks | +0.074 |
aw | +0.071 |
Neg logit contributions | |
ge | -0.097 |
igsaw | -0.090 |
chie | -0.086 |
ilda | -0.082 |
pack | -0.077 |
Token | but |
Token ID | 475 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
ge | +0.059 |
igsaw | +0.055 |
chie | +0.051 |
ilda | +0.051 |
spe | +0.047 |
Neg logit contributions | |
icks | -0.049 |
Kai | -0.049 |
Leo | -0.048 |
Rex | -0.048 |
aw | -0.047 |
Token | today |
Token ID | 1909 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ge | +0.032 |
igsaw | +0.030 |
chie | +0.029 |
ilda | +0.028 |
pack | +0.027 |
Neg logit contributions | |
Leo | -0.019 |
Kai | -0.019 |
Rex | -0.019 |
icks | -0.018 |
aw | -0.018 |
Token | they |
Token ID | 484 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
ge | +0.049 |
igsaw | +0.046 |
chie | +0.045 |
ilda | +0.042 |
pack | +0.041 |
Neg logit contributions | |
Rex | -0.022 |
Leo | -0.022 |
named | -0.021 |
aw | -0.021 |
Kai | -0.021 |
Token | were |
Token ID | 547 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ge | +0.077 |
igsaw | +0.072 |
chie | +0.068 |
ilda | +0.066 |
pack | +0.062 |
Neg logit contributions | |
Leo | -0.053 |
Kai | -0.053 |
Rex | -0.053 |
icks | -0.051 |
aw | -0.050 |
Token | qu |
Token ID | 627 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ge | +0.039 |
igsaw | +0.037 |
chie | +0.034 |
ilda | +0.033 |
pack | +0.031 |
Neg logit contributions | |
Leo | -0.030 |
Rex | -0.030 |
Kai | -0.029 |
named | -0.029 |
icks | -0.029 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ge | +0.061 |
igsaw | +0.048 |
ilda | +0.048 |
recipe | +0.045 |
fitting | +0.041 |
Neg logit contributions | |
aw | -0.096 |
aver | -0.079 |
icks | -0.078 |
named | -0.078 |
agged | -0.075 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
igsaw | +0.301 |
ge | +0.254 |
enny | +0.250 |
ress | +0.246 |
ilda | +0.245 |
Neg logit contributions | |
aw | -0.145 |
named | -0.110 |
marsh | -0.108 |
slit | -0.108 |
then | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
Kai | +0.002 |
Leo | +0.002 |
Rex | +0.002 |
icks | +0.002 |
ses | +0.002 |
Neg logit contributions | |
ge | -0.002 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
spe | -0.002 |
Token | Jenna |
Token ID | 45377 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
ge | +0.023 |
igsaw | +0.020 |
chie | +0.020 |
ilda | +0.019 |
pack | +0.018 |
Neg logit contributions | |
Leo | -0.012 |
Rex | -0.012 |
Kai | -0.011 |
named | -0.011 |
aw | -0.011 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ge | +0.121 |
igsaw | +0.115 |
chie | +0.108 |
ilda | +0.103 |
pack | +0.099 |
Neg logit contributions | |
Leo | -0.085 |
Kai | -0.084 |
Rex | -0.084 |
named | -0.082 |
aw | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.014 |
pack | +0.014 |
Neg logit contributions | |
Leo | -0.019 |
Rex | -0.019 |
Kai | -0.019 |
icks | -0.019 |
aw | -0.018 |
Token | It |
Token ID | 632 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
ge | +0.009 |
igsaw | +0.009 |
chie | +0.008 |
ilda | +0.008 |
pack | +0.008 |
Neg logit contributions | |
Kai | -0.006 |
Rex | -0.006 |
Leo | -0.006 |
icks | -0.006 |
aw | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.004 |
chie | +0.004 |
ilda | +0.004 |
pack | +0.003 |
Neg logit contributions | |
Leo | -0.004 |
Kai | -0.004 |
Rex | -0.004 |
icks | -0.004 |
aw | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
Kai | +0.004 |
icks | +0.004 |
Leo | +0.004 |
aw | +0.004 |
Rex | +0.004 |
Neg logit contributions | |
ge | -0.005 |
igsaw | -0.004 |
ilda | -0.004 |
chie | -0.004 |
pack | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ge | +0.012 |
igsaw | +0.012 |
chie | +0.011 |
ilda | +0.010 |
pack | +0.010 |
Neg logit contributions | |
Kai | -0.011 |
Leo | -0.011 |
Rex | -0.011 |
icks | -0.011 |
aw | -0.011 |
Token | j |
Token ID | 474 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
Kai | +0.018 |
icks | +0.018 |
Leo | +0.018 |
Rex | +0.017 |
aw | +0.017 |
Neg logit contributions | |
igsaw | -0.021 |
ge | -0.021 |
chie | -0.019 |
ilda | -0.018 |
pack | -0.017 |
Token | igsaw |
Token ID | 45636 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ge | +0.058 |
chie | +0.049 |
ilda | +0.046 |
igsaw | +0.045 |
pack | +0.045 |
Neg logit contributions | |
aw | -0.052 |
named | -0.051 |
bye | -0.050 |
Rex | -0.050 |
Leo | -0.050 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ge | +0.272 |
chie | +0.248 |
hr | +0.223 |
ptions | +0.212 |
ilda | +0.211 |
Neg logit contributions | |
named | -0.228 |
marsh | -0.224 |
thank | -0.216 |
goodbye | -0.212 |
Leo | -0.211 |
Token | and |
Token ID | 290 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ge | +0.048 |
igsaw | +0.044 |
chie | +0.043 |
ilda | +0.041 |
pack | +0.039 |
Neg logit contributions | |
Leo | -0.032 |
Rex | -0.032 |
Kai | -0.031 |
named | -0.031 |
aw | -0.031 |
Token | she |
Token ID | 673 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ge | +0.021 |
igsaw | +0.020 |
chie | +0.019 |
ilda | +0.018 |
pack | +0.017 |
Neg logit contributions | |
Kai | -0.017 |
Leo | -0.016 |
Rex | -0.016 |
icks | -0.016 |
aw | -0.016 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ge | +0.047 |
igsaw | +0.045 |
chie | +0.042 |
ilda | +0.041 |
pack | +0.039 |
Neg logit contributions | |
Leo | -0.030 |
Kai | -0.030 |
Rex | -0.030 |
icks | -0.029 |
aw | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
ge | +0.028 |
igsaw | +0.027 |
chie | +0.025 |
ini | +0.023 |
ilda | +0.023 |
Neg logit contributions | |
Rex | -0.025 |
Leo | -0.024 |
Kai | -0.024 |
named | -0.023 |
goodbye | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
icks | +0.018 |
Kai | +0.017 |
Rex | +0.017 |
Leo | +0.017 |
ses | +0.016 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.022 |
chie | -0.021 |
ilda | -0.020 |
pack | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
ge | +0.024 |
igsaw | +0.021 |
chie | +0.020 |
ilda | +0.020 |
pack | +0.019 |
Neg logit contributions | |
icks | -0.019 |
Kai | -0.018 |
Rex | -0.018 |
Leo | -0.018 |
ses | -0.018 |
Token | two |
Token ID | 734 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
icks | +0.026 |
ses | +0.024 |
bye | +0.024 |
sed | +0.024 |
Kai | +0.023 |
Neg logit contributions | |
ge | -0.025 |
igsaw | -0.024 |
chie | -0.023 |
ilda | -0.022 |
spe | -0.021 |
Token | birds |
Token ID | 10087 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ge | +0.067 |
igsaw | +0.063 |
chie | +0.059 |
ilda | +0.058 |
pack | +0.056 |
Neg logit contributions | |
Leo | -0.043 |
Kai | -0.043 |
Rex | -0.042 |
icks | -0.041 |
aw | -0.041 |
Token | qu |
Token ID | 627 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
Kai | +0.027 |
Leo | +0.027 |
Rex | +0.027 |
icks | +0.026 |
aw | +0.025 |
Neg logit contributions | |
ge | -0.037 |
igsaw | -0.033 |
chie | -0.032 |
ilda | -0.031 |
pack | -0.029 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ge | +0.077 |
igsaw | +0.070 |
ilda | +0.069 |
recipe | +0.060 |
spe | +0.059 |
Neg logit contributions | |
aw | -0.090 |
icks | -0.080 |
named | -0.072 |
icked | -0.071 |
Leo | -0.069 |
Token | ling |
Token ID | 1359 |
Feature activation | +8.91e-03 |
Pos logit contributions | |
igsaw | +0.304 |
enny | +0.260 |
ilda | +0.246 |
ge | +0.243 |
chie | +0.241 |
Neg logit contributions | |
aw | -0.170 |
slit | -0.151 |
icks | -0.146 |
horns | -0.144 |
marsh | -0.143 |
Token | ! |
Token ID | 0 |
Feature activation | +8.43e-03 |
Pos logit contributions | |
ge | +0.017 |
igsaw | +0.015 |
chie | +0.015 |
ilda | +0.013 |
spe | +0.013 |
Neg logit contributions | |
Kai | -0.015 |
Rex | -0.014 |
Leo | -0.014 |
icks | -0.014 |
ses | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
ge | +0.019 |
igsaw | +0.018 |
chie | +0.017 |
ilda | +0.017 |
pack | +0.016 |
Neg logit contributions | |
Kai | -0.010 |
icks | -0.010 |
Leo | -0.010 |
Rex | -0.010 |
aw | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
ge | +0.035 |
chie | +0.031 |
igsaw | +0.031 |
ilda | +0.029 |
spe | +0.028 |
Neg logit contributions | |
icks | -0.029 |
Rex | -0.029 |
Kai | -0.029 |
Leo | -0.029 |
ses | -0.028 |
Token | squ |
Token ID | 2809 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.009 |
chie | +0.009 |
ilda | +0.008 |
pack | +0.007 |
Neg logit contributions | |
Kai | -0.010 |
Rex | -0.010 |
Leo | -0.010 |
icks | -0.010 |
aw | -0.010 |
Token | lively |
Token ID | 29696 |
Feature activation | +2.41e-04 |
Pos logit contributions | |
ge | +0.008 |
igsaw | +0.008 |
chie | +0.007 |
ilda | +0.007 |
spe | +0.006 |
Neg logit contributions | |
icks | -0.009 |
Kai | -0.008 |
Leo | -0.008 |
aw | -0.008 |
Rex | -0.008 |
Token | sound |
Token ID | 2128 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
ge | +0.000 |
igsaw | +0.000 |
chie | +0.000 |
ilda | +0.000 |
pack | +0.000 |
Neg logit contributions | |
Leo | -0.000 |
Kai | -0.000 |
Rex | -0.000 |
icks | -0.000 |
aw | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
Kai | +0.037 |
Leo | +0.037 |
Rex | +0.036 |
icks | +0.036 |
ses | +0.035 |
Neg logit contributions | |
ge | -0.043 |
igsaw | -0.039 |
chie | -0.037 |
ilda | -0.036 |
pack | -0.033 |
Token | The |
Token ID | 383 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
Kai | +0.013 |
icks | +0.013 |
aw | +0.013 |
Leo | +0.013 |
bye | +0.013 |
Neg logit contributions | |
igsaw | -0.021 |
ge | -0.021 |
chie | -0.019 |
ilda | -0.018 |
pack | -0.017 |
Token | qu |
Token ID | 627 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
Leo | +0.039 |
Kai | +0.039 |
Rex | +0.038 |
icks | +0.038 |
aw | +0.037 |
Neg logit contributions | |
ge | -0.039 |
igsaw | -0.036 |
chie | -0.034 |
ilda | -0.032 |
pack | -0.030 |
Token | arre |
Token ID | 9624 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
ge | +0.080 |
igsaw | +0.068 |
ilda | +0.066 |
chie | +0.061 |
pack | +0.060 |
Neg logit contributions | |
aw | -0.062 |
icks | -0.055 |
Rex | -0.052 |
named | -0.052 |
marsh | -0.051 |
Token | ling |
Token ID | 1359 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
igsaw | +0.279 |
ge | +0.259 |
ilda | +0.233 |
pack | +0.222 |
chie | +0.221 |
Neg logit contributions | |
aw | -0.168 |
named | -0.152 |
marsh | -0.150 |
icks | -0.150 |
slit | -0.148 |
Token | stopped |
Token ID | 5025 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
ge | +0.019 |
igsaw | +0.018 |
chie | +0.017 |
ilda | +0.016 |
spe | +0.015 |
Neg logit contributions | |
Kai | -0.017 |
Leo | -0.017 |
Rex | -0.017 |
icks | -0.017 |
aw | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +8.62e-03 |
Pos logit contributions | |
ge | +0.019 |
igsaw | +0.018 |
chie | +0.016 |
ilda | +0.016 |
pack | +0.015 |
Neg logit contributions | |
Leo | -0.014 |
Rex | -0.014 |
Kai | -0.014 |
named | -0.014 |
icks | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
ge | +0.017 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.015 |
spe | +0.014 |
Neg logit contributions | |
icks | -0.013 |
Kai | -0.013 |
aw | -0.012 |
Leo | -0.012 |
Rex | -0.012 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
ge | +0.051 |
chie | +0.045 |
spe | +0.044 |
ilda | +0.044 |
igsaw | +0.042 |
Neg logit contributions | |
Kai | -0.048 |
icks | -0.047 |
ses | -0.047 |
Leo | -0.047 |
Rex | -0.046 |
Token | would |
Token ID | 561 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
ge | +0.022 |
igsaw | +0.021 |
chie | +0.020 |
ilda | +0.019 |
pack | +0.019 |
Neg logit contributions | |
Kai | -0.015 |
Leo | -0.015 |
Rex | -0.015 |
icks | -0.015 |
aw | -0.015 |
Token | take |
Token ID | 1011 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Leo | +0.067 |
icks | +0.065 |
named | +0.065 |
ear | +0.065 |
Kai | +0.065 |
Neg logit contributions | |
ge | -0.073 |
igsaw | -0.069 |
chie | -0.064 |
ilda | -0.062 |
ini | -0.059 |
Token | out |
Token ID | 503 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
Leo | +0.015 |
Rex | +0.015 |
Kai | +0.015 |
icks | +0.014 |
aw | +0.014 |
Neg logit contributions | |
ge | -0.026 |
igsaw | -0.024 |
chie | -0.023 |
ilda | -0.022 |
pack | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -3.69e-03 |
Pos logit contributions | |
Leo | +0.039 |
Rex | +0.038 |
icks | +0.036 |
named | +0.036 |
goodbye | +0.035 |
Neg logit contributions | |
ge | -0.091 |
igsaw | -0.084 |
chie | -0.083 |
ilda | -0.083 |
ini | -0.080 |
Token | j |
Token ID | 474 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
thank | +0.005 |
Leo | +0.005 |
goodbye | +0.005 |
marsh | +0.005 |
named | +0.005 |
Neg logit contributions | |
ge | -0.008 |
chie | -0.007 |
ic | -0.007 |
ini | -0.007 |
any | -0.007 |
Token | igsaw |
Token ID | 45636 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
ge | +0.021 |
chie | +0.018 |
ilda | +0.017 |
spe | +0.017 |
hr | +0.017 |
Neg logit contributions | |
aw | -0.018 |
icks | -0.018 |
bye | -0.018 |
named | -0.018 |
Rex | -0.018 |
Token | puzzle |
Token ID | 15027 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
ge | +0.235 |
chie | +0.223 |
hr | +0.201 |
shadow | +0.188 |
any | +0.181 |
Neg logit contributions | |
marsh | -0.190 |
Leo | -0.188 |
thank | -0.188 |
named | -0.187 |
goodbye | -0.182 |
Token | and |
Token ID | 290 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.009 |
chie | +0.009 |
ilda | +0.009 |
ini | +0.008 |
Neg logit contributions | |
Leo | -0.007 |
Rex | -0.007 |
named | -0.006 |
Kai | -0.006 |
icks | -0.006 |
Token | try |
Token ID | 1949 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.004 |
chie | +0.004 |
ilda | +0.003 |
ic | +0.003 |
Neg logit contributions | |
Leo | -0.004 |
Rex | -0.004 |
Kai | -0.004 |
named | -0.003 |
ear | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Leo | +0.018 |
Rex | +0.017 |
icks | +0.016 |
Kai | +0.016 |
aw | +0.016 |
Neg logit contributions | |
igsaw | -0.029 |
chie | -0.029 |
ge | -0.028 |
ini | -0.026 |
spe | -0.025 |
Token | solve |
Token ID | 8494 |
Feature activation | +7.94e-03 |
Pos logit contributions | |
igsaw | +0.029 |
ge | +0.027 |
ilda | +0.027 |
ini | +0.027 |
any | +0.026 |
Neg logit contributions | |
thank | -0.025 |
Leo | -0.023 |
ear | -0.023 |
named | -0.021 |
then | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
ge | +0.038 |
igsaw | +0.037 |
chie | +0.035 |
ilda | +0.034 |
ini | +0.033 |
Neg logit contributions | |
Rex | -0.021 |
Leo | -0.021 |
Kai | -0.021 |
aw | -0.021 |
marsh | -0.020 |
Token | Mama |
Token ID | 40084 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.004 |
chie | +0.004 |
ilda | +0.004 |
hr | +0.003 |
Neg logit contributions | |
icks | -0.002 |
Kai | -0.002 |
Rex | -0.002 |
Leo | -0.002 |
aw | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ge | +0.024 |
igsaw | +0.022 |
chie | +0.022 |
ilda | +0.021 |
pack | +0.020 |
Neg logit contributions | |
icks | -0.018 |
Kai | -0.018 |
Leo | -0.017 |
Rex | -0.017 |
ses | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -6.28e-03 |
Pos logit contributions | |
ge | +0.026 |
igsaw | +0.026 |
chie | +0.026 |
ilda | +0.024 |
re | +0.023 |
Neg logit contributions | |
ses | -0.028 |
Kai | -0.027 |
icks | -0.027 |
Rex | -0.026 |
aw | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -1.49e-03 |
Pos logit contributions | |
Leo | +0.011 |
Kai | +0.011 |
Rex | +0.011 |
icks | +0.011 |
aw | +0.011 |
Neg logit contributions | |
ge | -0.011 |
igsaw | -0.010 |
chie | -0.010 |
ilda | -0.009 |
pack | -0.009 |
Token | time |
Token ID | 640 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
Rex | +0.002 |
Leo | +0.002 |
Kai | +0.002 |
named | +0.002 |
icks | +0.002 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.003 |
chie | -0.003 |
ilda | -0.003 |
pack | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
ge | +0.082 |
igsaw | +0.077 |
chie | +0.071 |
ilda | +0.068 |
pack | +0.064 |
Neg logit contributions | |
Leo | -0.086 |
Kai | -0.086 |
Rex | -0.086 |
icks | -0.084 |
aw | -0.083 |
Token | go |
Token ID | 467 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
ge | +0.068 |
igsaw | +0.063 |
chie | +0.059 |
ilda | +0.057 |
pack | +0.056 |
Neg logit contributions | |
Leo | -0.056 |
aw | -0.055 |
icks | -0.055 |
Kai | -0.055 |
Rex | -0.054 |
Token | home |
Token ID | 1363 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ge | +0.005 |
igsaw | +0.005 |
chie | +0.005 |
ilda | +0.004 |
spe | +0.004 |
Neg logit contributions | |
Rex | -0.005 |
named | -0.005 |
Kai | -0.005 |
Leo | -0.005 |
goodbye | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
igsaw | +0.062 |
chie | +0.060 |
ge | +0.060 |
ini | +0.056 |
ic | +0.055 |
Neg logit contributions | |
Rex | -0.024 |
named | -0.024 |
Leo | -0.023 |
Kai | -0.023 |
goodbye | -0.023 |
Token | so |
Token ID | 523 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
ge | +0.046 |
igsaw | +0.041 |
chie | +0.039 |
ilda | +0.038 |
pack | +0.036 |
Neg logit contributions | |
icks | -0.044 |
Kai | -0.043 |
Leo | -0.043 |
aw | -0.042 |
Rex | -0.042 |
Token | came |
Token ID | 1625 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
Kai | +0.020 |
Leo | +0.020 |
icks | +0.019 |
Rex | +0.019 |
ear | +0.019 |
Neg logit contributions | |
ge | -0.027 |
igsaw | -0.025 |
chie | -0.024 |
ilda | -0.023 |
pack | -0.022 |
Token | out |
Token ID | 503 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
igsaw | +0.065 |
ge | +0.062 |
ilda | +0.057 |
chie | +0.055 |
pack | +0.053 |
Neg logit contributions | |
Rex | -0.041 |
Kai | -0.040 |
Leo | -0.040 |
icks | -0.038 |
aw | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | +9.70e-03 |
Pos logit contributions | |
Rex | +0.005 |
Leo | +0.004 |
Kai | +0.004 |
named | +0.004 |
icks | +0.004 |
Neg logit contributions | |
ge | -0.007 |
igsaw | -0.007 |
ilda | -0.006 |
chie | -0.006 |
pack | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
ge | +0.020 |
igsaw | +0.019 |
chie | +0.018 |
ilda | +0.017 |
pack | +0.016 |
Neg logit contributions | |
Kai | -0.014 |
Leo | -0.014 |
Rex | -0.014 |
icks | -0.014 |
aw | -0.014 |
Token | bath |
Token ID | 7837 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
ge | +0.046 |
igsaw | +0.042 |
chie | +0.040 |
ilda | +0.039 |
hr | +0.037 |
Neg logit contributions | |
marsh | -0.029 |
Rex | -0.028 |
named | -0.027 |
ear | -0.026 |
sorry | -0.026 |
Token | tub |
Token ID | 37995 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
ge | +0.074 |
igsaw | +0.066 |
chie | +0.060 |
ilda | +0.055 |
hr | +0.050 |
Neg logit contributions | |
Rex | -0.120 |
Leo | -0.117 |
named | -0.117 |
aw | -0.117 |
marsh | -0.117 |
Token | ! |
Token ID | 0 |
Feature activation | +3.36e-03 |
Pos logit contributions | |
ge | +0.109 |
igsaw | +0.104 |
chie | +0.097 |
ilda | +0.094 |
pack | +0.089 |
Neg logit contributions | |
Leo | -0.075 |
Rex | -0.075 |
Kai | -0.074 |
icks | -0.072 |
aw | -0.072 |
Token | |
Token ID | 220 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
ge | +0.007 |
igsaw | +0.006 |
chie | +0.006 |
ilda | +0.006 |
pack | +0.006 |
Neg logit contributions | |
Kai | -0.005 |
Rex | -0.005 |
Leo | -0.005 |
icks | -0.005 |
named | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
ge | +0.119 |
igsaw | +0.114 |
chie | +0.108 |
ilda | +0.103 |
spe | +0.099 |
Neg logit contributions | |
Rex | -0.052 |
Kai | -0.051 |
Leo | -0.050 |
icks | -0.050 |
aw | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ge | +0.055 |
igsaw | +0.052 |
chie | +0.049 |
ilda | +0.048 |
pack | +0.045 |
Neg logit contributions | |
Kai | -0.032 |
Leo | -0.031 |
Rex | -0.031 |
icks | -0.030 |
named | -0.030 |
Token | The |
Token ID | 464 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ge | +0.036 |
igsaw | +0.034 |
ilda | +0.031 |
chie | +0.030 |
pack | +0.028 |
Neg logit contributions | |
Kai | -0.035 |
Rex | -0.035 |
named | -0.035 |
Leo | -0.035 |
aw | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
ge | +0.011 |
igsaw | +0.011 |
chie | +0.010 |
ilda | +0.010 |
re | +0.009 |
Neg logit contributions | |
Leo | -0.008 |
Rex | -0.008 |
Kai | -0.008 |
aw | -0.008 |
named | -0.008 |
Token | Don |
Token ID | 3987 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
ge | +0.035 |
igsaw | +0.032 |
chie | +0.030 |
ilda | +0.029 |
pack | +0.027 |
Neg logit contributions | |
Leo | -0.030 |
Kai | -0.030 |
Rex | -0.029 |
icks | -0.029 |
aw | -0.028 |
Token | 't |
Token ID | 470 |
Feature activation | +9.43e-03 |
Pos logit contributions | |
Rex | +0.078 |
Kai | +0.076 |
Leo | +0.075 |
Spot | +0.073 |
thank | +0.073 |
Neg logit contributions | |
ge | -0.094 |
igsaw | -0.083 |
chie | -0.073 |
spe | -0.071 |
hr | -0.069 |
Token | worry |
Token ID | 5490 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
igsaw | +0.017 |
ge | +0.016 |
ilda | +0.016 |
pack | +0.015 |
ic | +0.014 |
Neg logit contributions | |
bye | -0.017 |
thank | -0.017 |
Leo | -0.017 |
named | -0.016 |
Rex | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
ge | +0.028 |
igsaw | +0.027 |
chie | +0.025 |
ilda | +0.025 |
pack | +0.024 |
Neg logit contributions | |
Leo | -0.012 |
Kai | -0.012 |
Rex | -0.012 |
icks | -0.012 |
aw | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
ge | +0.002 |
igsaw | +0.002 |
chie | +0.002 |
ilda | +0.002 |
hr | +0.002 |
Neg logit contributions | |
icks | -0.002 |
Kai | -0.002 |
aw | -0.002 |
Leo | -0.002 |
Rex | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | -5.09e-03 |
Pos logit contributions | |
ge | +0.101 |
igsaw | +0.097 |
chie | +0.086 |
ilda | +0.085 |
pack | +0.080 |
Neg logit contributions | |
Leo | -0.102 |
Rex | -0.101 |
Kai | -0.101 |
icks | -0.099 |
aw | -0.098 |
Token | many |
Token ID | 867 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
Kai | +0.009 |
Leo | +0.009 |
Rex | +0.008 |
icks | +0.008 |
aw | +0.008 |
Neg logit contributions | |
ge | -0.009 |
igsaw | -0.009 |
chie | -0.008 |
ilda | -0.008 |
pack | -0.007 |
Token | more |
Token ID | 517 |
Feature activation | +8.41e-03 |
Pos logit contributions | |
ge | +0.041 |
igsaw | +0.037 |
chie | +0.036 |
hr | +0.033 |
ini | +0.032 |
Neg logit contributions | |
Kai | -0.040 |
Leo | -0.039 |
Rex | -0.039 |
ses | -0.037 |
icks | -0.037 |
Token | butterflies |
Token ID | 44571 |
Feature activation | +5.92e-03 |
Pos logit contributions | |
ge | +0.015 |
igsaw | +0.014 |
chie | +0.013 |
ilda | +0.012 |
hr | +0.012 |
Neg logit contributions | |
Rex | -0.015 |
Kai | -0.015 |
Leo | -0.015 |
icks | -0.014 |
Rover | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
ge | +0.012 |
igsaw | +0.012 |
chie | +0.011 |
ilda | +0.011 |
pack | +0.010 |
Neg logit contributions | |
Leo | -0.008 |
Rex | -0.008 |
Kai | -0.008 |
icks | -0.008 |
aw | -0.008 |
Token | at |
Token ID | 379 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ge | +0.029 |
igsaw | +0.027 |
chie | +0.026 |
ilda | +0.025 |
pack | +0.024 |
Neg logit contributions | |
Leo | -0.016 |
Kai | -0.016 |
Rex | -0.016 |
icks | -0.015 |
aw | -0.015 |
Token | kicking |
Token ID | 17997 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
ge | +0.025 |
igsaw | +0.023 |
chie | +0.021 |
ilda | +0.020 |
pack | +0.020 |
Neg logit contributions | |
Kai | -0.020 |
aw | -0.020 |
icks | -0.019 |
Rex | -0.019 |
Leo | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
Kai | +0.037 |
icks | +0.036 |
Leo | +0.035 |
ses | +0.035 |
sed | +0.035 |
Neg logit contributions | |
ge | -0.045 |
igsaw | -0.042 |
chie | -0.039 |
ilda | -0.036 |
pack | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | +9.18e-03 |
Pos logit contributions | |
ge | +0.027 |
igsaw | +0.023 |
chie | +0.022 |
ilda | +0.021 |
hr | +0.020 |
Neg logit contributions | |
icks | -0.026 |
Kai | -0.025 |
aw | -0.025 |
Leo | -0.024 |
Rex | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.015 |
chie | +0.014 |
ilda | +0.014 |
spe | +0.014 |
Neg logit contributions | |
icks | -0.015 |
aw | -0.015 |
Kai | -0.015 |
ses | -0.014 |
Leo | -0.014 |
Token | mill |
Token ID | 3939 |
Feature activation | +5.87e-02 |
Pos logit contributions | |
ge | +0.005 |
igsaw | +0.005 |
chie | +0.004 |
ilda | +0.004 |
pack | +0.004 |
Neg logit contributions | |
Kai | -0.006 |
Rex | -0.006 |
Leo | -0.006 |
icks | -0.006 |
aw | -0.006 |
Token | er |
Token ID | 263 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
ge | +0.103 |
igsaw | +0.092 |
chie | +0.089 |
ilda | +0.086 |
spe | +0.083 |
Neg logit contributions | |
Kai | -0.104 |
Leo | -0.104 |
icks | -0.104 |
Rex | -0.102 |
ear | -0.098 |
Token | was |
Token ID | 373 |
Feature activation | -1.46e-03 |
Pos logit contributions | |
ge | +0.033 |
igsaw | +0.030 |
chie | +0.029 |
ilda | +0.028 |
spe | +0.027 |
Neg logit contributions | |
Leo | -0.025 |
Kai | -0.024 |
Rex | -0.024 |
icks | -0.024 |
bye | -0.023 |
Token | very |
Token ID | 845 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
Kai | +0.002 |
Leo | +0.002 |
icks | +0.002 |
Rex | +0.002 |
aw | +0.002 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
pack | -0.002 |
Token | proud |
Token ID | 6613 |
Feature activation | +4.96e-02 |
Pos logit contributions | |
ge | +0.086 |
igsaw | +0.082 |
chie | +0.077 |
ilda | +0.077 |
pack | +0.071 |
Neg logit contributions | |
Rex | -0.058 |
Leo | -0.058 |
Kai | -0.058 |
icks | -0.055 |
named | -0.055 |
Token | of |
Token ID | 286 |
Feature activation | +5.26e-03 |
Pos logit contributions | |
ge | +0.089 |
igsaw | +0.083 |
chie | +0.077 |
ilda | +0.074 |
pack | +0.069 |
Neg logit contributions | |
Kai | -0.087 |
Leo | -0.085 |
Rex | -0.085 |
icks | -0.084 |
aw | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -7.33e-05 |
Pos logit contributions | |
Leo | +0.060 |
Rex | +0.060 |
Kai | +0.059 |
icks | +0.058 |
aw | +0.057 |
Neg logit contributions | |
ge | -0.091 |
igsaw | -0.086 |
chie | -0.082 |
ilda | -0.078 |
pack | -0.074 |
Token | pretend |
Token ID | 16614 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
aw | +0.000 |
Kai | +0.000 |
icks | +0.000 |
Leo | +0.000 |
Rex | +0.000 |
Neg logit contributions | |
ge | -0.000 |
igsaw | -0.000 |
chie | -0.000 |
ilda | -0.000 |
pack | -0.000 |
Token | you |
Token ID | 345 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Kai | +0.020 |
Leo | +0.019 |
icks | +0.019 |
Rex | +0.019 |
aw | +0.018 |
Neg logit contributions | |
ge | -0.019 |
igsaw | -0.018 |
chie | -0.017 |
ilda | -0.016 |
pack | -0.015 |
Token | are |
Token ID | 389 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
Kai | +0.015 |
Leo | +0.015 |
Rex | +0.015 |
icks | +0.015 |
aw | +0.014 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.021 |
chie | -0.021 |
ilda | -0.020 |
pack | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
Kai | +0.002 |
Leo | +0.002 |
Rex | +0.002 |
icks | +0.002 |
aw | +0.002 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.002 |
chie | -0.002 |
ilda | -0.002 |
pack | -0.002 |
Token | grown |
Token ID | 7334 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
Kai | +0.014 |
icks | +0.014 |
Leo | +0.014 |
Rex | +0.013 |
aw | +0.013 |
Neg logit contributions | |
ge | -0.018 |
igsaw | -0.017 |
chie | -0.016 |
ilda | -0.015 |
pack | -0.014 |
Token | - |
Token ID | 12 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
igsaw | +0.172 |
ge | +0.168 |
ilda | +0.155 |
chie | +0.155 |
pack | +0.144 |
Neg logit contributions | |
aw | -0.122 |
icks | -0.112 |
named | -0.111 |
ear | -0.107 |
goodbye | -0.105 |
Token | up |
Token ID | 929 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
aw | +0.005 |
Rex | +0.005 |
named | +0.005 |
Leo | +0.005 |
Kai | +0.005 |
Neg logit contributions | |
igsaw | -0.003 |
ge | -0.003 |
chie | -0.003 |
ilda | -0.003 |
solution | -0.002 |
Token | ." |
Token ID | 526 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
ge | +0.023 |
igsaw | +0.022 |
chie | +0.021 |
ilda | +0.020 |
pack | +0.019 |
Neg logit contributions | |
Leo | -0.015 |
Rex | -0.014 |
aw | -0.014 |
Kai | -0.014 |
named | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
ge | +0.007 |
igsaw | +0.006 |
ilda | +0.006 |
re | +0.006 |
pack | +0.005 |
Neg logit contributions | |
icks | -0.007 |
marsh | -0.007 |
slit | -0.007 |
aw | -0.007 |
ses | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +2.16e-03 |
Pos logit contributions | |
ge | +0.008 |
igsaw | +0.007 |
ilda | +0.007 |
pack | +0.006 |
re | +0.006 |
Neg logit contributions | |
ear | -0.009 |
ses | -0.009 |
sed | -0.009 |
marsh | -0.009 |
goodbye | -0.009 |
Token | grandma |
Token ID | 49890 |
Feature activation | -1.92e-03 |
Pos logit contributions | |
ge | +0.034 |
igsaw | +0.032 |
chie | +0.030 |
ilda | +0.028 |
ini | +0.027 |
Neg logit contributions | |
Leo | -0.033 |
Rex | -0.032 |
Kai | -0.031 |
icks | -0.031 |
named | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Leo | +0.003 |
Rex | +0.003 |
named | +0.003 |
icks | +0.003 |
aw | +0.003 |
Neg logit contributions | |
ge | -0.004 |
igsaw | -0.004 |
chie | -0.004 |
ilda | -0.003 |
pack | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ge | +0.038 |
igsaw | +0.038 |
chie | +0.035 |
ilda | +0.034 |
pack | +0.032 |
Neg logit contributions | |
Kai | -0.033 |
Leo | -0.033 |
slit | -0.032 |
Rex | -0.032 |
aw | -0.032 |
Token | is |
Token ID | 318 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
Kai | +0.018 |
Leo | +0.018 |
Rex | +0.018 |
icks | +0.017 |
bye | +0.017 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.022 |
chie | -0.021 |
ilda | -0.021 |
pack | -0.019 |
Token | sick |
Token ID | 6639 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Leo | +0.022 |
Rex | +0.022 |
named | +0.021 |
icks | +0.021 |
ear | +0.020 |
Neg logit contributions | |
ge | -0.032 |
igsaw | -0.030 |
chie | -0.028 |
ilda | -0.027 |
spe | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
Kai | +0.017 |
Leo | +0.017 |
Rex | +0.016 |
icks | +0.016 |
aw | +0.016 |
Neg logit contributions | |
ge | -0.022 |
igsaw | -0.020 |
chie | -0.019 |
ilda | -0.019 |
pack | -0.018 |
Token | we |
Token ID | 356 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
ge | +0.022 |
igsaw | +0.021 |
chie | +0.019 |
ilda | +0.019 |
pack | +0.018 |
Neg logit contributions | |
Kai | -0.020 |
Leo | -0.019 |
Rex | -0.019 |
icks | -0.019 |
aw | -0.019 |
Token | want |
Token ID | 765 |
Feature activation | +2.72e-04 |
Pos logit contributions | |
ge | +0.052 |
igsaw | +0.052 |
chie | +0.046 |
ilda | +0.046 |
ic | +0.043 |
Neg logit contributions | |
named | -0.036 |
icks | -0.036 |
Rex | -0.036 |
Leo | -0.035 |
Kai | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ge | +0.000 |
igsaw | +0.000 |
chie | +0.000 |
ilda | +0.000 |
pack | +0.000 |
Neg logit contributions | |
Leo | -0.000 |
Rex | -0.000 |
Kai | -0.000 |
icks | -0.000 |
aw | -0.000 |
Token | give |
Token ID | 1577 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
ge | +0.037 |
igsaw | +0.034 |
chie | +0.031 |
ilda | +0.030 |
pack | +0.030 |
Neg logit contributions | |
Kai | -0.035 |
Leo | -0.035 |
Rex | -0.034 |
aw | -0.034 |
icks | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
ge | +0.055 |
igsaw | +0.052 |
chie | +0.049 |
ilda | +0.047 |
pack | +0.045 |
Neg logit contributions | |
Rex | -0.034 |
Leo | -0.034 |
Kai | -0.033 |
icks | -0.032 |
aw | -0.032 |
Token | special |
Token ID | 2041 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ge | +0.054 |
igsaw | +0.052 |
chie | +0.048 |
ilda | +0.045 |
pack | +0.042 |
Neg logit contributions | |
Kai | -0.057 |
Rex | -0.056 |
Leo | -0.056 |
aw | -0.055 |
icks | -0.055 |
Token | friend |
Token ID | 1545 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
ge | +0.073 |
igsaw | +0.069 |
chie | +0.064 |
ilda | +0.061 |
pack | +0.058 |
Neg logit contributions | |
Kai | -0.070 |
Leo | -0.070 |
Rex | -0.070 |
icks | -0.068 |
aw | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
Kai | +0.061 |
icks | +0.061 |
ses | +0.059 |
marsh | +0.059 |
slit | +0.057 |
Neg logit contributions | |
ge | -0.061 |
igsaw | -0.057 |
ilda | -0.053 |
chie | -0.052 |
spe | -0.049 |
Token | Whenever |
Token ID | 21326 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
igsaw | +0.009 |
ge | +0.009 |
ilda | +0.008 |
chie | +0.008 |
pack | +0.007 |
Neg logit contributions | |
Kai | -0.007 |
aw | -0.006 |
slit | -0.006 |
hawk | -0.006 |
Rex | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
Leo | +0.037 |
Rex | +0.036 |
Kai | +0.036 |
icks | +0.035 |
aw | +0.034 |
Neg logit contributions | |
ge | -0.062 |
igsaw | -0.059 |
chie | -0.056 |
ilda | -0.054 |
pack | -0.051 |
Token | was |
Token ID | 373 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.016 |
chie | +0.015 |
ilda | +0.015 |
pack | +0.014 |
Neg logit contributions | |
Kai | -0.014 |
Leo | -0.014 |
Rex | -0.013 |
icks | -0.013 |
aw | -0.013 |
Token | hungry |
Token ID | 14720 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
ge | +0.014 |
igsaw | +0.013 |
chie | +0.012 |
ilda | +0.012 |
pack | +0.011 |
Neg logit contributions | |
Kai | -0.014 |
Rex | -0.014 |
Leo | -0.014 |
aw | -0.013 |
icks | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
ge | +0.026 |
igsaw | +0.025 |
chie | +0.024 |
ilda | +0.023 |
pack | +0.022 |
Neg logit contributions | |
Leo | -0.011 |
Kai | -0.011 |
Rex | -0.011 |
icks | -0.011 |
aw | -0.010 |
Token | Anna |
Token ID | 11735 |
Feature activation | +7.75e-03 |
Pos logit contributions | |
ge | +0.029 |
igsaw | +0.028 |
chie | +0.026 |
ilda | +0.025 |
pack | +0.024 |
Neg logit contributions | |
Kai | -0.018 |
Leo | -0.018 |
Rex | -0.018 |
icks | -0.018 |
aw | -0.017 |
Token | would |
Token ID | 561 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
ge | +0.014 |
ilda | +0.013 |
igsaw | +0.012 |
chie | +0.012 |
re | +0.012 |
Neg logit contributions | |
Kai | -0.012 |
Rex | -0.012 |
icks | -0.012 |
ses | -0.012 |
Leo | -0.012 |
Token | feed |
Token ID | 3745 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
aw | +0.054 |
Kai | +0.053 |
Rex | +0.052 |
Leo | +0.050 |
ses | +0.050 |
Neg logit contributions | |
ge | -0.049 |
igsaw | -0.043 |
chie | -0.041 |
pack | -0.039 |
ilda | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | +6.96e-03 |
Pos logit contributions | |
ge | +0.025 |
igsaw | +0.023 |
chie | +0.021 |
ilda | +0.020 |
pack | +0.020 |
Neg logit contributions | |
Kai | -0.024 |
Leo | -0.023 |
Rex | -0.023 |
icks | -0.023 |
aw | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
ge | +0.018 |
igsaw | +0.017 |
chie | +0.016 |
ilda | +0.016 |
ini | +0.015 |
Neg logit contributions | |
Leo | -0.008 |
Rex | -0.008 |
Kai | -0.008 |
named | -0.007 |
Spot | -0.007 |
Token | car |
Token ID | 1097 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
Rex | +0.033 |
Leo | +0.033 |
Kai | +0.033 |
named | +0.032 |
icks | +0.032 |
Neg logit contributions | |
ge | -0.030 |
igsaw | -0.027 |
chie | -0.026 |
ilda | -0.024 |
ic | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
Leo | +0.048 |
Kai | +0.048 |
Rex | +0.048 |
icks | +0.047 |
aw | +0.046 |
Neg logit contributions | |
ge | -0.071 |
igsaw | -0.067 |
chie | -0.063 |
ilda | -0.061 |
pack | -0.058 |
Token | drove |
Token ID | 10357 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
icks | +0.003 |
Kai | +0.003 |
aw | +0.003 |
Leo | +0.002 |
Rex | +0.002 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.003 |
ilda | -0.003 |
chie | -0.003 |
pack | -0.003 |
Token | away |
Token ID | 1497 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ge | +0.031 |
igsaw | +0.028 |
chie | +0.026 |
ilda | +0.026 |
pack | +0.025 |
Neg logit contributions | |
Kai | -0.027 |
icks | -0.026 |
Leo | -0.026 |
Rex | -0.026 |
aw | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
Leo | +0.017 |
Rex | +0.017 |
Kai | +0.017 |
named | +0.016 |
icks | +0.015 |
Neg logit contributions | |
ge | -0.029 |
igsaw | -0.029 |
chie | -0.028 |
ilda | -0.027 |
ini | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +6.07e-03 |
Pos logit contributions | |
slit | +0.022 |
hawk | +0.022 |
aw | +0.022 |
Kai | +0.021 |
icks | +0.021 |
Neg logit contributions | |
igsaw | -0.021 |
ge | -0.021 |
ilda | -0.018 |
re | -0.018 |
enny | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.009 |
ilda | +0.008 |
pack | +0.008 |
chie | +0.008 |
Neg logit contributions | |
ses | -0.011 |
sed | -0.011 |
ear | -0.011 |
aw | -0.011 |
slit | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
ge | +0.008 |
igsaw | +0.007 |
chie | +0.007 |
ilda | +0.007 |
pack | +0.006 |
Neg logit contributions | |
Leo | -0.006 |
Kai | -0.006 |
Rex | -0.006 |
icks | -0.006 |
aw | -0.006 |
Token | next |
Token ID | 1306 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
Kai | +0.047 |
Leo | +0.047 |
icks | +0.046 |
Rex | +0.046 |
aw | +0.045 |
Neg logit contributions | |
ge | -0.042 |
igsaw | -0.041 |
chie | -0.037 |
ilda | -0.035 |
pack | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ge | +0.000 |
igsaw | +0.000 |
ilda | +0.000 |
chie | +0.000 |
pack | +0.000 |
Neg logit contributions | |
Kai | -0.000 |
icks | -0.000 |
ses | -0.000 |
slit | -0.000 |
sed | -0.000 |
Token | teacher |
Token ID | 4701 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
Kai | +0.018 |
icks | +0.017 |
Leo | +0.017 |
Rex | +0.017 |
aw | +0.017 |
Neg logit contributions | |
ge | -0.023 |
igsaw | -0.021 |
chie | -0.020 |
ilda | -0.020 |
pack | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -8.36e-03 |
Pos logit contributions | |
Leo | +0.043 |
Rex | +0.043 |
Kai | +0.042 |
icks | +0.041 |
named | +0.041 |
Neg logit contributions | |
ge | -0.068 |
igsaw | -0.064 |
chie | -0.062 |
ilda | -0.059 |
pack | -0.056 |
Token | her |
Token ID | 607 |
Feature activation | -6.34e-04 |
Pos logit contributions | |
Kai | +0.013 |
Leo | +0.013 |
Rex | +0.013 |
icks | +0.013 |
aw | +0.013 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.015 |
chie | -0.014 |
ilda | -0.014 |
pack | -0.013 |
Token | classmates |
Token ID | 28999 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
Kai | +0.001 |
icks | +0.001 |
Leo | +0.001 |
Rex | +0.001 |
aw | +0.001 |
Neg logit contributions | |
ge | -0.001 |
igsaw | -0.001 |
chie | -0.001 |
ilda | -0.001 |
pack | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-03 |
Pos logit contributions | |
Leo | +0.013 |
Rex | +0.013 |
Kai | +0.013 |
named | +0.013 |
icks | +0.013 |
Neg logit contributions | |
ge | -0.021 |
igsaw | -0.020 |
chie | -0.019 |
ilda | -0.018 |
ini | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.004 |
chie | +0.004 |
ilda | +0.004 |
pack | +0.003 |
Neg logit contributions | |
Leo | -0.003 |
Kai | -0.003 |
Rex | -0.003 |
icks | -0.003 |
aw | -0.003 |
Token | put |
Token ID | 1234 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
Leo | +0.027 |
Kai | +0.027 |
Rex | +0.027 |
icks | +0.026 |
aw | +0.025 |
Neg logit contributions | |
ge | -0.037 |
igsaw | -0.035 |
chie | -0.033 |
ilda | -0.032 |
pack | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | -8.02e-03 |
Pos logit contributions | |
ge | +0.002 |
igsaw | +0.002 |
ilda | +0.002 |
chie | +0.002 |
pack | +0.002 |
Neg logit contributions | |
Kai | -0.002 |
slit | -0.002 |
Leo | -0.002 |
Rex | -0.002 |
icks | -0.002 |
Token | book |
Token ID | 1492 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
Leo | +0.013 |
Rex | +0.012 |
icks | +0.012 |
Kai | +0.012 |
ear | +0.012 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.015 |
chie | -0.014 |
ilda | -0.014 |
pack | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -7.32e-03 |
Pos logit contributions | |
Leo | +0.074 |
Kai | +0.074 |
Rex | +0.074 |
icks | +0.072 |
aw | +0.071 |
Neg logit contributions | |
ge | -0.104 |
igsaw | -0.098 |
chie | -0.092 |
ilda | -0.090 |
pack | -0.085 |
Token | asleep |
Token ID | 16039 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
Rex | +0.035 |
Kai | +0.035 |
Leo | +0.035 |
icks | +0.034 |
aw | +0.033 |
Neg logit contributions | |
ge | -0.030 |
igsaw | -0.028 |
chie | -0.026 |
ilda | -0.025 |
pack | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
Leo | +0.032 |
Kai | +0.031 |
Rex | +0.031 |
icks | +0.030 |
aw | +0.030 |
Neg logit contributions | |
ge | -0.045 |
igsaw | -0.042 |
chie | -0.040 |
ilda | -0.038 |
pack | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
Kai | +0.032 |
ses | +0.032 |
sed | +0.032 |
icks | +0.031 |
aw | +0.030 |
Neg logit contributions | |
igsaw | -0.031 |
ge | -0.030 |
chie | -0.027 |
ilda | -0.025 |
solution | -0.024 |
Token | smile |
Token ID | 8212 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
Kai | +0.041 |
Leo | +0.041 |
Rex | +0.040 |
icks | +0.040 |
aw | +0.039 |
Neg logit contributions | |
ge | -0.052 |
igsaw | -0.049 |
chie | -0.046 |
ilda | -0.045 |
pack | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
Leo | +0.038 |
Kai | +0.037 |
Rex | +0.037 |
icks | +0.036 |
aw | +0.035 |
Neg logit contributions | |
ge | -0.071 |
igsaw | -0.066 |
chie | -0.062 |
ilda | -0.062 |
pack | -0.058 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
Kai | +0.018 |
Leo | +0.018 |
icks | +0.018 |
aw | +0.018 |
Rex | +0.017 |
Neg logit contributions | |
ge | -0.026 |
igsaw | -0.026 |
chie | -0.023 |
ilda | -0.023 |
pack | -0.022 |
Token | Fred |
Token ID | 30847 |
Feature activation | +8.08e-03 |
Pos logit contributions | |
ge | +0.040 |
igsaw | +0.037 |
chie | +0.034 |
ilda | +0.034 |
pack | +0.032 |
Neg logit contributions | |
Kai | -0.033 |
Leo | -0.032 |
icks | -0.032 |
Rex | -0.032 |
aw | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
ge | +0.013 |
igsaw | +0.011 |
ilda | +0.010 |
any | +0.010 |
upon | +0.010 |
Neg logit contributions | |
icks | -0.015 |
ses | -0.015 |
sorry | -0.015 |
Kai | -0.015 |
goodbye | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
Kai | +0.039 |
Rex | +0.036 |
icks | +0.036 |
bye | +0.036 |
Leo | +0.036 |
Neg logit contributions | |
ge | -0.032 |
igsaw | -0.030 |
pack | -0.029 |
ilda | -0.028 |
chie | -0.027 |
Token | excited |
Token ID | 6568 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
ge | +0.022 |
igsaw | +0.021 |
chie | +0.020 |
ilda | +0.019 |
pack | +0.018 |
Neg logit contributions | |
Kai | -0.020 |
Rex | -0.020 |
Leo | -0.020 |
icks | -0.019 |
aw | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.88e-03 |
Pos logit contributions | |
ge | +0.087 |
chie | +0.083 |
igsaw | +0.082 |
ini | +0.073 |
ilda | +0.072 |
Neg logit contributions | |
Leo | -0.049 |
goodbye | -0.047 |
Rex | -0.047 |
aw | -0.047 |
named | -0.047 |
Token | did |
Token ID | 750 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
ge | +0.011 |
chie | +0.009 |
re | +0.009 |
ilda | +0.009 |
pack | +0.009 |
Neg logit contributions | |
Kai | -0.011 |
Leo | -0.011 |
Rex | -0.011 |
Rover | -0.011 |
bye | -0.010 |
Token | not |
Token ID | 407 |
Feature activation | +1.74e-03 |
Pos logit contributions | |
Kai | +0.036 |
Leo | +0.035 |
Rex | +0.035 |
icks | +0.034 |
aw | +0.034 |
Neg logit contributions | |
ge | -0.058 |
igsaw | -0.054 |
chie | -0.051 |
ilda | -0.050 |
pack | -0.048 |
Token | mind |
Token ID | 2000 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
ge | +0.004 |
igsaw | +0.003 |
chie | +0.003 |
ilda | +0.003 |
pack | +0.003 |
Neg logit contributions | |
Leo | -0.003 |
Rex | -0.003 |
Kai | -0.002 |
icks | -0.002 |
named | -0.002 |
Token | if |
Token ID | 611 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
igsaw | +0.057 |
chie | +0.055 |
ge | +0.055 |
pack | +0.052 |
ic | +0.051 |
Neg logit contributions | |
Rex | -0.028 |
Leo | -0.026 |
Kai | -0.025 |
Spot | -0.024 |
Rover | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.24e-03 |
Pos logit contributions | |
icks | +0.035 |
aw | +0.034 |
Kai | +0.033 |
named | +0.033 |
ses | +0.033 |
Neg logit contributions | |
ge | -0.047 |
igsaw | -0.042 |
chie | -0.040 |
ilda | -0.040 |
spe | -0.037 |
Token | dog |
Token ID | 3290 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Kai | +0.005 |
icks | +0.005 |
Leo | +0.005 |
aw | +0.005 |
Rex | +0.005 |
Neg logit contributions | |
ge | -0.006 |
igsaw | -0.006 |
chie | -0.005 |
ilda | -0.005 |
spe | -0.005 |
Token | played |
Token ID | 2826 |
Feature activation | -6.27e-04 |
Pos logit contributions | |
Kai | +0.053 |
Leo | +0.052 |
icks | +0.052 |
marsh | +0.050 |
Rex | +0.050 |
Neg logit contributions | |
ge | -0.055 |
igsaw | -0.046 |
chie | -0.045 |
ilda | -0.044 |
re | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | -4.35e-03 |
Pos logit contributions | |
Kai | +0.001 |
Leo | +0.001 |
icks | +0.001 |
Dod | +0.001 |
bye | +0.001 |
Neg logit contributions | |
ge | -0.001 |
igsaw | -0.001 |
chie | -0.001 |
pack | -0.001 |
ilda | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
icks | +0.007 |
Kai | +0.007 |
ses | +0.007 |
sed | +0.007 |
bye | +0.006 |
Neg logit contributions | |
ge | -0.008 |
igsaw | -0.007 |
chie | -0.007 |
ilda | -0.007 |
ic | -0.006 |
Token | ball |
Token ID | 2613 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
Kai | +0.012 |
icks | +0.012 |
Leo | +0.011 |
aw | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
ge | -0.013 |
igsaw | -0.012 |
chie | -0.011 |
ilda | -0.010 |
pack | -0.010 |
Token | too |
Token ID | 1165 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
Leo | +0.023 |
Kai | +0.023 |
Rex | +0.023 |
icks | +0.023 |
aw | +0.022 |
Neg logit contributions | |
ge | -0.031 |
igsaw | -0.029 |
chie | -0.028 |
ilda | -0.027 |
pack | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
ge | +0.026 |
igsaw | +0.024 |
chie | +0.023 |
ilda | +0.021 |
pack | +0.020 |
Neg logit contributions | |
Rex | -0.016 |
aw | -0.016 |
Leo | -0.016 |
icks | -0.015 |
Kai | -0.015 |
Token | beauty |
Token ID | 8737 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
Leo | +0.012 |
Kai | +0.012 |
Rex | +0.012 |
icks | +0.011 |
aw | +0.011 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.015 |
chie | -0.014 |
ilda | -0.013 |
pack | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
ge | +0.045 |
igsaw | +0.043 |
chie | +0.039 |
ilda | +0.038 |
ic | +0.036 |
Neg logit contributions | |
Kai | -0.045 |
Leo | -0.044 |
Rex | -0.044 |
slit | -0.043 |
ses | -0.042 |
Token | We |
Token ID | 775 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
slit | +0.004 |
hawk | +0.003 |
aw | +0.003 |
sed | +0.003 |
Kai | +0.003 |
Neg logit contributions | |
igsaw | -0.003 |
ge | -0.002 |
ilda | -0.002 |
chie | -0.002 |
any | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ge | +0.013 |
igsaw | +0.012 |
chie | +0.012 |
ilda | +0.011 |
pack | +0.011 |
Neg logit contributions | |
Leo | -0.009 |
Kai | -0.009 |
Rex | -0.009 |
aw | -0.008 |
icks | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
Rex | +0.018 |
Leo | +0.018 |
Kai | +0.018 |
icks | +0.018 |
named | +0.018 |
Neg logit contributions | |
ge | -0.024 |
igsaw | -0.023 |
chie | -0.021 |
ilda | -0.020 |
ini | -0.019 |
Token | dress |
Token ID | 6576 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
Leo | +0.050 |
Kai | +0.050 |
Rex | +0.050 |
icks | +0.049 |
aw | +0.048 |
Neg logit contributions | |
ge | -0.054 |
igsaw | -0.051 |
chie | -0.047 |
ilda | -0.046 |
pack | -0.043 |
Token | up |
Token ID | 510 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Rex | +0.033 |
Kai | +0.033 |
Leo | +0.033 |
aw | +0.032 |
icks | +0.032 |
Neg logit contributions | |
ge | -0.036 |
igsaw | -0.034 |
chie | -0.032 |
ilda | -0.030 |
pack | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
Kai | +0.025 |
icks | +0.024 |
Rex | +0.023 |
Leo | +0.023 |
ses | +0.023 |
Neg logit contributions | |
ge | -0.028 |
igsaw | -0.026 |
chie | -0.024 |
ilda | -0.023 |
pack | -0.022 |
Token | have |
Token ID | 423 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
ge | +0.010 |
igsaw | +0.010 |
chie | +0.009 |
ilda | +0.009 |
ic | +0.009 |
Neg logit contributions | |
Rex | -0.007 |
Leo | -0.007 |
Kai | -0.007 |
bye | -0.007 |
named | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Kai | +0.005 |
Leo | +0.005 |
Rex | +0.005 |
icks | +0.005 |
ses | +0.005 |
Neg logit contributions | |
ge | -0.005 |
igsaw | -0.004 |
chie | -0.004 |
ilda | -0.004 |
pack | -0.004 |
Token | parents |
Token ID | 3397 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
icks | +0.003 |
Leo | +0.003 |
Kai | +0.003 |
Rex | +0.003 |
aw | +0.003 |
Neg logit contributions | |
ge | -0.003 |
igsaw | -0.003 |
chie | -0.003 |
ilda | -0.003 |
spe | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
ge | +0.037 |
igsaw | +0.035 |
chie | +0.033 |
ilda | +0.032 |
pack | +0.030 |
Neg logit contributions | |
Leo | -0.024 |
Kai | -0.024 |
Rex | -0.024 |
icks | -0.024 |
named | -0.023 |
Token | so |
Token ID | 523 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
ge | +0.049 |
igsaw | +0.047 |
chie | +0.043 |
ilda | +0.042 |
pack | +0.039 |
Neg logit contributions | |
Leo | -0.037 |
Kai | -0.036 |
Rex | -0.036 |
icks | -0.035 |
named | -0.035 |
Token | proud |
Token ID | 6613 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
ge | +0.080 |
igsaw | +0.077 |
chie | +0.071 |
ilda | +0.071 |
ic | +0.066 |
Neg logit contributions | |
Leo | -0.038 |
Kai | -0.037 |
thank | -0.037 |
named | -0.037 |
Rex | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ge | +0.076 |
igsaw | +0.071 |
chie | +0.067 |
ilda | +0.064 |
pack | +0.061 |
Neg logit contributions | |
Leo | -0.064 |
Rex | -0.063 |
Kai | -0.063 |
aw | -0.061 |
icks | -0.061 |
Token | him |
Token ID | 683 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ge | +0.023 |
igsaw | +0.022 |
chie | +0.020 |
ilda | +0.020 |
pack | +0.019 |
Neg logit contributions | |
icks | -0.013 |
Kai | -0.013 |
ses | -0.013 |
Leo | -0.013 |
sed | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
Leo | +0.055 |
Kai | +0.055 |
Rex | +0.055 |
icks | +0.054 |
aw | +0.053 |
Neg logit contributions | |
ge | -0.077 |
igsaw | -0.072 |
chie | -0.068 |
ilda | -0.066 |
pack | -0.062 |
Token | |
Token ID | 220 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
Leo | +0.002 |
Rex | +0.002 |
Kai | +0.002 |
named | +0.002 |
icks | +0.002 |
Neg logit contributions | |
ge | -0.004 |
igsaw | -0.004 |
chie | -0.004 |
ilda | -0.003 |
pack | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
ge | +0.070 |
igsaw | +0.067 |
chie | +0.063 |
ilda | +0.061 |
pack | +0.058 |
Neg logit contributions | |
Leo | -0.040 |
Rex | -0.040 |
Kai | -0.040 |
icks | -0.039 |
aw | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ge | +0.031 |
igsaw | +0.031 |
chie | +0.029 |
ilda | +0.028 |
ini | +0.026 |
Neg logit contributions | |
Leo | -0.014 |
Rex | -0.014 |
Kai | -0.014 |
named | -0.013 |
Rover | -0.012 |
Token | One |
Token ID | 3198 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
ge | +0.026 |
igsaw | +0.026 |
chie | +0.024 |
ilda | +0.023 |
ic | +0.022 |
Neg logit contributions | |
Rex | -0.016 |
Leo | -0.016 |
named | -0.016 |
Kai | -0.016 |
aw | -0.015 |
Token | take |
Token ID | 1011 |
Feature activation | -6.99e-03 |
Pos logit contributions | |
aw | +0.058 |
Kai | +0.057 |
Leo | +0.056 |
Rex | +0.056 |
icks | +0.054 |
Neg logit contributions | |
ge | -0.054 |
igsaw | -0.048 |
chie | -0.047 |
ilda | -0.046 |
pack | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -2.11e-03 |
Pos logit contributions | |
Kai | +0.014 |
ses | +0.013 |
sed | +0.013 |
slit | +0.013 |
named | +0.013 |
Neg logit contributions | |
ge | -0.010 |
igsaw | -0.010 |
chie | -0.009 |
ilda | -0.009 |
ic | -0.008 |
Token | pill |
Token ID | 9582 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
Kai | +0.003 |
Leo | +0.003 |
Rex | +0.003 |
icks | +0.003 |
aw | +0.003 |
Neg logit contributions | |
ge | -0.004 |
igsaw | -0.004 |
chie | -0.004 |
ilda | -0.004 |
pack | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
Rex | +0.003 |
Leo | +0.003 |
icks | +0.003 |
goodbye | +0.003 |
Kai | +0.003 |
Neg logit contributions | |
ge | -0.005 |
igsaw | -0.005 |
chie | -0.005 |
ilda | -0.004 |
ini | -0.004 |
Token | But |
Token ID | 887 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
igsaw | +0.005 |
chie | +0.004 |
pack | +0.004 |
Emmy | +0.004 |
Gr | +0.004 |
Neg logit contributions | |
aw | -0.009 |
hawk | -0.008 |
slit | -0.008 |
aver | -0.008 |
Kai | -0.008 |
Token | only |
Token ID | 691 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
Kai | +0.031 |
aw | +0.031 |
icks | +0.031 |
Leo | +0.030 |
Rex | +0.030 |
Neg logit contributions | |
ge | -0.033 |
igsaw | -0.030 |
chie | -0.029 |
ilda | -0.028 |
pack | -0.026 |
Token | if |
Token ID | 611 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
Kai | +0.043 |
Leo | +0.042 |
Rex | +0.042 |
icks | +0.041 |
aw | +0.041 |
Neg logit contributions | |
ge | -0.054 |
igsaw | -0.050 |
chie | -0.047 |
ilda | -0.045 |
pack | -0.043 |
Token | you |
Token ID | 345 |
Feature activation | -8.47e-03 |
Pos logit contributions | |
icks | +0.085 |
Kai | +0.083 |
aw | +0.083 |
ses | +0.082 |
Leo | +0.081 |
Neg logit contributions | |
ge | -0.048 |
igsaw | -0.043 |
chie | -0.040 |
ilda | -0.039 |
pack | -0.033 |
Token | let |
Token ID | 1309 |
Feature activation | -4.92e-03 |
Pos logit contributions | |
Kai | +0.014 |
Rex | +0.014 |
Leo | +0.014 |
aw | +0.014 |
icks | +0.013 |
Neg logit contributions | |
ge | -0.016 |
igsaw | -0.014 |
chie | -0.014 |
ilda | -0.013 |
pack | -0.013 |
Token | me |
Token ID | 502 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
Kai | +0.008 |
Leo | +0.008 |
Rex | +0.008 |
icks | +0.008 |
aw | +0.008 |
Neg logit contributions | |
ge | -0.009 |
igsaw | -0.009 |
chie | -0.008 |
ilda | -0.008 |
pack | -0.007 |
Token | watch |
Token ID | 2342 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
Kai | +0.080 |
Leo | +0.080 |
Rex | +0.080 |
icks | +0.078 |
aw | +0.077 |
Neg logit contributions | |
ge | -0.090 |
igsaw | -0.084 |
chie | -0.079 |
ilda | -0.076 |
pack | -0.072 |
Token | in |
Token ID | 287 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
Kai | +0.047 |
Leo | +0.046 |
icks | +0.045 |
marsh | +0.045 |
aw | +0.045 |
Neg logit contributions | |
ge | -0.058 |
igsaw | -0.050 |
chie | -0.049 |
pack | -0.047 |
ilda | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
icks | +0.042 |
aw | +0.042 |
Kai | +0.040 |
sed | +0.039 |
icked | +0.039 |
Neg logit contributions | |
ge | -0.044 |
igsaw | -0.042 |
ilda | -0.035 |
chie | -0.035 |
pack | -0.034 |
Token | car |
Token ID | 1097 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
Leo | +0.022 |
Kai | +0.021 |
icks | +0.021 |
slit | +0.020 |
Rex | +0.020 |
Neg logit contributions | |
ge | -0.022 |
igsaw | -0.022 |
chie | -0.020 |
pack | -0.019 |
ilda | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -7.12e-03 |
Pos logit contributions | |
Kai | +0.053 |
Leo | +0.051 |
icks | +0.051 |
marsh | +0.051 |
Dod | +0.050 |
Neg logit contributions | |
ge | -0.058 |
igsaw | -0.049 |
pack | -0.048 |
ilda | -0.046 |
chie | -0.046 |
Token | waves |
Token ID | 9813 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
aw | +0.011 |
icks | +0.010 |
aver | +0.009 |
named | +0.009 |
sed | +0.009 |
Neg logit contributions | |
ge | -0.014 |
igsaw | -0.012 |
ilda | -0.012 |
pack | -0.011 |
chie | -0.011 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
ses | +0.042 |
sed | +0.040 |
marsh | +0.040 |
slit | +0.040 |
hawk | +0.039 |
Neg logit contributions | |
ge | -0.031 |
chie | -0.024 |
upon | -0.022 |
re | -0.022 |
oe | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
icks | +0.062 |
Kai | +0.061 |
Leo | +0.060 |
marsh | +0.060 |
Rex | +0.059 |
Neg logit contributions | |
ge | -0.053 |
igsaw | -0.044 |
chie | -0.043 |
ilda | -0.040 |
pack | -0.039 |
Token | Tom |
Token ID | 4186 |
Feature activation | +8.25e-03 |
Pos logit contributions | |
aw | +0.007 |
icks | +0.007 |
hawk | +0.007 |
icked | +0.007 |
sed | +0.007 |
Neg logit contributions | |
igsaw | -0.006 |
ge | -0.005 |
ilda | -0.005 |
Gr | -0.004 |
enny | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -6.66e-03 |
Pos logit contributions | |
ge | +0.014 |
ilda | +0.012 |
igsaw | +0.011 |
pack | +0.011 |
re | +0.011 |
Neg logit contributions | |
Kai | -0.013 |
marsh | -0.013 |
sed | -0.013 |
ses | -0.012 |
icks | -0.012 |
Token | Mia |
Token ID | 32189 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
aw | +0.008 |
Kai | +0.008 |
icks | +0.008 |
Leo | +0.007 |
Rex | +0.007 |
Neg logit contributions | |
ge | -0.015 |
igsaw | -0.015 |
chie | -0.014 |
ilda | -0.013 |
pack | -0.013 |
Token | wave |
Token ID | 6769 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ge | +0.005 |
chie | +0.004 |
pack | +0.004 |
re | +0.004 |
igsaw | +0.004 |
Neg logit contributions | |
sed | -0.005 |
ses | -0.005 |
Kai | -0.005 |
aw | -0.005 |
Leo | -0.005 |