Token | Rudy |
Token ID | 37602 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
relief | +0.020 |
gentleman | +0.018 |
woman | +0.018 |
cal | +0.018 |
lady | +0.018 |
Neg logit contributions | |
ug | -0.016 |
issors | -0.015 |
ors | -0.014 |
om | -0.014 |
utes | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ug | +0.071 |
ors | +0.068 |
eds | +0.067 |
issors | +0.066 |
bowl | +0.065 |
Neg logit contributions | |
relief | -0.089 |
gentleman | -0.081 |
Heidi | -0.076 |
cal | -0.076 |
stranger | -0.076 |
Token | He |
Token ID | 679 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
relief | +0.017 |
lady | +0.016 |
cal | +0.016 |
service | +0.015 |
woman | +0.015 |
Neg logit contributions | |
ug | -0.016 |
issors | -0.015 |
ors | -0.015 |
bar | -0.015 |
bowl | -0.014 |
Token | 's |
Token ID | 338 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
relief | +0.010 |
gentleman | +0.010 |
woman | +0.009 |
Heidi | +0.009 |
stranger | +0.009 |
Neg logit contributions | |
fet | -0.007 |
om | -0.007 |
ug | -0.007 |
ors | -0.007 |
bowl | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ug | +0.047 |
issors | +0.046 |
utes | +0.045 |
bar | +0.045 |
om | +0.045 |
Neg logit contributions | |
relief | -0.057 |
gentleman | -0.053 |
cal | -0.052 |
woman | -0.050 |
stranger | -0.050 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
relief | +0.016 |
gentleman | +0.015 |
Heidi | +0.015 |
cal | +0.015 |
woman | +0.014 |
Neg logit contributions | |
ug | -0.019 |
utes | -0.018 |
bar | -0.018 |
bowl | -0.017 |
issors | -0.017 |
Token | present |
Token ID | 1944 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
relief | +0.266 |
cal | +0.252 |
Heidi | +0.248 |
gentleman | +0.237 |
Lord | +0.224 |
Neg logit contributions | |
ug | -0.211 |
bar | -0.200 |
issors | -0.196 |
bowl | -0.195 |
clubs | -0.195 |
Token | from |
Token ID | 422 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
relief | +0.084 |
cal | +0.077 |
gentleman | +0.072 |
woman | +0.070 |
Heidi | +0.070 |
Neg logit contributions | |
ug | -0.057 |
ors | -0.055 |
bar | -0.055 |
issors | -0.053 |
bed | -0.051 |
Token | my |
Token ID | 616 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
relief | +0.033 |
gentleman | +0.032 |
cal | +0.031 |
lady | +0.030 |
woman | +0.030 |
Neg logit contributions | |
ug | -0.030 |
issors | -0.028 |
utes | -0.027 |
bed | -0.027 |
eds | -0.027 |
Token | grandma |
Token ID | 49890 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
relief | +0.026 |
Heidi | +0.025 |
gentleman | +0.025 |
cal | +0.025 |
stranger | +0.024 |
Neg logit contributions | |
ug | -0.025 |
utes | -0.023 |
bed | -0.023 |
clubs | -0.022 |
issors | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
relief | +0.054 |
gentleman | +0.049 |
cal | +0.048 |
stranger | +0.047 |
lady | +0.046 |
Neg logit contributions | |
ug | -0.048 |
ors | -0.046 |
issors | -0.046 |
eds | -0.044 |
usted | -0.043 |
Token | twins |
Token ID | 20345 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
gentleman | +0.089 |
relief | +0.089 |
woman | +0.084 |
lady | +0.084 |
stranger | +0.081 |
Neg logit contributions | |
ug | -0.103 |
issors | -0.099 |
usted | -0.096 |
bar | -0.095 |
utes | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
relief | +0.067 |
gentleman | +0.065 |
lady | +0.062 |
stranger | +0.061 |
Heidi | +0.060 |
Neg logit contributions | |
ug | -0.074 |
usted | -0.068 |
bed | -0.068 |
issors | -0.067 |
ors | -0.067 |
Token | They |
Token ID | 1119 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
relief | +0.022 |
lady | +0.021 |
gentleman | +0.021 |
woman | +0.020 |
stranger | +0.020 |
Neg logit contributions | |
ug | -0.018 |
issors | -0.017 |
usted | -0.017 |
bar | -0.016 |
bed | -0.016 |
Token | have |
Token ID | 423 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
relief | +0.032 |
gentleman | +0.032 |
Heidi | +0.031 |
woman | +0.031 |
stranger | +0.030 |
Neg logit contributions | |
ug | -0.022 |
issors | -0.021 |
built | -0.021 |
usted | -0.021 |
aved | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
relief | +0.053 |
gentleman | +0.050 |
lady | +0.050 |
woman | +0.049 |
cal | +0.048 |
Neg logit contributions | |
ug | -0.065 |
issors | -0.063 |
usted | -0.061 |
bar | -0.060 |
utes | -0.060 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
relief | +0.009 |
gentleman | +0.008 |
cal | +0.008 |
Heidi | +0.008 |
lady | +0.008 |
Neg logit contributions | |
issors | -0.009 |
ug | -0.009 |
utes | -0.009 |
om | -0.008 |
clubs | -0.008 |
Token | today |
Token ID | 1909 |
Feature activation | +4.59e-02 |
Pos logit contributions | |
relief | +0.304 |
cal | +0.298 |
Heidi | +0.293 |
gentleman | +0.291 |
stranger | +0.272 |
Neg logit contributions | |
ug | -0.151 |
usted | -0.148 |
issors | -0.146 |
utes | -0.145 |
bed | -0.142 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
relief | +0.097 |
gentleman | +0.095 |
Heidi | +0.090 |
cal | +0.089 |
stranger | +0.086 |
Neg logit contributions | |
ug | -0.049 |
utes | -0.048 |
often | -0.046 |
usted | -0.046 |
everywhere | -0.045 |
Token | Mom |
Token ID | 11254 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
relief | +0.021 |
gentleman | +0.020 |
stranger | +0.020 |
cal | +0.020 |
lady | +0.020 |
Neg logit contributions | |
issors | -0.014 |
ug | -0.013 |
utes | -0.012 |
usted | -0.012 |
bowl | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
relief | +0.068 |
gentleman | +0.062 |
gru | +0.060 |
stranger | +0.057 |
Heidi | +0.057 |
Neg logit contributions | |
usted | -0.048 |
om | -0.048 |
angles | -0.047 |
ors | -0.046 |
built | -0.045 |
Token | Dad |
Token ID | 17415 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
relief | +0.047 |
gentleman | +0.043 |
cal | +0.043 |
gen | +0.040 |
service | +0.039 |
Neg logit contributions | |
issors | -0.040 |
usted | -0.039 |
ug | -0.038 |
bar | -0.037 |
bowl | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
gentleman | +0.017 |
relief | +0.017 |
lady | +0.016 |
woman | +0.016 |
Heidi | +0.016 |
Neg logit contributions | |
ug | -0.009 |
bed | -0.009 |
ors | -0.009 |
often | -0.008 |
bowl | -0.008 |
Token | but |
Token ID | 475 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
ug | +0.020 |
usted | +0.018 |
bar | +0.018 |
issors | +0.018 |
bed | +0.017 |
Neg logit contributions | |
gentleman | -0.027 |
relief | -0.026 |
lady | -0.025 |
stranger | -0.025 |
woman | -0.025 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
gentleman | +0.013 |
relief | +0.013 |
lady | +0.012 |
woman | +0.012 |
stranger | +0.012 |
Neg logit contributions | |
ug | -0.010 |
bar | -0.009 |
issors | -0.009 |
bed | -0.009 |
utes | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
ug | +0.015 |
often | +0.014 |
bed | +0.013 |
ors | +0.013 |
igs | +0.012 |
Neg logit contributions | |
gentleman | -0.023 |
relief | -0.021 |
lady | -0.019 |
woman | -0.019 |
stranger | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
gentleman | +0.002 |
relief | +0.002 |
lady | +0.002 |
stranger | +0.002 |
woman | +0.002 |
Neg logit contributions | |
ug | -0.002 |
bed | -0.002 |
usted | -0.002 |
issors | -0.002 |
ors | -0.002 |
Token | endings |
Token ID | 38168 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
gentleman | +0.036 |
Heidi | +0.033 |
relief | +0.030 |
Debbie | +0.030 |
cal | +0.030 |
Neg logit contributions | |
ug | -0.031 |
hamm | -0.030 |
bar | -0.030 |
bed | -0.029 |
usted | -0.029 |
Token | are |
Token ID | 389 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
gentleman | +0.294 |
woman | +0.273 |
Heidi | +0.273 |
relief | +0.272 |
lady | +0.270 |
Neg logit contributions | |
ug | -0.193 |
ors | -0.168 |
often | -0.163 |
ir | -0.157 |
ert | -0.153 |
Token | not |
Token ID | 407 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
gentleman | +0.060 |
relief | +0.058 |
woman | +0.054 |
lady | +0.054 |
stranger | +0.053 |
Neg logit contributions | |
ug | -0.040 |
issors | -0.037 |
usted | -0.037 |
often | -0.037 |
bar | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
gentleman | +0.046 |
relief | +0.044 |
lady | +0.042 |
woman | +0.041 |
stranger | +0.039 |
Neg logit contributions | |
ug | -0.032 |
bar | -0.030 |
usted | -0.030 |
often | -0.028 |
issors | -0.028 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
relief | +0.006 |
gentleman | +0.005 |
lady | +0.005 |
stranger | +0.005 |
woman | +0.005 |
Neg logit contributions | |
ug | -0.005 |
issors | -0.005 |
bar | -0.004 |
usted | -0.004 |
bowl | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
relief | +0.021 |
gentleman | +0.020 |
lady | +0.019 |
woman | +0.019 |
cal | +0.019 |
Neg logit contributions | |
ug | -0.025 |
bowl | -0.023 |
bed | -0.023 |
usted | -0.023 |
issors | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
relief | +0.075 |
gentleman | +0.071 |
woman | +0.069 |
lady | +0.067 |
stranger | +0.067 |
Neg logit contributions | |
usted | -0.057 |
ug | -0.056 |
bar | -0.056 |
bed | -0.055 |
ors | -0.051 |
Token | there |
Token ID | 612 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
ug | +0.010 |
usted | +0.010 |
bar | +0.009 |
accidentally | +0.009 |
everywhere | +0.009 |
Neg logit contributions | |
relief | -0.014 |
cal | -0.013 |
MacDonald | -0.012 |
Lord | -0.012 |
service | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -8.44e-03 |
Pos logit contributions | |
ug | +0.025 |
bed | +0.024 |
bar | +0.023 |
usted | +0.022 |
rolled | +0.021 |
Neg logit contributions | |
relief | -0.041 |
gentleman | -0.039 |
cal | -0.038 |
service | -0.038 |
stranger | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
bar | +0.012 |
hamm | +0.012 |
usted | +0.011 |
ug | +0.011 |
bed | +0.010 |
Neg logit contributions | |
gentleman | -0.014 |
relief | -0.014 |
vation | -0.013 |
service | -0.013 |
woman | -0.013 |
Token | huge |
Token ID | 3236 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
Heidi | +0.017 |
ment | +0.016 |
relief | +0.016 |
gentleman | +0.015 |
Eva | +0.015 |
Neg logit contributions | |
hamm | -0.016 |
om | -0.015 |
hammer | -0.015 |
ug | -0.015 |
bar | -0.015 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Sleep | +0.019 |
Heidi | +0.019 |
ment | +0.019 |
cal | +0.018 |
Debbie | +0.018 |
Neg logit contributions | |
ug | -0.017 |
hammer | -0.017 |
om | -0.016 |
clubs | -0.016 |
bar | -0.016 |
Token | cake |
Token ID | 12187 |
Feature activation | +7.09e-02 |
Pos logit contributions | |
cal | +0.261 |
relief | +0.251 |
Heidi | +0.250 |
nods | +0.233 |
bluff | +0.229 |
Neg logit contributions | |
everywhere | -0.165 |
om | -0.157 |
bar | -0.153 |
clubs | -0.149 |
built | -0.146 |
Token | and |
Token ID | 290 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
relief | +0.150 |
cal | +0.144 |
gentleman | +0.130 |
Lord | +0.130 |
Heidi | +0.126 |
Neg logit contributions | |
bar | -0.080 |
bed | -0.080 |
everywhere | -0.079 |
usted | -0.074 |
ors | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
bar | +0.004 |
usted | +0.004 |
lots | +0.004 |
built | +0.004 |
bed | +0.004 |
Neg logit contributions | |
relief | -0.006 |
cal | -0.006 |
gentleman | -0.006 |
service | -0.005 |
Lord | -0.005 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
Heidi | +0.006 |
relief | +0.006 |
cal | +0.006 |
gentleman | +0.005 |
service | +0.005 |
Neg logit contributions | |
om | -0.006 |
bar | -0.006 |
utes | -0.006 |
hamm | -0.006 |
bowl | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
relief | +0.040 |
gentleman | +0.038 |
Heidi | +0.037 |
woman | +0.037 |
MacDonald | +0.036 |
Neg logit contributions | |
usted | -0.010 |
bar | -0.009 |
ug | -0.008 |
om | -0.008 |
issors | -0.008 |
Token | time |
Token ID | 640 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
relief | +0.010 |
lady | +0.009 |
gentleman | +0.009 |
woman | +0.009 |
cal | +0.009 |
Neg logit contributions | |
ug | -0.013 |
issors | -0.012 |
usted | -0.012 |
ors | -0.012 |
bar | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
relief | +0.060 |
gentleman | +0.056 |
woman | +0.055 |
lady | +0.055 |
cal | +0.054 |
Neg logit contributions | |
ug | -0.063 |
issors | -0.058 |
bed | -0.057 |
ors | -0.056 |
bar | -0.056 |
Token | there |
Token ID | 612 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
ug | +0.007 |
issors | +0.007 |
usted | +0.007 |
ors | +0.007 |
bar | +0.007 |
Neg logit contributions | |
relief | -0.005 |
lady | -0.005 |
gentleman | -0.005 |
woman | -0.005 |
stranger | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
ug | +0.051 |
bed | +0.048 |
issors | +0.046 |
bar | +0.046 |
usted | +0.046 |
Neg logit contributions | |
relief | -0.045 |
gentleman | -0.043 |
lady | -0.042 |
woman | -0.042 |
cal | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
relief | +0.003 |
lady | +0.003 |
gentleman | +0.003 |
woman | +0.003 |
cal | +0.003 |
Neg logit contributions | |
ug | -0.006 |
issors | -0.006 |
usted | -0.006 |
ors | -0.006 |
bar | -0.006 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
relief | +0.019 |
Heidi | +0.017 |
gentleman | +0.017 |
service | +0.017 |
cal | +0.017 |
Neg logit contributions | |
ug | -0.024 |
utes | -0.023 |
om | -0.022 |
bowl | -0.021 |
issors | -0.021 |
Token | party |
Token ID | 2151 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
relief | +0.286 |
cal | +0.277 |
Heidi | +0.258 |
confusion | +0.251 |
gentleman | +0.247 |
Neg logit contributions | |
ug | -0.159 |
utes | -0.150 |
om | -0.150 |
everywhere | -0.140 |
issors | -0.136 |
Token | in |
Token ID | 287 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
relief | +0.168 |
cal | +0.159 |
gentleman | +0.145 |
sigh | +0.140 |
Heidi | +0.140 |
Neg logit contributions | |
ug | -0.083 |
utes | -0.078 |
bed | -0.077 |
issors | -0.075 |
usted | -0.074 |
Token | a |
Token ID | 257 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
both | +0.032 |
lots | +0.031 |
issors | +0.028 |
hamm | +0.027 |
everywhere | +0.026 |
Neg logit contributions | |
gentleman | -0.061 |
cal | -0.059 |
relief | -0.055 |
stranger | -0.054 |
therapist | -0.054 |
Token | big |
Token ID | 1263 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ug | +0.016 |
issors | +0.016 |
utes | +0.015 |
usted | +0.015 |
bar | +0.015 |
Neg logit contributions | |
relief | -0.012 |
gentleman | -0.011 |
cal | -0.011 |
lady | -0.011 |
woman | -0.011 |
Token | hall |
Token ID | 6899 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
relief | +0.025 |
gentleman | +0.024 |
cal | +0.024 |
Heidi | +0.023 |
lady | +0.022 |
Neg logit contributions | |
ug | -0.021 |
bowl | -0.020 |
issors | -0.020 |
eds | -0.020 |
bar | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
relief | +0.001 |
lady | +0.001 |
gentleman | +0.001 |
woman | +0.001 |
cal | +0.001 |
Neg logit contributions | |
ug | -0.001 |
issors | -0.001 |
usted | -0.001 |
ors | -0.001 |
bar | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
relief | +0.045 |
lady | +0.042 |
gentleman | +0.042 |
woman | +0.041 |
cal | +0.041 |
Neg logit contributions | |
ug | -0.055 |
issors | -0.052 |
bed | -0.050 |
usted | -0.050 |
ors | -0.050 |
Token | there |
Token ID | 612 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
issors | +0.015 |
ug | +0.015 |
ors | +0.014 |
usted | +0.014 |
bar | +0.014 |
Neg logit contributions | |
relief | -0.008 |
lady | -0.008 |
woman | -0.008 |
stranger | -0.007 |
gentleman | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -1.03e-03 |
Pos logit contributions | |
ug | +0.057 |
issors | +0.054 |
bed | +0.053 |
usted | +0.053 |
bar | +0.052 |
Neg logit contributions | |
relief | -0.044 |
gentleman | -0.042 |
lady | -0.042 |
woman | -0.041 |
cal | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ug | +0.003 |
issors | +0.003 |
ors | +0.003 |
bar | +0.002 |
eds | +0.002 |
Neg logit contributions | |
relief | -0.001 |
lady | -0.001 |
woman | -0.001 |
stranger | -0.001 |
Heidi | -0.001 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
relief | +0.016 |
gentleman | +0.014 |
cal | +0.014 |
service | +0.014 |
Heidi | +0.014 |
Neg logit contributions | |
ug | -0.024 |
utes | -0.022 |
issors | -0.022 |
bowl | -0.021 |
bed | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -3.87e-03 |
Pos logit contributions | |
relief | +0.270 |
cal | +0.261 |
Heidi | +0.245 |
gentleman | +0.231 |
confusion | +0.230 |
Neg logit contributions | |
ug | -0.174 |
utes | -0.167 |
om | -0.165 |
everywhere | -0.153 |
issors | -0.152 |
Token | It |
Token ID | 632 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ug | +0.005 |
issors | +0.005 |
usted | +0.005 |
bed | +0.005 |
bowl | +0.005 |
Neg logit contributions | |
cal | -0.007 |
relief | -0.007 |
gentleman | -0.007 |
stranger | -0.006 |
lady | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
relief | +0.022 |
gentleman | +0.021 |
cal | +0.020 |
service | +0.019 |
stranger | +0.019 |
Neg logit contributions | |
bed | -0.012 |
bowl | -0.011 |
built | -0.011 |
often | -0.011 |
accidentally | -0.010 |
Token | unusual |
Token ID | 8468 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
relief | +0.002 |
lady | +0.002 |
gentleman | +0.002 |
woman | +0.002 |
stranger | +0.002 |
Neg logit contributions | |
ug | -0.003 |
issors | -0.003 |
ors | -0.003 |
usted | -0.003 |
bar | -0.003 |
Token | because |
Token ID | 780 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
relief | +0.031 |
cal | +0.029 |
gentleman | +0.028 |
Heidi | +0.027 |
woman | +0.026 |
Neg logit contributions | |
ug | -0.027 |
ors | -0.025 |
usted | -0.025 |
issors | -0.025 |
utes | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
ug | +0.009 |
bed | +0.009 |
bar | +0.008 |
usted | +0.008 |
ors | +0.008 |
Neg logit contributions | |
relief | -0.010 |
gentleman | -0.010 |
cal | -0.010 |
stranger | -0.010 |
service | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
relief | +0.007 |
gentleman | +0.007 |
cal | +0.007 |
service | +0.007 |
stranger | +0.006 |
Neg logit contributions | |
ug | -0.005 |
bar | -0.005 |
issors | -0.005 |
usted | -0.005 |
bed | -0.005 |
Token | Jack |
Token ID | 14295 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ug | +0.087 |
bar | +0.086 |
issors | +0.085 |
utes | +0.083 |
bed | +0.083 |
Neg logit contributions | |
relief | -0.094 |
cal | -0.087 |
witch | -0.083 |
stranger | -0.083 |
service | -0.083 |
Token | has |
Token ID | 468 |
Feature activation | +6.32e-03 |
Pos logit contributions | |
ug | +0.015 |
ors | +0.014 |
om | +0.014 |
bed | +0.014 |
bar | +0.013 |
Neg logit contributions | |
relief | -0.022 |
gentleman | -0.021 |
stranger | -0.021 |
woman | -0.020 |
pastor | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
relief | +0.009 |
gentleman | +0.009 |
lady | +0.009 |
woman | +0.009 |
cal | +0.008 |
Neg logit contributions | |
ug | -0.011 |
issors | -0.011 |
usted | -0.011 |
bar | -0.011 |
ors | -0.010 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
relief | +0.015 |
gentleman | +0.014 |
cal | +0.014 |
lady | +0.014 |
Heidi | +0.014 |
Neg logit contributions | |
issors | -0.017 |
ug | -0.017 |
bar | -0.017 |
utes | -0.016 |
bowl | -0.016 |
Token | today |
Token ID | 1909 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
relief | +0.265 |
cal | +0.259 |
Heidi | +0.248 |
gentleman | +0.247 |
woman | +0.238 |
Neg logit contributions | |
ug | -0.170 |
bar | -0.169 |
issors | -0.158 |
usted | -0.158 |
bowl | -0.154 |
Token | and |
Token ID | 290 |
Feature activation | +3.75e-03 |
Pos logit contributions | |
relief | +0.078 |
gentleman | +0.075 |
woman | +0.071 |
cal | +0.070 |
stranger | +0.068 |
Neg logit contributions | |
ug | -0.043 |
ors | -0.039 |
usted | -0.039 |
often | -0.039 |
bar | -0.038 |
Token | I |
Token ID | 314 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
relief | +0.006 |
gentleman | +0.006 |
cal | +0.006 |
lady | +0.005 |
woman | +0.005 |
Neg logit contributions | |
ug | -0.006 |
bed | -0.005 |
usted | -0.005 |
bar | -0.005 |
issors | -0.005 |
Token | don |
Token ID | 836 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
relief | +0.048 |
gentleman | +0.048 |
Heidi | +0.048 |
woman | +0.048 |
lady | +0.047 |
Neg logit contributions | |
ug | -0.029 |
bowl | -0.029 |
aved | -0.028 |
built | -0.027 |
bar | -0.026 |
Token | 't |
Token ID | 470 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
lady | +0.002 |
relief | +0.002 |
gentleman | +0.002 |
stranger | +0.002 |
cal | +0.002 |
Neg logit contributions | |
ug | -0.002 |
issors | -0.002 |
leys | -0.002 |
bowl | -0.002 |
eds | -0.002 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
relief | +0.008 |
cal | +0.007 |
Heidi | +0.006 |
gentleman | +0.006 |
service | +0.006 |
Neg logit contributions | |
ug | -0.019 |
bowl | -0.018 |
bar | -0.018 |
utes | -0.018 |
issors | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
lady | +0.047 |
woman | +0.046 |
relief | +0.044 |
gentleman | +0.042 |
witch | +0.042 |
Neg logit contributions | |
issors | -0.048 |
ug | -0.046 |
usted | -0.046 |
bar | -0.046 |
leys | -0.045 |
Token | She |
Token ID | 1375 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ug | +0.010 |
issors | +0.010 |
bed | +0.010 |
usted | +0.010 |
ors | +0.010 |
Neg logit contributions | |
relief | -0.009 |
gentleman | -0.008 |
lady | -0.008 |
cal | -0.008 |
stranger | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
relief | +0.029 |
gentleman | +0.028 |
cal | +0.028 |
lady | +0.027 |
stranger | +0.027 |
Neg logit contributions | |
ug | -0.019 |
bed | -0.018 |
issors | -0.017 |
bowl | -0.016 |
eds | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +6.41e-03 |
Pos logit contributions | |
ug | +0.061 |
issors | +0.059 |
ors | +0.057 |
usted | +0.057 |
bar | +0.056 |
Neg logit contributions | |
relief | -0.029 |
lady | -0.027 |
woman | -0.026 |
gentleman | -0.026 |
stranger | -0.025 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
relief | +0.010 |
gentleman | +0.009 |
cal | +0.009 |
lady | +0.009 |
service | +0.009 |
Neg logit contributions | |
ug | -0.011 |
issors | -0.010 |
utes | -0.010 |
bed | -0.010 |
bar | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
relief | +0.268 |
cal | +0.266 |
Heidi | +0.250 |
gentleman | +0.246 |
gru | +0.231 |
Neg logit contributions | |
issors | -0.164 |
ug | -0.163 |
bed | -0.158 |
om | -0.157 |
bowl | -0.156 |
Token | On |
Token ID | 1550 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
relief | +0.007 |
gentleman | +0.006 |
cal | +0.006 |
lady | +0.006 |
stranger | +0.006 |
Neg logit contributions | |
ug | -0.006 |
issors | -0.006 |
bed | -0.005 |
usted | -0.005 |
bowl | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
issors | +0.019 |
bed | +0.019 |
ug | +0.019 |
bar | +0.019 |
utes | +0.018 |
Neg logit contributions | |
relief | -0.019 |
gentleman | -0.019 |
cal | -0.018 |
stranger | -0.018 |
woman | -0.017 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
gentleman | +0.068 |
relief | +0.067 |
cal | +0.066 |
stranger | +0.063 |
Heidi | +0.062 |
Neg logit contributions | |
bed | -0.051 |
issors | -0.048 |
utes | -0.047 |
ug | -0.046 |
usted | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
relief | +0.254 |
cal | +0.245 |
gentleman | +0.234 |
gru | +0.218 |
Heidi | +0.218 |
Neg logit contributions | |
ug | -0.121 |
bed | -0.115 |
om | -0.112 |
issors | -0.108 |
bowl | -0.106 |
Token | Jane |
Token ID | 12091 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
ug | +0.033 |
issors | +0.032 |
bed | +0.030 |
usted | +0.030 |
ors | +0.029 |
Neg logit contributions | |
relief | -0.027 |
cal | -0.026 |
gentleman | -0.026 |
stranger | -0.024 |
woman | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
lady | +0.017 |
woman | +0.017 |
relief | +0.017 |
gentleman | +0.015 |
stranger | +0.015 |
Neg logit contributions | |
ug | -0.041 |
issors | -0.040 |
bar | -0.039 |
usted | -0.038 |
utes | -0.038 |
Token | Jane |
Token ID | 12091 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
relief | +0.003 |
gentleman | +0.003 |
woman | +0.003 |
cal | +0.003 |
lady | +0.003 |
Neg logit contributions | |
ug | -0.004 |
issors | -0.004 |
usted | -0.004 |
bed | -0.004 |
ors | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
relief | +0.038 |
lady | +0.037 |
gentleman | +0.036 |
woman | +0.036 |
cal | +0.035 |
Neg logit contributions | |
ug | -0.038 |
issors | -0.037 |
usted | -0.035 |
bar | -0.035 |
ors | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
ug | +0.057 |
issors | +0.055 |
usted | +0.053 |
bar | +0.053 |
ors | +0.053 |
Neg logit contributions | |
relief | -0.031 |
lady | -0.029 |
gentleman | -0.028 |
woman | -0.028 |
cal | -0.027 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
relief | +0.012 |
gentleman | +0.011 |
cal | +0.011 |
lady | +0.011 |
woman | +0.010 |
Neg logit contributions | |
ug | -0.013 |
issors | -0.013 |
utes | -0.013 |
bed | -0.012 |
bar | -0.012 |
Token | coming |
Token ID | 2406 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
relief | +0.257 |
cal | +0.256 |
Heidi | +0.239 |
gentleman | +0.237 |
pastor | +0.222 |
Neg logit contributions | |
issors | -0.177 |
ug | -0.174 |
bowl | -0.169 |
bed | -0.168 |
om | -0.167 |
Token | up |
Token ID | 510 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
relief | +0.131 |
lady | +0.130 |
gentleman | +0.126 |
woman | +0.126 |
stranger | +0.124 |
Neg logit contributions | |
ug | -0.091 |
issors | -0.085 |
usted | -0.081 |
bar | -0.081 |
ors | -0.080 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
relief | +0.069 |
gentleman | +0.065 |
lady | +0.064 |
woman | +0.063 |
cal | +0.063 |
Neg logit contributions | |
ug | -0.066 |
issors | -0.063 |
usted | -0.061 |
utes | -0.060 |
bed | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +8.00e-03 |
Pos logit contributions | |
bed | +0.024 |
usted | +0.024 |
issors | +0.023 |
ug | +0.023 |
everywhere | +0.023 |
Neg logit contributions | |
relief | -0.022 |
cal | -0.021 |
gentleman | -0.021 |
service | -0.020 |
payoff | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | -5.56e-03 |
Pos logit contributions | |
relief | +0.010 |
gentleman | +0.010 |
cal | +0.009 |
stranger | +0.009 |
lady | +0.009 |
Neg logit contributions | |
bed | -0.015 |
usted | -0.015 |
ug | -0.014 |
often | -0.014 |
bar | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +8.97e-03 |
Pos logit contributions | |
ug | +0.009 |
bed | +0.009 |
bowl | +0.009 |
usted | +0.009 |
leys | +0.008 |
Neg logit contributions | |
gentleman | -0.011 |
relief | -0.010 |
service | -0.010 |
lady | -0.010 |
cal | -0.010 |
Token | time |
Token ID | 640 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
relief | +0.013 |
gentleman | +0.013 |
lady | +0.013 |
woman | +0.012 |
cal | +0.012 |
Neg logit contributions | |
ug | -0.016 |
issors | -0.015 |
usted | -0.015 |
bed | -0.015 |
utes | -0.015 |
Token | there |
Token ID | 612 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
relief | +0.061 |
gentleman | +0.057 |
woman | +0.056 |
lady | +0.056 |
cal | +0.056 |
Neg logit contributions | |
ug | -0.060 |
issors | -0.055 |
bed | -0.055 |
ors | -0.054 |
bar | -0.053 |
Token | was |
Token ID | 373 |
Feature activation | +8.53e-05 |
Pos logit contributions | |
ug | +0.047 |
bed | +0.046 |
bowl | +0.043 |
bar | +0.042 |
ors | +0.042 |
Neg logit contributions | |
relief | -0.056 |
gentleman | -0.054 |
woman | -0.053 |
cal | -0.053 |
lady | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
relief | +0.000 |
gentleman | +0.000 |
lady | +0.000 |
woman | +0.000 |
cal | +0.000 |
Neg logit contributions | |
ug | -0.000 |
issors | -0.000 |
usted | -0.000 |
bed | -0.000 |
utes | -0.000 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
relief | +0.016 |
gentleman | +0.015 |
Heidi | +0.015 |
service | +0.015 |
cal | +0.015 |
Neg logit contributions | |
ug | -0.020 |
utes | -0.019 |
om | -0.019 |
issors | -0.018 |
bowl | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
relief | +0.276 |
cal | +0.264 |
Heidi | +0.250 |
confusion | +0.244 |
gentleman | +0.242 |
Neg logit contributions | |
ug | -0.156 |
utes | -0.151 |
om | -0.147 |
everywhere | -0.140 |
often | -0.138 |
Token | A |
Token ID | 317 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
issors | +0.005 |
ug | +0.005 |
bed | +0.004 |
usted | +0.004 |
om | +0.004 |
Neg logit contributions | |
cal | -0.009 |
gentleman | -0.008 |
relief | -0.008 |
stranger | -0.008 |
man | -0.008 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
relief | +0.050 |
Heidi | +0.049 |
cal | +0.048 |
ment | +0.045 |
handed | +0.044 |
Neg logit contributions | |
utes | -0.040 |
om | -0.039 |
accidentally | -0.039 |
hamm | -0.037 |
hammer | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
relief | +0.092 |
cal | +0.088 |
gentleman | +0.085 |
stranger | +0.083 |
Heidi | +0.082 |
Neg logit contributions | |
ug | -0.038 |
bed | -0.037 |
bowl | -0.034 |
om | -0.033 |
issors | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +7.91e-03 |
Pos logit contributions | |
ug | +0.043 |
issors | +0.042 |
usted | +0.041 |
bed | +0.041 |
bar | +0.040 |
Neg logit contributions | |
relief | -0.031 |
gentleman | -0.029 |
cal | -0.029 |
lady | -0.027 |
stranger | -0.027 |
Token | " |
Token ID | 1 |
Feature activation | -9.76e-04 |
Pos logit contributions | |
relief | +0.043 |
lady | +0.041 |
gentleman | +0.040 |
woman | +0.040 |
stranger | +0.039 |
Neg logit contributions | |
ug | -0.048 |
issors | -0.046 |
ors | -0.045 |
usted | -0.045 |
bed | -0.044 |
Token | Hey |
Token ID | 10814 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
bar | +0.001 |
issors | +0.001 |
utes | +0.001 |
bowl | +0.001 |
usted | +0.001 |
Neg logit contributions | |
relief | -0.002 |
cal | -0.002 |
service | -0.001 |
witch | -0.001 |
prayer | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
relief | +0.162 |
cal | +0.157 |
Lord | +0.156 |
woman | +0.156 |
gentleman | +0.155 |
Neg logit contributions | |
ug | -0.098 |
bar | -0.082 |
bed | -0.081 |
om | -0.080 |
ors | -0.079 |
Token | hey |
Token ID | 17207 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
relief | +0.033 |
gentleman | +0.031 |
service | +0.030 |
cal | +0.030 |
title | +0.029 |
Neg logit contributions | |
ug | -0.035 |
bar | -0.034 |
issors | -0.033 |
bowl | -0.031 |
usted | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
relief | +0.272 |
gentleman | +0.270 |
woman | +0.258 |
stranger | +0.255 |
cal | +0.255 |
Neg logit contributions | |
ug | -0.186 |
bed | -0.162 |
ors | -0.159 |
eds | -0.155 |
usted | -0.152 |
Token | hey |
Token ID | 17207 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
gentleman | +0.046 |
woman | +0.044 |
relief | +0.042 |
Heidi | +0.041 |
lady | +0.041 |
Neg logit contributions | |
ug | -0.053 |
bar | -0.050 |
issors | -0.050 |
usted | -0.048 |
hamm | -0.047 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
gentleman | +0.285 |
relief | +0.278 |
woman | +0.269 |
stranger | +0.266 |
lady | +0.261 |
Neg logit contributions | |
ug | -0.181 |
bed | -0.153 |
eds | -0.152 |
ors | -0.151 |
usted | -0.145 |
Token | he |
Token ID | 339 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
relief | +0.038 |
gentleman | +0.037 |
cal | +0.037 |
service | +0.036 |
stranger | +0.035 |
Neg logit contributions | |
ug | -0.033 |
issors | -0.031 |
bed | -0.031 |
bar | -0.030 |
usted | -0.029 |
Token | yelled |
Token ID | 22760 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
ug | +0.018 |
usted | +0.017 |
issors | +0.017 |
bed | +0.016 |
ors | +0.016 |
Neg logit contributions | |
relief | -0.018 |
gentleman | -0.017 |
service | -0.016 |
woman | -0.016 |
lady | -0.016 |
Token | at |
Token ID | 379 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
relief | +0.014 |
gentleman | +0.013 |
woman | +0.013 |
service | +0.013 |
stranger | +0.013 |
Neg logit contributions | |
ug | -0.013 |
bed | -0.012 |
usted | -0.012 |
ors | -0.012 |
issors | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
relief | +0.024 |
gentleman | +0.023 |
cal | +0.023 |
service | +0.022 |
lady | +0.022 |
Neg logit contributions | |
ug | -0.018 |
bed | -0.016 |
issors | -0.016 |
ors | -0.016 |
ir | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ug | +0.111 |
issors | +0.105 |
bar | +0.103 |
usted | +0.102 |
ors | +0.102 |
Neg logit contributions | |
relief | -0.065 |
lady | -0.065 |
gentleman | -0.061 |
woman | -0.061 |
cal | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
ug | +0.026 |
issors | +0.025 |
bar | +0.025 |
ors | +0.025 |
usted | +0.025 |
Neg logit contributions | |
lady | -0.014 |
relief | -0.013 |
gentleman | -0.013 |
woman | -0.013 |
stranger | -0.012 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
relief | +0.005 |
lady | +0.005 |
gentleman | +0.005 |
woman | +0.005 |
stranger | +0.005 |
Neg logit contributions | |
ug | -0.006 |
issors | -0.005 |
ors | -0.005 |
bar | -0.005 |
utes | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
gentleman | +0.054 |
relief | +0.053 |
stranger | +0.050 |
woman | +0.050 |
service | +0.050 |
Neg logit contributions | |
ug | -0.039 |
bed | -0.036 |
usted | -0.034 |
bar | -0.033 |
ors | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
gentleman | +0.035 |
cal | +0.034 |
relief | +0.033 |
service | +0.032 |
Lord | +0.032 |
Neg logit contributions | |
bed | -0.034 |
ug | -0.032 |
accidentally | -0.032 |
usted | -0.031 |
bar | -0.030 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
gentleman | +0.052 |
Heidi | +0.050 |
relief | +0.050 |
cal | +0.049 |
MacDonald | +0.047 |
Neg logit contributions | |
usted | -0.047 |
bricks | -0.046 |
cubes | -0.046 |
bar | -0.046 |
everywhere | -0.045 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
relief | +0.224 |
cal | +0.221 |
gentleman | +0.216 |
Heidi | +0.205 |
bluff | +0.202 |
Neg logit contributions | |
usted | -0.189 |
accidentally | -0.183 |
built | -0.181 |
om | -0.178 |
ug | -0.178 |
Token | 's |
Token ID | 338 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
relief | +0.032 |
gentleman | +0.030 |
service | +0.029 |
cal | +0.029 |
lady | +0.028 |
Neg logit contributions | |
bed | -0.021 |
ug | -0.020 |
usted | -0.020 |
bar | -0.019 |
accidentally | -0.019 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
bed | +0.057 |
ug | +0.056 |
usted | +0.056 |
om | +0.054 |
issors | +0.053 |
Neg logit contributions | |
gentleman | -0.070 |
Heidi | -0.066 |
relief | -0.066 |
cal | -0.065 |
MacDonald | -0.064 |
Token | said |
Token ID | 531 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
relief | +0.046 |
gentleman | +0.044 |
lady | +0.043 |
woman | +0.042 |
stranger | +0.042 |
Neg logit contributions | |
ug | -0.050 |
issors | -0.047 |
usted | -0.047 |
bar | -0.046 |
bed | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
ug | +0.015 |
bed | +0.015 |
usted | +0.014 |
bar | +0.014 |
issors | +0.014 |
Neg logit contributions | |
relief | -0.020 |
gentleman | -0.020 |
cal | -0.019 |
woman | -0.019 |
lady | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.50e-04 |
Pos logit contributions | |
ug | +0.095 |
bar | +0.089 |
ors | +0.088 |
utes | +0.088 |
issors | +0.088 |
Neg logit contributions | |
lady | -0.041 |
relief | -0.041 |
woman | -0.037 |
gentleman | -0.035 |
stranger | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +2.36e-03 |
Pos logit contributions | |
ug | +0.001 |
issors | +0.001 |
usted | +0.001 |
utes | +0.001 |
bar | +0.001 |
Neg logit contributions | |
relief | -0.000 |
lady | -0.000 |
woman | -0.000 |
gentleman | -0.000 |
stranger | -0.000 |
Token | It |
Token ID | 632 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
lady | +0.002 |
relief | +0.002 |
woman | +0.001 |
gentleman | +0.001 |
girl | +0.001 |
Neg logit contributions | |
ug | -0.006 |
eds | -0.006 |
utes | -0.006 |
bar | -0.006 |
ors | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
relief | +0.026 |
gentleman | +0.024 |
lady | +0.024 |
woman | +0.024 |
cal | +0.023 |
Neg logit contributions | |
ug | -0.032 |
issors | -0.031 |
bed | -0.030 |
usted | -0.030 |
bar | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
relief | +0.011 |
lady | +0.011 |
woman | +0.011 |
cal | +0.010 |
gentleman | +0.010 |
Neg logit contributions | |
ug | -0.022 |
ors | -0.021 |
issors | -0.021 |
utes | -0.020 |
bar | -0.020 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
relief | +0.061 |
gentleman | +0.058 |
cal | +0.057 |
lady | +0.056 |
woman | +0.055 |
Neg logit contributions | |
ug | -0.060 |
issors | -0.058 |
utes | -0.056 |
usted | -0.055 |
bed | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
relief | +0.270 |
cal | +0.262 |
gentleman | +0.255 |
Heidi | +0.243 |
stranger | +0.241 |
Neg logit contributions | |
ug | -0.176 |
issors | -0.166 |
bed | -0.164 |
usted | -0.160 |
bowl | -0.153 |
Token | she |
Token ID | 673 |
Feature activation | -4.91e-03 |
Pos logit contributions | |
relief | +0.027 |
cal | +0.026 |
gentleman | +0.026 |
service | +0.024 |
stranger | +0.024 |
Neg logit contributions | |
bed | -0.036 |
ug | -0.035 |
usted | -0.035 |
issors | -0.034 |
bar | -0.034 |
Token | was |
Token ID | 373 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
ug | +0.007 |
bed | +0.007 |
issors | +0.007 |
usted | +0.007 |
ors | +0.007 |
Neg logit contributions | |
relief | -0.009 |
gentleman | -0.008 |
lady | -0.008 |
cal | -0.008 |
stranger | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ug | +0.003 |
issors | +0.002 |
usted | +0.002 |
ors | +0.002 |
bar | +0.002 |
Neg logit contributions | |
relief | -0.003 |
lady | -0.003 |
gentleman | -0.003 |
woman | -0.003 |
cal | -0.003 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
relief | +0.022 |
gentleman | +0.020 |
cal | +0.020 |
Heidi | +0.020 |
woman | +0.019 |
Neg logit contributions | |
ug | -0.023 |
issors | -0.021 |
utes | -0.021 |
om | -0.021 |
usted | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
relief | +0.013 |
cal | +0.013 |
gentleman | +0.013 |
Heidi | +0.013 |
MacDonald | +0.012 |
Neg logit contributions | |
ug | -0.006 |
bowl | -0.004 |
utes | -0.004 |
om | -0.004 |
issors | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
relief | +0.120 |
cal | +0.114 |
woman | +0.110 |
witch | +0.110 |
Fairy | +0.108 |
Neg logit contributions | |
ug | -0.071 |
usted | -0.065 |
bed | -0.062 |
issors | -0.062 |
om | -0.061 |
Token | it |
Token ID | 340 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
relief | +0.030 |
cal | +0.029 |
witch | +0.028 |
Fairy | +0.028 |
gentleman | +0.027 |
Neg logit contributions | |
issors | -0.027 |
usted | -0.027 |
ug | -0.027 |
bar | -0.026 |
bed | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
relief | +0.060 |
gentleman | +0.057 |
woman | +0.055 |
lady | +0.054 |
service | +0.054 |
Neg logit contributions | |
ug | -0.052 |
usted | -0.051 |
bed | -0.050 |
issors | -0.049 |
bar | -0.048 |
Token | his |
Token ID | 465 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
ug | +0.005 |
issors | +0.005 |
ors | +0.005 |
usted | +0.005 |
utes | +0.005 |
Neg logit contributions | |
relief | -0.004 |
lady | -0.004 |
woman | -0.004 |
gentleman | -0.004 |
cal | -0.004 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
relief | +0.015 |
gentleman | +0.014 |
lady | +0.014 |
cal | +0.013 |
woman | +0.013 |
Neg logit contributions | |
ug | -0.015 |
issors | -0.014 |
utes | -0.013 |
usted | -0.013 |
bar | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
relief | +0.274 |
cal | +0.261 |
Heidi | +0.254 |
gentleman | +0.250 |
gru | +0.235 |
Neg logit contributions | |
ug | -0.163 |
issors | -0.158 |
bar | -0.158 |
usted | -0.157 |
everywhere | -0.155 |
Token | He |
Token ID | 679 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
relief | +0.019 |
witch | +0.018 |
cal | +0.018 |
woman | +0.018 |
Fairy | +0.018 |
Neg logit contributions | |
issors | -0.015 |
usted | -0.014 |
ug | -0.014 |
bar | -0.013 |
om | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
relief | +0.015 |
gentleman | +0.013 |
cal | +0.013 |
service | +0.013 |
Heidi | +0.013 |
Neg logit contributions | |
ug | -0.010 |
usted | -0.010 |
bed | -0.009 |
issors | -0.009 |
ors | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
relief | +0.018 |
gentleman | +0.017 |
lady | +0.017 |
woman | +0.017 |
cal | +0.017 |
Neg logit contributions | |
ug | -0.013 |
issors | -0.012 |
usted | -0.012 |
bed | -0.011 |
bar | -0.011 |
Token | excited |
Token ID | 6568 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
relief | +0.028 |
gentleman | +0.026 |
cal | +0.026 |
woman | +0.025 |
Heidi | +0.025 |
Neg logit contributions | |
ug | -0.030 |
issors | -0.029 |
usted | -0.028 |
utes | -0.028 |
om | -0.028 |
Token | " |
Token ID | 1 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
relief | +0.037 |
lady | +0.036 |
gentleman | +0.035 |
woman | +0.035 |
cal | +0.034 |
Neg logit contributions | |
ug | -0.036 |
issors | -0.034 |
usted | -0.033 |
ors | -0.033 |
bar | -0.032 |
Token | Hey |
Token ID | 10814 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
relief | +0.015 |
gentleman | +0.014 |
service | +0.013 |
cal | +0.013 |
prayer | +0.013 |
Neg logit contributions | |
usted | -0.016 |
issors | -0.015 |
ug | -0.015 |
bed | -0.015 |
utes | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
relief | +0.146 |
gentleman | +0.146 |
woman | +0.144 |
cal | +0.140 |
lady | +0.137 |
Neg logit contributions | |
ug | -0.110 |
bed | -0.098 |
ors | -0.095 |
issors | -0.094 |
usted | -0.092 |
Token | hey |
Token ID | 17207 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
gentleman | +0.026 |
relief | +0.026 |
woman | +0.025 |
lady | +0.024 |
cal | +0.024 |
Neg logit contributions | |
ug | -0.032 |
issors | -0.031 |
usted | -0.030 |
bar | -0.030 |
bed | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
relief | +0.255 |
gentleman | +0.252 |
woman | +0.242 |
stranger | +0.239 |
cal | +0.237 |
Neg logit contributions | |
ug | -0.176 |
bed | -0.161 |
ors | -0.159 |
eds | -0.157 |
usted | -0.153 |
Token | hey |
Token ID | 17207 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
gentleman | +0.038 |
woman | +0.037 |
relief | +0.036 |
lady | +0.036 |
cal | +0.034 |
Neg logit contributions | |
ug | -0.053 |
issors | -0.051 |
usted | -0.049 |
bed | -0.049 |
bar | -0.048 |
Token | ! |
Token ID | 0 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
gentleman | +0.270 |
relief | +0.270 |
woman | +0.259 |
stranger | +0.254 |
lady | +0.253 |
Neg logit contributions | |
ug | -0.181 |
eds | -0.164 |
ors | -0.163 |
bed | -0.163 |
usted | -0.155 |
Token | What |
Token ID | 1867 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
relief | +0.039 |
lady | +0.037 |
gentleman | +0.037 |
woman | +0.036 |
cal | +0.036 |
Neg logit contributions | |
ug | -0.046 |
issors | -0.045 |
usted | -0.043 |
ors | -0.042 |
bar | -0.042 |
Token | is |
Token ID | 318 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
relief | +0.144 |
lady | +0.138 |
gentleman | +0.134 |
woman | +0.133 |
cal | +0.132 |
Neg logit contributions | |
ug | -0.190 |
issors | -0.183 |
usted | -0.176 |
bar | -0.176 |
ors | -0.175 |
Token | going |
Token ID | 1016 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
relief | +0.030 |
lady | +0.029 |
gentleman | +0.028 |
woman | +0.028 |
stranger | +0.027 |
Neg logit contributions | |
ug | -0.041 |
issors | -0.039 |
usted | -0.038 |
bar | -0.038 |
ors | -0.038 |
Token | on |
Token ID | 319 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
relief | +0.050 |
lady | +0.048 |
gentleman | +0.048 |
woman | +0.047 |
cal | +0.047 |
Neg logit contributions | |
ug | -0.037 |
issors | -0.035 |
usted | -0.033 |
bar | -0.033 |
ors | -0.033 |
Token | ! |
Token ID | 0 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
relief | +0.223 |
gentleman | +0.219 |
cal | +0.218 |
Heidi | +0.214 |
pastor | +0.202 |
Neg logit contributions | |
usted | -0.143 |
everywhere | -0.143 |
bed | -0.142 |
bar | -0.142 |
ug | -0.137 |
Token | There |
Token ID | 1318 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
ug | +0.023 |
issors | +0.022 |
usted | +0.021 |
bed | +0.021 |
utes | +0.021 |
Neg logit contributions | |
relief | -0.022 |
gentleman | -0.021 |
lady | -0.021 |
stranger | -0.020 |
cal | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
gentleman | +0.017 |
relief | +0.017 |
stranger | +0.016 |
lady | +0.016 |
cal | +0.015 |
Neg logit contributions | |
ug | -0.011 |
bed | -0.010 |
usted | -0.010 |
bar | -0.010 |
bowl | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +9.94e-03 |
Pos logit contributions | |
usted | +0.011 |
bed | +0.011 |
bar | +0.011 |
ug | +0.011 |
hamm | +0.010 |
Neg logit contributions | |
gentleman | -0.013 |
relief | -0.013 |
stranger | -0.012 |
cal | -0.012 |
woman | -0.012 |
Token | big |
Token ID | 1263 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
relief | +0.014 |
gentleman | +0.014 |
Heidi | +0.014 |
cal | +0.014 |
service | +0.013 |
Neg logit contributions | |
ug | -0.015 |
utes | -0.015 |
bar | -0.015 |
issors | -0.015 |
bed | -0.015 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Heidi | +0.039 |
gentleman | +0.039 |
cal | +0.039 |
pastor | +0.038 |
relief | +0.037 |
Neg logit contributions | |
ug | -0.036 |
bed | -0.036 |
bar | -0.035 |
clubs | -0.035 |
om | -0.034 |
Token | party |
Token ID | 2151 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
cal | +0.258 |
relief | +0.252 |
Heidi | +0.244 |
gentleman | +0.237 |
Lord | +0.228 |
Neg logit contributions | |
everywhere | -0.163 |
usted | -0.151 |
built | -0.151 |
bar | -0.150 |
om | -0.150 |
Token | waiting |
Token ID | 4953 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
relief | +0.151 |
cal | +0.145 |
gentleman | +0.131 |
Lord | +0.127 |
nods | +0.127 |
Neg logit contributions | |
usted | -0.076 |
ug | -0.075 |
bed | -0.074 |
everywhere | -0.071 |
built | -0.070 |
Token | for |
Token ID | 329 |
Feature activation | +2.01e-03 |
Pos logit contributions | |
relief | +0.115 |
gentleman | +0.112 |
cal | +0.109 |
woman | +0.106 |
Heidi | +0.106 |
Neg logit contributions | |
usted | -0.035 |
ug | -0.034 |
utes | -0.032 |
issors | -0.031 |
everywhere | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
gentleman | +0.004 |
cal | +0.003 |
stranger | +0.003 |
relief | +0.003 |
woman | +0.003 |
Neg logit contributions | |
ug | -0.003 |
bed | -0.003 |
ir | -0.003 |
issors | -0.003 |
eds | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +6.59e-03 |
Pos logit contributions | |
ug | +0.017 |
bed | +0.017 |
utes | +0.017 |
usted | +0.017 |
ors | +0.017 |
Neg logit contributions | |
relief | -0.022 |
gentleman | -0.020 |
cal | -0.020 |
Heidi | -0.020 |
stranger | -0.019 |
Token | do |
Token ID | 466 |
Feature activation | +5.54e-03 |
Pos logit contributions | |
relief | +0.032 |
lady | +0.029 |
man | +0.026 |
woman | +0.025 |
witch | +0.024 |
Neg logit contributions | |
ug | -0.080 |
ors | -0.076 |
utes | -0.076 |
usted | -0.073 |
ants | -0.073 |
Token | ? |
Token ID | 30 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
relief | +0.010 |
gentleman | +0.009 |
woman | +0.009 |
cal | +0.009 |
lady | +0.009 |
Neg logit contributions | |
ug | -0.008 |
issors | -0.008 |
ors | -0.008 |
bed | -0.008 |
utes | -0.008 |
Token | This |
Token ID | 770 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
relief | +0.032 |
stranger | +0.030 |
lady | +0.030 |
gentleman | +0.030 |
cal | +0.030 |
Neg logit contributions | |
issors | -0.033 |
ug | -0.033 |
bed | -0.030 |
usted | -0.030 |
bar | -0.030 |
Token | is |
Token ID | 318 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
gentleman | +0.087 |
relief | +0.085 |
cal | +0.077 |
Heidi | +0.073 |
gru | +0.071 |
Neg logit contributions | |
issors | -0.056 |
om | -0.056 |
built | -0.055 |
usted | -0.054 |
angles | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
gentleman | +0.044 |
relief | +0.043 |
woman | +0.042 |
lady | +0.041 |
stranger | +0.041 |
Neg logit contributions | |
issors | -0.040 |
ug | -0.039 |
bar | -0.037 |
usted | -0.036 |
ors | -0.035 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
issors | +0.012 |
ug | +0.012 |
bar | +0.011 |
utes | +0.011 |
eds | +0.011 |
Neg logit contributions | |
gentleman | -0.009 |
relief | -0.009 |
cal | -0.008 |
Heidi | -0.008 |
lady | -0.008 |
Token | cake |
Token ID | 12187 |
Feature activation | +6.96e-02 |
Pos logit contributions | |
relief | +0.227 |
cal | +0.224 |
gentleman | +0.223 |
Heidi | +0.221 |
gru | +0.200 |
Neg logit contributions | |
issors | -0.187 |
bar | -0.183 |
ug | -0.183 |
usted | -0.177 |
om | -0.174 |
Token | for |
Token ID | 329 |
Feature activation | +3.50e-03 |
Pos logit contributions | |
relief | +0.138 |
gentleman | +0.128 |
cal | +0.128 |
woman | +0.122 |
Heidi | +0.120 |
Neg logit contributions | |
issors | -0.087 |
bar | -0.086 |
ug | -0.086 |
ors | -0.082 |
eds | -0.081 |
Token | Mrs |
Token ID | 9074 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
gentleman | +0.006 |
relief | +0.006 |
woman | +0.006 |
cal | +0.006 |
stranger | +0.006 |
Neg logit contributions | |
ug | -0.005 |
issors | -0.005 |
utes | -0.005 |
eds | -0.005 |
usted | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e-03 |
Pos logit contributions | |
relief | +0.026 |
cal | +0.023 |
relieved | +0.021 |
gentleman | +0.021 |
vation | +0.021 |
Neg logit contributions | |
ug | -0.019 |
ors | -0.018 |
issors | -0.017 |
ants | -0.017 |
ert | -0.016 |
Token | Lee |
Token ID | 5741 |
Feature activation | -1.17e-03 |
Pos logit contributions | |
bar | +0.004 |
issors | +0.004 |
om | +0.004 |
ree | +0.003 |
ert | +0.003 |
Neg logit contributions | |
cal | -0.004 |
relief | -0.004 |
stranger | -0.004 |
amused | -0.003 |
relieved | -0.003 |
Token | twins |
Token ID | 20345 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
lady | +0.065 |
relief | +0.062 |
woman | +0.062 |
stranger | +0.059 |
service | +0.059 |
Neg logit contributions | |
ug | -0.085 |
ors | -0.084 |
issors | -0.083 |
bar | -0.082 |
bed | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
relief | +0.051 |
gentleman | +0.048 |
Heidi | +0.046 |
stranger | +0.046 |
woman | +0.044 |
Neg logit contributions | |
ug | -0.038 |
bed | -0.038 |
ors | -0.036 |
usted | -0.036 |
eds | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | +1.89e-03 |
Pos logit contributions | |
ug | +0.020 |
issors | +0.019 |
usted | +0.018 |
bed | +0.018 |
utes | +0.018 |
Neg logit contributions | |
relief | -0.025 |
lady | -0.024 |
gentleman | -0.024 |
woman | -0.024 |
cal | -0.023 |
Token | have |
Token ID | 423 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
relief | +0.004 |
gentleman | +0.004 |
cal | +0.003 |
woman | +0.003 |
stranger | +0.003 |
Neg logit contributions | |
issors | -0.002 |
ug | -0.002 |
built | -0.002 |
often | -0.002 |
bowl | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
relief | +0.039 |
gentleman | +0.036 |
cal | +0.035 |
lady | +0.034 |
stranger | +0.033 |
Neg logit contributions | |
ug | -0.048 |
issors | -0.046 |
usted | -0.046 |
utes | -0.046 |
bar | -0.046 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
relief | +0.002 |
gentleman | +0.002 |
cal | +0.002 |
Heidi | +0.001 |
lady | +0.001 |
Neg logit contributions | |
utes | -0.002 |
issors | -0.002 |
ug | -0.002 |
bowl | -0.002 |
om | -0.002 |
Token | today |
Token ID | 1909 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
relief | +0.278 |
cal | +0.264 |
gentleman | +0.256 |
Heidi | +0.253 |
stranger | +0.240 |
Neg logit contributions | |
ug | -0.167 |
utes | -0.164 |
issors | -0.163 |
usted | -0.161 |
bed | -0.156 |
Token | . |
Token ID | 13 |
Feature activation | -6.54e-03 |
Pos logit contributions | |
relief | +0.085 |
gentleman | +0.080 |
cal | +0.079 |
gru | +0.076 |
Heidi | +0.075 |
Neg logit contributions | |
utes | -0.037 |
om | -0.037 |
often | -0.037 |
ug | -0.035 |
everywhere | -0.035 |
Token | Mom |
Token ID | 11254 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ug | +0.011 |
issors | +0.011 |
usted | +0.010 |
bed | +0.010 |
utes | +0.010 |
Neg logit contributions | |
relief | -0.010 |
lady | -0.010 |
gentleman | -0.010 |
woman | -0.010 |
cal | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
relief | +0.066 |
gentleman | +0.060 |
stranger | +0.056 |
gru | +0.055 |
woman | +0.055 |
Neg logit contributions | |
usted | -0.054 |
ors | -0.053 |
angles | -0.053 |
om | -0.053 |
issors | -0.052 |
Token | Dad |
Token ID | 17415 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
relief | +0.021 |
lady | +0.020 |
gentleman | +0.020 |
woman | +0.019 |
cal | +0.019 |
Neg logit contributions | |
ug | -0.038 |
issors | -0.037 |
usted | -0.036 |
ors | -0.035 |
bar | -0.035 |
Token | day |
Token ID | 1110 |
Feature activation | +6.04e-02 |
Pos logit contributions | |
relief | +0.022 |
gentleman | +0.021 |
cal | +0.021 |
Heidi | +0.021 |
MacDonald | +0.020 |
Neg logit contributions | |
ug | -0.009 |
om | -0.008 |
utes | -0.007 |
bowl | -0.007 |
issors | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
relief | +0.129 |
gentleman | +0.126 |
cal | +0.122 |
woman | +0.121 |
witch | +0.114 |
Neg logit contributions | |
ug | -0.069 |
bed | -0.069 |
usted | -0.063 |
utes | -0.059 |
om | -0.058 |
Token | it |
Token ID | 340 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
gentleman | +0.040 |
relief | +0.039 |
cal | +0.039 |
woman | +0.036 |
service | +0.035 |
Neg logit contributions | |
bed | -0.025 |
usted | -0.024 |
utes | -0.023 |
both | -0.023 |
everywhere | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +1.16e-03 |
Pos logit contributions | |
relief | +0.062 |
gentleman | +0.060 |
woman | +0.057 |
lady | +0.056 |
cal | +0.055 |
Neg logit contributions | |
ug | -0.061 |
usted | -0.059 |
bed | -0.058 |
issors | -0.058 |
bar | -0.056 |
Token | their |
Token ID | 511 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
relief | +0.002 |
lady | +0.002 |
cal | +0.001 |
woman | +0.001 |
stranger | +0.001 |
Neg logit contributions | |
ug | -0.002 |
issors | -0.002 |
ors | -0.002 |
bar | -0.002 |
utes | -0.002 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
relief | +0.046 |
gentleman | +0.042 |
cal | +0.042 |
lady | +0.040 |
woman | +0.040 |
Neg logit contributions | |
ug | -0.052 |
issors | -0.051 |
utes | -0.050 |
usted | -0.048 |
bed | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
relief | +0.276 |
cal | +0.256 |
gentleman | +0.256 |
Heidi | +0.255 |
gru | +0.238 |
Neg logit contributions | |
usted | -0.158 |
ug | -0.156 |
om | -0.152 |
everywhere | -0.152 |
issors | -0.151 |
Token | They |
Token ID | 1119 |
Feature activation | +9.88e-03 |
Pos logit contributions | |
gentleman | +0.020 |
service | +0.020 |
cal | +0.020 |
woman | +0.020 |
relief | +0.019 |
Neg logit contributions | |
issors | -0.016 |
bed | -0.015 |
usted | -0.015 |
ug | -0.015 |
bowl | -0.014 |
Token | were |
Token ID | 547 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
relief | +0.019 |
gentleman | +0.018 |
cal | +0.018 |
lady | +0.018 |
woman | +0.017 |
Neg logit contributions | |
ug | -0.013 |
usted | -0.012 |
issors | -0.012 |
bed | -0.011 |
ors | -0.011 |
Token | very |
Token ID | 845 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
relief | +0.032 |
lady | +0.031 |
gentleman | +0.030 |
woman | +0.030 |
stranger | +0.030 |
Neg logit contributions | |
ug | -0.023 |
issors | -0.022 |
bar | -0.021 |
ors | -0.021 |
usted | -0.021 |
Token | happy |
Token ID | 3772 |
Feature activation | +3.31e-02 |
Pos logit contributions | |
relief | +0.027 |
gentleman | +0.027 |
cal | +0.025 |
woman | +0.025 |
lady | +0.025 |
Neg logit contributions | |
ug | -0.033 |
issors | -0.031 |
usted | -0.031 |
utes | -0.030 |
om | -0.030 |
Token | games |
Token ID | 1830 |
Feature activation | +5.08e-02 |
Pos logit contributions | |
usted | +0.006 |
ug | +0.006 |
clubs | +0.006 |
bar | +0.006 |
bowl | +0.006 |
Neg logit contributions | |
relief | -0.011 |
gentleman | -0.010 |
cal | -0.010 |
Heidi | -0.010 |
lady | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
relief | +0.094 |
cal | +0.086 |
gentleman | +0.085 |
woman | +0.083 |
Lord | +0.082 |
Neg logit contributions | |
ug | -0.072 |
clubs | -0.070 |
usted | -0.070 |
issors | -0.069 |
bed | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
usted | +0.025 |
ug | +0.024 |
clubs | +0.023 |
bed | +0.023 |
bar | +0.022 |
Neg logit contributions | |
relief | -0.044 |
gentleman | -0.043 |
stranger | -0.041 |
woman | -0.040 |
Heidi | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
relief | +0.018 |
gentleman | +0.018 |
cal | +0.017 |
Heidi | +0.017 |
lady | +0.016 |
Neg logit contributions | |
ug | -0.011 |
usted | -0.011 |
bar | -0.010 |
bed | -0.009 |
hamm | -0.009 |
Token | giant |
Token ID | 6175 |
Feature activation | +4.24e-03 |
Pos logit contributions | |
relief | +0.019 |
Heidi | +0.018 |
gentleman | +0.018 |
cal | +0.018 |
service | +0.017 |
Neg logit contributions | |
bar | -0.018 |
ug | -0.018 |
utes | -0.018 |
bowl | -0.017 |
issors | -0.017 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
relief | +0.008 |
cal | +0.007 |
Heidi | +0.007 |
gentleman | +0.007 |
Lord | +0.007 |
Neg logit contributions | |
ug | -0.006 |
bar | -0.006 |
bowl | -0.006 |
bed | -0.006 |
clubs | -0.006 |
Token | cake |
Token ID | 12187 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
relief | +0.244 |
cal | +0.232 |
Heidi | +0.228 |
gentleman | +0.213 |
Lord | +0.204 |
Neg logit contributions | |
clubs | -0.186 |
usted | -0.183 |
ug | -0.183 |
bar | -0.182 |
utes | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
relief | +0.140 |
cal | +0.129 |
gentleman | +0.119 |
Heidi | +0.117 |
Lord | +0.115 |
Neg logit contributions | |
bar | -0.090 |
bed | -0.089 |
usted | -0.088 |
ug | -0.087 |
utes | -0.087 |
Token | The |
Token ID | 383 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
relief | +0.002 |
lady | +0.002 |
gentleman | +0.002 |
woman | +0.002 |
cal | +0.002 |
Neg logit contributions | |
ug | -0.002 |
issors | -0.002 |
usted | -0.002 |
ors | -0.002 |
bar | -0.002 |
Token | kids |
Token ID | 3988 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
Heidi | +0.022 |
relief | +0.021 |
cal | +0.020 |
gentleman | +0.020 |
ment | +0.019 |
Neg logit contributions | |
cubes | -0.020 |
usted | -0.019 |
bowl | -0.019 |
bricks | -0.018 |
clubs | -0.018 |
Token | were |
Token ID | 547 |
Feature activation | +6.22e-03 |
Pos logit contributions | |
relief | +0.066 |
lady | +0.066 |
gentleman | +0.064 |
woman | +0.064 |
stranger | +0.063 |
Neg logit contributions | |
ug | -0.062 |
issors | -0.061 |
utes | -0.057 |
ors | -0.057 |
eds | -0.056 |
Token | share |
Token ID | 2648 |
Feature activation | -8.14e-03 |
Pos logit contributions | |
ug | +0.002 |
issors | +0.002 |
bar | +0.002 |
bed | +0.002 |
usted | +0.002 |
Neg logit contributions | |
relief | -0.003 |
gentleman | -0.002 |
woman | -0.002 |
cal | -0.002 |
stranger | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
bed | +0.010 |
usted | +0.009 |
eds | +0.009 |
ors | +0.009 |
issors | +0.009 |
Neg logit contributions | |
gentleman | -0.015 |
relief | -0.015 |
prayer | -0.014 |
woman | -0.014 |
pastor | -0.014 |
Token | own |
Token ID | 898 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
clubs | +0.044 |
bed | +0.044 |
igs | +0.043 |
hamm | +0.042 |
bowl | +0.041 |
Neg logit contributions | |
Heidi | -0.047 |
pastor | -0.045 |
gentleman | -0.045 |
relief | -0.044 |
cal | -0.043 |
Token | l |
Token ID | 300 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
clubs | +0.109 |
bed | +0.107 |
issors | +0.103 |
igs | +0.102 |
usted | +0.101 |
Neg logit contributions | |
relief | -0.110 |
cal | -0.104 |
gentleman | -0.102 |
Heidi | -0.101 |
woman | -0.101 |
Token | oll |
Token ID | 692 |
Feature activation | -6.53e-02 |
Pos logit contributions | |
ug | +0.080 |
issors | +0.078 |
usted | +0.075 |
bar | +0.074 |
ors | +0.073 |
Neg logit contributions | |
relief | -0.087 |
woman | -0.081 |
lady | -0.078 |
cal | -0.078 |
gentleman | -0.078 |
Token | ip |
Token ID | 541 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
ug | +0.086 |
issors | +0.085 |
ors | +0.085 |
bed | +0.079 |
usted | +0.079 |
Neg logit contributions | |
relief | -0.134 |
cal | -0.123 |
woman | -0.121 |
gentleman | -0.119 |
lady | -0.117 |
Token | ops |
Token ID | 2840 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
ors | +0.129 |
bed | +0.120 |
issors | +0.115 |
ug | +0.111 |
usted | +0.109 |
Neg logit contributions | |
relief | -0.428 |
woman | -0.397 |
cal | -0.390 |
stranger | -0.387 |
gentleman | -0.386 |
Token | with |
Token ID | 351 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
ug | +0.166 |
usted | +0.162 |
ors | +0.162 |
bed | +0.160 |
issors | +0.160 |
Neg logit contributions | |
relief | -0.207 |
gentleman | -0.189 |
woman | -0.187 |
cal | -0.183 |
stranger | -0.179 |
Token | others |
Token ID | 1854 |
Feature activation | +8.09e-03 |
Pos logit contributions | |
ug | +0.025 |
issors | +0.025 |
bed | +0.025 |
ors | +0.024 |
usted | +0.024 |
Neg logit contributions | |
gentleman | -0.028 |
relief | -0.028 |
stranger | -0.026 |
cal | -0.026 |
lady | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -8.59e-03 |
Pos logit contributions | |
relief | +0.015 |
gentleman | +0.014 |
cal | +0.013 |
woman | +0.013 |
lady | +0.013 |
Neg logit contributions | |
usted | -0.011 |
ors | -0.011 |
bed | -0.011 |
ug | -0.011 |
bowl | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ug | +0.014 |
issors | +0.013 |
usted | +0.013 |
ors | +0.013 |
bar | +0.013 |
Neg logit contributions | |
relief | -0.014 |
gentleman | -0.013 |
lady | -0.013 |
stranger | -0.013 |
woman | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ug | +0.034 |
usted | +0.033 |
bed | +0.032 |
issors | +0.031 |
ors | +0.031 |
Neg logit contributions | |
relief | -0.052 |
gentleman | -0.047 |
cal | -0.046 |
woman | -0.046 |
Heidi | -0.046 |
Token | share |
Token ID | 2648 |
Feature activation | +1.94e-04 |
Pos logit contributions | |
ug | +0.023 |
issors | +0.023 |
usted | +0.022 |
bed | +0.022 |
bar | +0.022 |
Neg logit contributions | |
relief | -0.029 |
gentleman | -0.028 |
lady | -0.028 |
woman | -0.027 |
cal | -0.027 |
Token | her |
Token ID | 607 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
relief | +0.000 |
gentleman | +0.000 |
service | +0.000 |
cal | +0.000 |
pastor | +0.000 |
Neg logit contributions | |
bed | -0.000 |
issors | -0.000 |
clubs | -0.000 |
usted | -0.000 |
bowl | -0.000 |
Token | l |
Token ID | 300 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
bed | +0.045 |
clubs | +0.045 |
issors | +0.045 |
bowl | +0.045 |
igs | +0.045 |
Neg logit contributions | |
relief | -0.046 |
Heidi | -0.043 |
gentleman | -0.043 |
cal | -0.042 |
woman | -0.041 |
Token | oll |
Token ID | 692 |
Feature activation | -5.60e-02 |
Pos logit contributions | |
ug | +0.069 |
issors | +0.067 |
usted | +0.064 |
bar | +0.064 |
ors | +0.063 |
Neg logit contributions | |
relief | -0.064 |
woman | -0.059 |
lady | -0.059 |
gentleman | -0.059 |
cal | -0.058 |
Token | ip |
Token ID | 541 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
ug | +0.078 |
issors | +0.075 |
ors | +0.072 |
usted | +0.071 |
bar | +0.070 |
Neg logit contributions | |
relief | -0.107 |
lady | -0.100 |
gentleman | -0.100 |
woman | -0.099 |
cal | -0.099 |
Token | ops |
Token ID | 2840 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
ug | +0.136 |
issors | +0.134 |
ors | +0.133 |
bed | +0.130 |
usted | +0.125 |
Neg logit contributions | |
relief | -0.382 |
woman | -0.356 |
gentleman | -0.352 |
cal | -0.352 |
stranger | -0.350 |
Token | with |
Token ID | 351 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ug | +0.149 |
issors | +0.144 |
usted | +0.141 |
bed | +0.141 |
ors | +0.140 |
Neg logit contributions | |
relief | -0.174 |
gentleman | -0.161 |
woman | -0.158 |
cal | -0.156 |
stranger | -0.154 |
Token | others |
Token ID | 1854 |
Feature activation | +5.91e-03 |
Pos logit contributions | |
ug | +0.022 |
issors | +0.022 |
bed | +0.021 |
usted | +0.021 |
ors | +0.021 |
Neg logit contributions | |
relief | -0.023 |
gentleman | -0.022 |
lady | -0.021 |
cal | -0.021 |
woman | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
relief | +0.012 |
gentleman | +0.010 |
woman | +0.010 |
cal | +0.010 |
Heidi | +0.010 |
Neg logit contributions | |
bed | -0.008 |
ors | -0.008 |
usted | -0.008 |
ug | -0.008 |
bowl | -0.007 |
Token | just |
Token ID | 655 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
ug | +0.041 |
issors | +0.039 |
usted | +0.038 |
bar | +0.037 |
bed | +0.037 |
Neg logit contributions | |
relief | -0.047 |
gentleman | -0.045 |
lady | -0.044 |
woman | -0.044 |
stranger | -0.044 |
Token | number |
Token ID | 1271 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ug | +0.008 |
bar | +0.008 |
bed | +0.008 |
issors | +0.008 |
drib | +0.008 |
Neg logit contributions | |
woman | -0.011 |
gentleman | -0.011 |
relief | -0.011 |
stranger | -0.011 |
lady | -0.010 |
Token | all |
Token ID | 477 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
ug | +0.024 |
usted | +0.024 |
issors | +0.023 |
bar | +0.023 |
ors | +0.023 |
Neg logit contributions | |
relief | -0.029 |
gentleman | -0.026 |
woman | -0.025 |
stranger | -0.025 |
lady | -0.025 |
Token | her |
Token ID | 607 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
ug | +0.122 |
usted | +0.120 |
issors | +0.116 |
eds | +0.116 |
ors | +0.115 |
Neg logit contributions | |
relief | -0.146 |
gentleman | -0.137 |
woman | -0.132 |
cal | -0.130 |
gen | -0.128 |
Token | l |
Token ID | 300 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
issors | +0.026 |
ug | +0.026 |
usted | +0.025 |
bed | +0.025 |
ors | +0.025 |
Neg logit contributions | |
relief | -0.029 |
gentleman | -0.027 |
woman | -0.027 |
stranger | -0.027 |
lady | -0.026 |
Token | oll |
Token ID | 692 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
ug | +0.061 |
issors | +0.059 |
usted | +0.057 |
bar | +0.056 |
ors | +0.056 |
Neg logit contributions | |
relief | -0.053 |
lady | -0.050 |
woman | -0.050 |
gentleman | -0.049 |
stranger | -0.048 |
Token | ip |
Token ID | 541 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
ug | +0.025 |
issors | +0.023 |
ors | +0.022 |
usted | +0.020 |
bed | +0.019 |
Neg logit contributions | |
relief | -0.141 |
woman | -0.134 |
gentleman | -0.133 |
cal | -0.133 |
lady | -0.133 |
Token | ops |
Token ID | 2840 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
ug | +0.118 |
issors | +0.116 |
ors | +0.116 |
bed | +0.114 |
usted | +0.114 |
Neg logit contributions | |
relief | -0.393 |
woman | -0.365 |
stranger | -0.361 |
gentleman | -0.360 |
cal | -0.360 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-04 |
Pos logit contributions | |
ug | +0.154 |
usted | +0.151 |
issors | +0.150 |
bar | +0.149 |
ors | +0.148 |
Neg logit contributions | |
relief | -0.163 |
gentleman | -0.146 |
cal | -0.144 |
woman | -0.144 |
stranger | -0.139 |
Token | She |
Token ID | 1375 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ug | +0.000 |
issors | +0.000 |
usted | +0.000 |
bed | +0.000 |
ors | +0.000 |
Neg logit contributions | |
relief | -0.000 |
lady | -0.000 |
gentleman | -0.000 |
woman | -0.000 |
stranger | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
relief | +0.020 |
lady | +0.019 |
gentleman | +0.019 |
woman | +0.018 |
cal | +0.018 |
Neg logit contributions | |
ug | -0.024 |
issors | -0.023 |
usted | -0.022 |
ors | -0.022 |
bar | -0.021 |
Token | two |
Token ID | 734 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
ug | +0.058 |
issors | +0.057 |
usted | +0.057 |
bar | +0.056 |
bed | +0.054 |
Neg logit contributions | |
relief | -0.074 |
gentleman | -0.071 |
lady | -0.070 |
woman | -0.069 |
stranger | -0.068 |
Token | they |
Token ID | 484 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
ug | +0.027 |
bar | +0.026 |
ert | +0.025 |
bed | +0.025 |
leys | +0.025 |
Neg logit contributions | |
relief | -0.032 |
gentleman | -0.029 |
cal | -0.028 |
woman | -0.026 |
lady | -0.026 |
Token | could |
Token ID | 714 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
ug | +0.031 |
issors | +0.029 |
usted | +0.028 |
bar | +0.027 |
ors | +0.027 |
Neg logit contributions | |
relief | -0.083 |
lady | -0.079 |
gentleman | -0.079 |
woman | -0.078 |
cal | -0.077 |
Token | buy |
Token ID | 2822 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
ug | +0.140 |
issors | +0.139 |
bar | +0.132 |
usted | +0.129 |
bed | +0.129 |
Neg logit contributions | |
relief | -0.159 |
gentleman | -0.148 |
woman | -0.147 |
lady | -0.145 |
cal | -0.145 |
Token | l |
Token ID | 300 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
relief | +0.055 |
gentleman | +0.051 |
woman | +0.050 |
lady | +0.050 |
stranger | +0.050 |
Neg logit contributions | |
ug | -0.038 |
bar | -0.037 |
issors | -0.037 |
ors | -0.036 |
bed | -0.035 |
Token | oll |
Token ID | 692 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
ug | +0.071 |
issors | +0.068 |
usted | +0.066 |
bar | +0.065 |
ors | +0.065 |
Neg logit contributions | |
relief | -0.062 |
lady | -0.059 |
gentleman | -0.058 |
woman | -0.057 |
cal | -0.056 |
Token | ip |
Token ID | 541 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
ug | +0.038 |
issors | +0.035 |
ors | +0.034 |
usted | +0.031 |
bar | +0.031 |
Neg logit contributions | |
relief | -0.152 |
woman | -0.143 |
gentleman | -0.142 |
lady | -0.142 |
cal | -0.141 |
Token | ops |
Token ID | 2840 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ug | +0.143 |
issors | +0.143 |
ors | +0.139 |
bed | +0.134 |
bar | +0.133 |
Neg logit contributions | |
relief | -0.364 |
woman | -0.337 |
stranger | -0.333 |
gentleman | -0.332 |
cal | -0.330 |
Token | for |
Token ID | 329 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
ug | +0.172 |
issors | +0.169 |
bar | +0.169 |
ors | +0.163 |
usted | +0.163 |
Neg logit contributions | |
relief | -0.181 |
woman | -0.160 |
gentleman | -0.159 |
cal | -0.157 |
stranger | -0.153 |
Token | them |
Token ID | 606 |
Feature activation | -5.15e-03 |
Pos logit contributions | |
ug | +0.020 |
issors | +0.019 |
bed | +0.018 |
ors | +0.018 |
bar | +0.018 |
Neg logit contributions | |
relief | -0.023 |
gentleman | -0.022 |
lady | -0.022 |
woman | -0.022 |
cal | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.009 |
bar | +0.009 |
ors | +0.009 |
usted | +0.009 |
Neg logit contributions | |
relief | -0.008 |
gentleman | -0.007 |
woman | -0.007 |
lady | -0.007 |
cal | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -8.18e-03 |
Pos logit contributions | |
ug | +0.023 |
issors | +0.022 |
usted | +0.021 |
bed | +0.021 |
ors | +0.021 |
Neg logit contributions | |
relief | -0.023 |
lady | -0.021 |
gentleman | -0.021 |
woman | -0.021 |
cal | -0.021 |
Token | ball |
Token ID | 2613 |
Feature activation | -4.85e-02 |
Pos logit contributions | |
relief | +0.008 |
gentleman | +0.008 |
cal | +0.008 |
service | +0.008 |
lady | +0.008 |
Neg logit contributions | |
issors | -0.008 |
ug | -0.008 |
usted | -0.008 |
utes | -0.008 |
bar | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ug | +0.096 |
issors | +0.093 |
utes | +0.092 |
ors | +0.090 |
ants | +0.089 |
Neg logit contributions | |
lady | -0.065 |
cal | -0.058 |
man | -0.057 |
stranger | -0.055 |
relief | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
bed | +0.014 |
clubs | +0.014 |
ug | +0.014 |
issors | +0.014 |
fet | +0.014 |
Neg logit contributions | |
gentleman | -0.019 |
relief | -0.019 |
stranger | -0.018 |
woman | -0.018 |
Lord | -0.018 |
Token | dog |
Token ID | 3290 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
relief | +0.022 |
gentleman | +0.022 |
cal | +0.021 |
service | +0.021 |
Heidi | +0.021 |
Neg logit contributions | |
issors | -0.013 |
ug | -0.013 |
clubs | -0.012 |
bar | -0.012 |
usted | -0.012 |
Token | fet |
Token ID | 11351 |
Feature activation | -9.65e-02 |
Pos logit contributions | |
ug | +0.028 |
issors | +0.027 |
usted | +0.026 |
bed | +0.026 |
ors | +0.026 |
Neg logit contributions | |
relief | -0.030 |
gentleman | -0.029 |
woman | -0.028 |
lady | -0.028 |
stranger | -0.027 |
Token | ches |
Token ID | 2052 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
bar | +0.128 |
ogram | +0.124 |
bed | +0.120 |
bowl | +0.119 |
years | +0.115 |
Neg logit contributions | |
relief | -0.170 |
lady | -0.167 |
man | -0.164 |
cal | -0.163 |
stranger | -0.150 |
Token | it |
Token ID | 340 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
ug | +0.314 |
issors | +0.311 |
bar | +0.311 |
utes | +0.309 |
usted | +0.305 |
Neg logit contributions | |
lady | -0.160 |
man | -0.150 |
relief | -0.148 |
cal | -0.142 |
stranger | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
ug | +0.083 |
issors | +0.080 |
utes | +0.079 |
bar | +0.076 |
eds | +0.076 |
Neg logit contributions | |
lady | -0.034 |
relief | -0.031 |
cal | -0.030 |
man | -0.029 |
stranger | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
ug | +0.008 |
issors | +0.008 |
usted | +0.008 |
utes | +0.008 |
bed | +0.007 |
Neg logit contributions | |
relief | -0.010 |
gentleman | -0.010 |
lady | -0.010 |
stranger | -0.010 |
woman | -0.010 |
Token | push |
Token ID | 4574 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
ug | +0.005 |
issors | +0.005 |
usted | +0.005 |
bed | +0.004 |
bar | +0.004 |
Neg logit contributions | |
relief | -0.005 |
gentleman | -0.005 |
woman | -0.005 |
lady | -0.005 |
stranger | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
issors | +0.022 |
ug | +0.022 |
bar | +0.022 |
utes | +0.022 |
leys | +0.022 |
Neg logit contributions | |
relief | -0.015 |
lady | -0.015 |
woman | -0.014 |
cal | -0.014 |
man | -0.014 |
Token | itty |
Token ID | 9760 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
relief | +0.003 |
stranger | +0.003 |
cal | +0.003 |
lady | +0.003 |
woman | +0.003 |
Neg logit contributions | |
ug | -0.003 |
bar | -0.003 |
bed | -0.003 |
ors | -0.003 |
issors | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
ug | +0.041 |
bed | +0.041 |
bar | +0.038 |
ors | +0.038 |
usted | +0.037 |
Neg logit contributions | |
relief | -0.050 |
gentleman | -0.045 |
stranger | -0.045 |
service | -0.044 |
cal | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ug | +0.018 |
bar | +0.017 |
issors | +0.016 |
ors | +0.015 |
bed | +0.014 |
Neg logit contributions | |
relief | -0.078 |
gentleman | -0.075 |
cal | -0.072 |
lady | -0.071 |
woman | -0.071 |
Token | introduce |
Token ID | 10400 |
Feature activation | -4.76e-03 |
Pos logit contributions | |
relief | +0.023 |
gentleman | +0.023 |
woman | +0.022 |
cal | +0.021 |
lady | +0.021 |
Neg logit contributions | |
ug | -0.019 |
issors | -0.018 |
bar | -0.018 |
bed | -0.017 |
bowl | -0.017 |
Token | Dog |
Token ID | 8532 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
ug | +0.008 |
bed | +0.007 |
issors | +0.007 |
ors | +0.007 |
bar | +0.007 |
Neg logit contributions | |
relief | -0.008 |
gentleman | -0.007 |
cal | -0.007 |
woman | -0.007 |
lady | -0.007 |
Token | gy |
Token ID | 1360 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ug | +0.055 |
issors | +0.049 |
bar | +0.049 |
ors | +0.049 |
bed | +0.048 |
Neg logit contributions | |
relief | -0.136 |
gentleman | -0.125 |
lady | -0.124 |
cal | -0.122 |
woman | -0.122 |
Token | to |
Token ID | 284 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
ug | +0.188 |
issors | +0.177 |
usted | +0.166 |
ors | +0.164 |
bed | +0.164 |
Neg logit contributions | |
relief | -0.296 |
lady | -0.293 |
gentleman | -0.287 |
woman | -0.285 |
stranger | -0.283 |
Token | her |
Token ID | 607 |
Feature activation | +2.63e-06 |
Pos logit contributions | |
ug | +0.027 |
issors | +0.024 |
bed | +0.024 |
bar | +0.024 |
ors | +0.023 |
Neg logit contributions | |
relief | -0.027 |
gentleman | -0.027 |
lady | -0.025 |
woman | -0.025 |
stranger | -0.025 |
Token | ball |
Token ID | 2613 |
Feature activation | -7.68e-02 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ug | +0.134 |
issors | +0.128 |
bar | +0.124 |
usted | +0.123 |
ors | +0.122 |
Neg logit contributions | |
relief | -0.118 |
gentleman | -0.110 |
lady | -0.110 |
woman | -0.108 |
cal | -0.107 |
Token | She |
Token ID | 1375 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
ug | +0.023 |
issors | +0.022 |
bar | +0.021 |
usted | +0.021 |
ors | +0.021 |
Neg logit contributions | |
relief | -0.023 |
cal | -0.021 |
stranger | -0.021 |
gentleman | -0.021 |
lady | -0.021 |
Token | for |
Token ID | 329 |
Feature activation | +2.75e-03 |
Pos logit contributions | |
ug | +0.013 |
bar | +0.012 |
bed | +0.012 |
usted | +0.012 |
ors | +0.012 |
Neg logit contributions | |
relief | -0.016 |
gentleman | -0.015 |
stranger | -0.015 |
cal | -0.014 |
woman | -0.014 |
Token | lots |
Token ID | 6041 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
gentleman | +0.005 |
stranger | +0.005 |
lady | +0.004 |
woman | +0.004 |
relief | +0.004 |
Neg logit contributions | |
ug | -0.004 |
bed | -0.004 |
hamm | -0.003 |
issors | -0.003 |
igs | -0.003 |
Token | more |
Token ID | 517 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
ug | +0.041 |
ors | +0.036 |
usted | +0.035 |
often | +0.026 |
ir | +0.024 |
Neg logit contributions | |
relief | -0.128 |
gentleman | -0.122 |
woman | -0.119 |
Heidi | -0.118 |
gen | -0.116 |
Token | l |
Token ID | 300 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
ug | +0.003 |
often | +0.003 |
ors | +0.003 |
usted | +0.003 |
igs | +0.003 |
Neg logit contributions | |
gentleman | -0.004 |
relief | -0.004 |
Heidi | -0.004 |
lady | -0.004 |
woman | -0.004 |
Token | oll |
Token ID | 692 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
ug | +0.061 |
issors | +0.058 |
usted | +0.056 |
bar | +0.055 |
ors | +0.055 |
Neg logit contributions | |
relief | -0.062 |
woman | -0.059 |
lady | -0.058 |
gentleman | -0.058 |
stranger | -0.057 |
Token | ip |
Token ID | 541 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ug | +0.050 |
ors | +0.048 |
issors | +0.046 |
igs | +0.044 |
ants | +0.043 |
Neg logit contributions | |
relief | -0.113 |
cal | -0.104 |
gentleman | -0.103 |
woman | -0.103 |
lady | -0.101 |
Token | ops |
Token ID | 2840 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ors | +0.105 |
ug | +0.105 |
issors | +0.095 |
bed | +0.092 |
usted | +0.091 |
Neg logit contributions | |
relief | -0.403 |
woman | -0.373 |
cal | -0.371 |
gentleman | -0.370 |
stranger | -0.368 |
Token | like |
Token ID | 588 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
ug | +0.162 |
bar | +0.153 |
ors | +0.153 |
usted | +0.150 |
issors | +0.149 |
Neg logit contributions | |
relief | -0.184 |
gentleman | -0.166 |
cal | -0.163 |
woman | -0.160 |
lady | -0.156 |
Token | the |
Token ID | 262 |
Feature activation | -8.13e-03 |
Pos logit contributions | |
ug | +0.009 |
bar | +0.009 |
usted | +0.008 |
bed | +0.008 |
issors | +0.008 |
Neg logit contributions | |
relief | -0.009 |
gentleman | -0.009 |
cal | -0.008 |
woman | -0.008 |
stranger | -0.008 |
Token | one |
Token ID | 530 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
bar | +0.012 |
usted | +0.011 |
drib | +0.011 |
issors | +0.011 |
targets | +0.011 |
Neg logit contributions | |
relief | -0.012 |
Heidi | -0.011 |
gentleman | -0.011 |
cal | -0.010 |
service | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
ug | +0.011 |
bar | +0.011 |
often | +0.010 |
bowl | +0.010 |
ogram | +0.010 |
Neg logit contributions | |
relief | -0.017 |
gentleman | -0.016 |
Heidi | -0.015 |
woman | -0.014 |
cal | -0.014 |
Token | get |
Token ID | 651 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
ug | +0.168 |
issors | +0.158 |
bed | +0.156 |
bar | +0.155 |
usted | +0.152 |
Neg logit contributions | |
relief | -0.185 |
gentleman | -0.179 |
lady | -0.176 |
woman | -0.175 |
stranger | -0.172 |
Token | her |
Token ID | 607 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
gentleman | +0.033 |
relief | +0.032 |
woman | +0.031 |
lady | +0.031 |
witch | +0.030 |
Neg logit contributions | |
ug | -0.020 |
usted | -0.019 |
bed | -0.019 |
bar | -0.019 |
bowl | -0.018 |
Token | own |
Token ID | 898 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
ug | +0.007 |
issors | +0.007 |
bed | +0.007 |
utes | +0.007 |
bar | +0.007 |
Neg logit contributions | |
gentleman | -0.009 |
relief | -0.009 |
cal | -0.008 |
woman | -0.008 |
lady | -0.008 |
Token | l |
Token ID | 300 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
ug | +0.064 |
bar | +0.062 |
clubs | +0.062 |
bed | +0.062 |
usted | +0.062 |
Neg logit contributions | |
relief | -0.073 |
gentleman | -0.072 |
cal | -0.067 |
woman | -0.067 |
Heidi | -0.067 |
Token | oll |
Token ID | 692 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
ug | +0.056 |
issors | +0.053 |
usted | +0.051 |
bar | +0.051 |
utes | +0.050 |
Neg logit contributions | |
relief | -0.051 |
lady | -0.048 |
woman | -0.047 |
gentleman | -0.047 |
cal | -0.046 |
Token | ip |
Token ID | 541 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
ug | +0.061 |
issors | +0.058 |
ors | +0.058 |
bar | +0.056 |
usted | +0.055 |
Neg logit contributions | |
relief | -0.087 |
cal | -0.081 |
gentleman | -0.080 |
woman | -0.079 |
lady | -0.079 |
Token | ops |
Token ID | 2840 |
Feature activation | -9.90e-02 |
Pos logit contributions | |
ug | +0.157 |
ors | +0.152 |
bar | +0.149 |
issors | +0.148 |
bed | +0.146 |
Neg logit contributions | |
relief | -0.341 |
woman | -0.313 |
gentleman | -0.312 |
cal | -0.311 |
stranger | -0.307 |
Token | . |
Token ID | 13 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
ug | +0.163 |
bar | +0.155 |
issors | +0.154 |
usted | +0.153 |
ors | +0.152 |
Neg logit contributions | |
relief | -0.168 |
gentleman | -0.155 |
woman | -0.151 |
cal | -0.150 |
lady | -0.150 |
Token | Betty |
Token ID | 29504 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
ug | +0.017 |
issors | +0.016 |
usted | +0.016 |
ors | +0.015 |
bar | +0.015 |
Neg logit contributions | |
relief | -0.016 |
lady | -0.015 |
gentleman | -0.015 |
woman | -0.014 |
cal | -0.014 |
Token | be |
Token ID | 307 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
ug | +0.047 |
bed | +0.045 |
usted | +0.045 |
bar | +0.043 |
ors | +0.043 |
Neg logit contributions | |
relief | -0.046 |
gentleman | -0.043 |
stranger | -0.042 |
lady | -0.042 |
woman | -0.042 |
Token | amed |
Token ID | 2434 |
Feature activation | -5.81e-03 |
Pos logit contributions | |
relief | +0.120 |
gentleman | +0.118 |
lady | +0.117 |
stranger | +0.115 |
woman | +0.115 |
Neg logit contributions | |
ug | -0.076 |
issors | -0.069 |
usted | -0.069 |
bar | -0.068 |
bed | -0.067 |
Token | ball |
Token ID | 2613 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
relief | +0.013 |
cal | +0.012 |
gentleman | +0.012 |
Lord | +0.012 |
service | +0.012 |
Neg logit contributions | |
issors | -0.012 |
ug | -0.012 |
clubs | -0.011 |
usted | -0.011 |
eds | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
ug | +0.094 |
issors | +0.094 |
utes | +0.091 |
ors | +0.090 |
ants | +0.088 |
Neg logit contributions | |
lady | -0.062 |
cal | -0.056 |
man | -0.055 |
stranger | -0.053 |
relief | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.009 |
bed | +0.009 |
clubs | +0.009 |
fet | +0.009 |
Neg logit contributions | |
gentleman | -0.013 |
relief | -0.013 |
stranger | -0.013 |
Lord | -0.013 |
woman | -0.013 |
Token | dog |
Token ID | 3290 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
relief | +0.028 |
gentleman | +0.027 |
cal | +0.027 |
Lord | +0.026 |
Heidi | +0.026 |
Neg logit contributions | |
issors | -0.015 |
ug | -0.015 |
clubs | -0.015 |
bar | -0.014 |
bowl | -0.014 |
Token | fet |
Token ID | 11351 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
ug | +0.029 |
issors | +0.028 |
usted | +0.027 |
bed | +0.027 |
ors | +0.027 |
Neg logit contributions | |
relief | -0.027 |
gentleman | -0.026 |
lady | -0.025 |
woman | -0.025 |
stranger | -0.025 |
Token | ches |
Token ID | 2052 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
bar | +0.124 |
ogram | +0.120 |
bed | +0.117 |
bowl | +0.116 |
ug | +0.112 |
Neg logit contributions | |
relief | -0.172 |
lady | -0.166 |
cal | -0.166 |
man | -0.163 |
sigh | -0.148 |
Token | it |
Token ID | 340 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
issors | +0.305 |
bar | +0.305 |
ug | +0.304 |
utes | +0.299 |
usted | +0.297 |
Neg logit contributions | |
lady | -0.161 |
relief | -0.154 |
man | -0.152 |
cal | -0.148 |
stranger | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
ug | +0.075 |
issors | +0.072 |
utes | +0.071 |
usted | +0.069 |
bar | +0.069 |
Neg logit contributions | |
lady | -0.031 |
relief | -0.029 |
cal | -0.027 |
man | -0.026 |
stranger | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | -2.47e-03 |
Pos logit contributions | |
ug | +0.003 |
issors | +0.003 |
bed | +0.003 |
utes | +0.003 |
usted | +0.003 |
Neg logit contributions | |
relief | -0.005 |
gentleman | -0.005 |
stranger | -0.005 |
lady | -0.005 |
woman | -0.005 |
Token | have |
Token ID | 423 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
ug | +0.004 |
issors | +0.003 |
bed | +0.003 |
bowl | +0.003 |
bar | +0.003 |
Neg logit contributions | |
relief | -0.004 |
gentleman | -0.004 |
woman | -0.004 |
lady | -0.004 |
stranger | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
relief | +0.021 |
gentleman | +0.020 |
lady | +0.020 |
woman | +0.019 |
stranger | +0.019 |
Neg logit contributions | |
ug | -0.030 |
issors | -0.029 |
usted | -0.029 |
bar | -0.028 |
bed | -0.028 |
Token | ball |
Token ID | 2613 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
ug | +0.018 |
ors | +0.018 |
issors | +0.017 |
bed | +0.017 |
leys | +0.016 |
Neg logit contributions | |
lady | -0.022 |
man | -0.021 |
stranger | -0.021 |
woman | -0.021 |
relief | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +4.39e-03 |
Pos logit contributions | |
leys | +0.086 |
ants | +0.086 |
utes | +0.086 |
issors | +0.085 |
ug | +0.084 |
Neg logit contributions | |
lady | -0.037 |
man | -0.031 |
cal | -0.028 |
ranger | -0.027 |
stranger | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
gentleman | +0.008 |
relief | +0.008 |
stranger | +0.008 |
Lord | +0.008 |
woman | +0.008 |
Neg logit contributions | |
ug | -0.005 |
issors | -0.005 |
clubs | -0.005 |
bar | -0.005 |
bed | -0.005 |
Token | dog |
Token ID | 3290 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
relief | +0.035 |
gentleman | +0.033 |
cal | +0.033 |
service | +0.032 |
Lord | +0.032 |
Neg logit contributions | |
ug | -0.023 |
issors | -0.023 |
bar | -0.022 |
clubs | -0.022 |
usted | -0.021 |
Token | fet |
Token ID | 11351 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
ug | +0.024 |
issors | +0.023 |
usted | +0.022 |
ors | +0.022 |
bed | +0.022 |
Neg logit contributions | |
relief | -0.021 |
gentleman | -0.020 |
woman | -0.019 |
lady | -0.019 |
stranger | -0.019 |
Token | ches |
Token ID | 2052 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
bar | +0.119 |
ogram | +0.116 |
bed | +0.112 |
bowl | +0.111 |
ug | +0.109 |
Neg logit contributions | |
relief | -0.169 |
cal | -0.165 |
lady | -0.165 |
man | -0.161 |
stranger | -0.148 |
Token | it |
Token ID | 340 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
ug | +0.316 |
utes | +0.313 |
issors | +0.312 |
bar | +0.312 |
leys | +0.311 |
Neg logit contributions | |
lady | -0.151 |
man | -0.144 |
relief | -0.136 |
cal | -0.135 |
stranger | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +2.68e-04 |
Pos logit contributions | |
ug | +0.078 |
issors | +0.075 |
utes | +0.075 |
eds | +0.073 |
leys | +0.072 |
Neg logit contributions | |
lady | -0.028 |
cal | -0.023 |
relief | -0.023 |
man | -0.023 |
stranger | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | +7.15e-04 |
Pos logit contributions | |
relief | +0.001 |
gentleman | +0.000 |
lady | +0.000 |
woman | +0.000 |
stranger | +0.000 |
Neg logit contributions | |
ug | -0.000 |
issors | -0.000 |
usted | -0.000 |
bed | -0.000 |
utes | -0.000 |
Token | hug |
Token ID | 16225 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
relief | +0.001 |
gentleman | +0.001 |
lady | +0.001 |
woman | +0.001 |
stranger | +0.001 |
Neg logit contributions | |
ug | -0.001 |
issors | -0.001 |
usted | -0.001 |
bar | -0.001 |
bed | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +8.09e-06 |
Pos logit contributions | |
relief | +0.052 |
gentleman | +0.050 |
lady | +0.049 |
cal | +0.048 |
woman | +0.048 |
Neg logit contributions | |
ug | -0.043 |
issors | -0.041 |
bed | -0.040 |
ors | -0.039 |
usted | -0.039 |
Token | him |
Token ID | 683 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
ug | +0.021 |
bed | +0.019 |
ir | +0.018 |
often | +0.018 |
usted | +0.018 |
Neg logit contributions | |
gentleman | -0.029 |
woman | -0.029 |
relief | -0.027 |
lady | -0.027 |
stranger | -0.027 |
Token | for |
Token ID | 329 |
Feature activation | +2.63e-03 |
Pos logit contributions | |
ug | +0.012 |
ors | +0.010 |
usted | +0.010 |
bed | +0.010 |
bar | +0.010 |
Neg logit contributions | |
relief | -0.017 |
gentleman | -0.016 |
woman | -0.016 |
Heidi | -0.016 |
pastor | -0.016 |
Token | remembering |
Token ID | 24865 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
gentleman | +0.005 |
woman | +0.005 |
lady | +0.004 |
relief | +0.004 |
stranger | +0.004 |
Neg logit contributions | |
ug | -0.004 |
bed | -0.004 |
bar | -0.003 |
issors | -0.003 |
usted | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
ug | +0.016 |
usted | +0.015 |
ors | +0.015 |
bed | +0.015 |
eds | +0.015 |
Neg logit contributions | |
relief | -0.028 |
gentleman | -0.027 |
woman | -0.026 |
lady | -0.026 |
stranger | -0.025 |
Token | pig |
Token ID | 12967 |
Feature activation | -9.49e-02 |
Pos logit contributions | |
ug | +0.040 |
issors | +0.039 |
utes | +0.038 |
bar | +0.038 |
clubs | +0.037 |
Neg logit contributions | |
gentleman | -0.034 |
relief | -0.034 |
Heidi | -0.033 |
cal | -0.033 |
lady | -0.032 |
Token | gy |
Token ID | 1360 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
ug | +0.136 |
bowl | +0.132 |
bar | +0.130 |
ors | +0.129 |
eds | +0.129 |
Neg logit contributions | |
relief | -0.172 |
gentleman | -0.159 |
cal | -0.154 |
stranger | -0.151 |
woman | -0.150 |
Token | bank |
Token ID | 3331 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
ug | +0.233 |
issors | +0.222 |
bar | +0.218 |
usted | +0.216 |
bed | +0.216 |
Neg logit contributions | |
relief | -0.244 |
gentleman | -0.231 |
lady | -0.227 |
woman | -0.223 |
cal | -0.222 |
Token | . |
Token ID | 13 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
ug | +0.093 |
usted | +0.089 |
bar | +0.089 |
issors | +0.087 |
ors | +0.084 |
Neg logit contributions | |
relief | -0.106 |
gentleman | -0.097 |
woman | -0.096 |
Heidi | -0.094 |
witch | -0.093 |
Token | From |
Token ID | 3574 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
ug | +0.007 |
issors | +0.007 |
bar | +0.006 |
usted | +0.006 |
ors | +0.006 |
Neg logit contributions | |
relief | -0.007 |
lady | -0.007 |
gentleman | -0.007 |
woman | -0.007 |
cal | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
relief | +0.025 |
gentleman | +0.023 |
woman | +0.023 |
cal | +0.023 |
prayer | +0.023 |
Neg logit contributions | |
ug | -0.018 |
bed | -0.018 |
bar | -0.017 |
ors | -0.016 |
issors | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
relief | +0.010 |
lady | +0.010 |
woman | +0.010 |
gentleman | +0.010 |
stranger | +0.010 |
Neg logit contributions | |
ug | -0.013 |
issors | -0.013 |
usted | -0.013 |
utes | -0.013 |
ors | -0.013 |
Token | count |
Token ID | 954 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
relief | +0.017 |
gentleman | +0.017 |
woman | +0.017 |
cal | +0.016 |
lady | +0.016 |
Neg logit contributions | |
ug | -0.015 |
issors | -0.014 |
bar | -0.014 |
bed | -0.013 |
usted | -0.013 |
Token | how |
Token ID | 703 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
relief | +0.033 |
gentleman | +0.031 |
lady | +0.030 |
woman | +0.030 |
cal | +0.029 |
Neg logit contributions | |
ug | -0.029 |
issors | -0.028 |
usted | -0.027 |
bar | -0.027 |
ors | -0.026 |
Token | many |
Token ID | 867 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
ug | +0.012 |
issors | +0.012 |
usted | +0.012 |
utes | +0.011 |
bar | +0.011 |
Neg logit contributions | |
relief | -0.018 |
gentleman | -0.017 |
lady | -0.017 |
woman | -0.017 |
cal | -0.016 |
Token | l |
Token ID | 300 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
ug | +0.035 |
igs | +0.033 |
usted | +0.033 |
often | +0.032 |
clubs | +0.031 |
Neg logit contributions | |
relief | -0.049 |
gentleman | -0.048 |
cal | -0.042 |
woman | -0.042 |
Heidi | -0.041 |
Token | oll |
Token ID | 692 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
ug | +0.040 |
issors | +0.037 |
usted | +0.035 |
utes | +0.034 |
bar | +0.034 |
Neg logit contributions | |
relief | -0.064 |
woman | -0.060 |
gentleman | -0.060 |
lady | -0.059 |
cal | -0.059 |
Token | ip |
Token ID | 541 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ug | +0.049 |
ors | +0.046 |
issors | +0.045 |
bed | +0.043 |
usted | +0.043 |
Neg logit contributions | |
relief | -0.093 |
cal | -0.087 |
gentleman | -0.086 |
woman | -0.085 |
lady | -0.085 |
Token | ops |
Token ID | 2840 |
Feature activation | -9.84e-02 |
Pos logit contributions | |
ug | +0.126 |
ors | +0.121 |
bed | +0.120 |
issors | +0.116 |
usted | +0.115 |
Neg logit contributions | |
relief | -0.371 |
gentleman | -0.341 |
woman | -0.339 |
cal | -0.339 |
stranger | -0.338 |
Token | she |
Token ID | 673 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
ug | +0.158 |
bar | +0.154 |
usted | +0.151 |
bed | +0.148 |
ors | +0.148 |
Neg logit contributions | |
relief | -0.178 |
gentleman | -0.158 |
cal | -0.154 |
woman | -0.153 |
stranger | -0.148 |
Token | had |
Token ID | 550 |
Feature activation | -8.20e-02 |
Pos logit contributions | |
ug | +0.041 |
bed | +0.039 |
issors | +0.039 |
usted | +0.038 |
bar | +0.037 |
Neg logit contributions | |
relief | -0.095 |
gentleman | -0.088 |
lady | -0.086 |
woman | -0.085 |
stranger | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-03 |
Pos logit contributions | |
usted | +0.114 |
ug | +0.113 |
issors | +0.111 |
bar | +0.110 |
leys | +0.110 |
Neg logit contributions | |
relief | -0.154 |
gentleman | -0.142 |
woman | -0.136 |
stranger | -0.134 |
cal | -0.134 |
Token | She |
Token ID | 1375 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
issors | +0.004 |
ug | +0.004 |
usted | +0.004 |
bar | +0.004 |
ors | +0.004 |
Neg logit contributions | |
relief | -0.004 |
cal | -0.004 |
stranger | -0.004 |
lady | -0.004 |
gentleman | -0.004 |
Token | walk |
Token ID | 2513 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
relief | +0.012 |
woman | +0.011 |
gentleman | +0.011 |
stranger | +0.011 |
lady | +0.011 |
Neg logit contributions | |
ug | -0.011 |
issors | -0.011 |
bar | -0.010 |
bed | -0.010 |
ors | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
relief | +0.022 |
gentleman | +0.021 |
lady | +0.021 |
woman | +0.020 |
cal | +0.020 |
Neg logit contributions | |
ug | -0.018 |
issors | -0.017 |
ors | -0.016 |
bed | -0.016 |
usted | -0.016 |
Token | give |
Token ID | 1577 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
ug | +0.019 |
issors | +0.018 |
bar | +0.018 |
bed | +0.018 |
usted | +0.018 |
Neg logit contributions | |
relief | -0.022 |
gentleman | -0.021 |
lady | -0.020 |
woman | -0.020 |
cal | -0.020 |
Token | l |
Token ID | 300 |
Feature activation | -2.91e-02 |
Pos logit contributions | |
relief | +0.030 |
gentleman | +0.029 |
lady | +0.028 |
woman | +0.028 |
stranger | +0.027 |
Neg logit contributions | |
ug | -0.027 |
issors | -0.027 |
usted | -0.026 |
ors | -0.026 |
bed | -0.026 |
Token | oll |
Token ID | 692 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
ug | +0.053 |
issors | +0.051 |
usted | +0.049 |
ors | +0.048 |
bar | +0.048 |
Neg logit contributions | |
relief | -0.043 |
lady | -0.040 |
gentleman | -0.040 |
woman | -0.039 |
cal | -0.039 |
Token | ip |
Token ID | 541 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ug | +0.042 |
issors | +0.039 |
usted | +0.036 |
ors | +0.035 |
bar | +0.035 |
Neg logit contributions | |
relief | -0.115 |
lady | -0.111 |
gentleman | -0.110 |
woman | -0.109 |
cal | -0.108 |
Token | ops |
Token ID | 2840 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
ug | +0.136 |
issors | +0.129 |
ors | +0.124 |
usted | +0.122 |
bar | +0.119 |
Neg logit contributions | |
relief | -0.349 |
woman | -0.327 |
gentleman | -0.327 |
lady | -0.324 |
stranger | -0.322 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
ug | +0.125 |
issors | +0.120 |
usted | +0.118 |
bar | +0.118 |
ors | +0.115 |
Neg logit contributions | |
relief | -0.170 |
gentleman | -0.157 |
woman | -0.155 |
cal | -0.154 |
lady | -0.151 |
Token | children |
Token ID | 1751 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
ug | +0.019 |
issors | +0.019 |
bed | +0.018 |
bar | +0.018 |
ors | +0.018 |
Neg logit contributions | |
relief | -0.023 |
gentleman | -0.023 |
woman | -0.022 |
stranger | -0.022 |
cal | -0.021 |
Token | ." |
Token ID | 526 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
ug | +0.035 |
issors | +0.032 |
ors | +0.032 |
bar | +0.032 |
usted | +0.032 |
Neg logit contributions | |
relief | -0.050 |
gentleman | -0.046 |
cal | -0.045 |
woman | -0.045 |
stranger | -0.044 |
Token | The |
Token ID | 383 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
ug | +0.018 |
usted | +0.018 |
issors | +0.018 |
bed | +0.017 |
ors | +0.016 |
Neg logit contributions | |
relief | -0.022 |
stranger | -0.021 |
gentleman | -0.021 |
cal | -0.021 |
woman | -0.020 |
Token | some |
Token ID | 617 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
relief | +0.062 |
gentleman | +0.061 |
woman | +0.058 |
Heidi | +0.057 |
lady | +0.056 |
Neg logit contributions | |
usted | -0.045 |
ug | -0.043 |
issors | -0.043 |
bar | -0.040 |
utes | -0.039 |
Token | money |
Token ID | 1637 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
relief | +0.006 |
gentleman | +0.006 |
Heidi | +0.006 |
woman | +0.005 |
cal | +0.005 |
Neg logit contributions | |
ug | -0.006 |
issors | -0.006 |
usted | -0.006 |
clubs | -0.006 |
utes | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
relief | +0.042 |
gentleman | +0.038 |
cal | +0.037 |
Heidi | +0.036 |
woman | +0.036 |
Neg logit contributions | |
issors | -0.031 |
ug | -0.030 |
usted | -0.029 |
ors | -0.029 |
bar | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.009 |
bed | +0.009 |
ors | +0.009 |
usted | +0.009 |
Neg logit contributions | |
relief | -0.009 |
gentleman | -0.009 |
cal | -0.009 |
lady | -0.009 |
woman | -0.009 |
Token | pig |
Token ID | 12967 |
Feature activation | -9.28e-02 |
Pos logit contributions | |
ug | +0.021 |
issors | +0.020 |
clubs | +0.020 |
ors | +0.020 |
utes | +0.019 |
Neg logit contributions | |
relief | -0.026 |
gentleman | -0.024 |
cal | -0.024 |
Heidi | -0.023 |
woman | -0.022 |
Token | gy |
Token ID | 1360 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ug | +0.167 |
issors | +0.162 |
ors | +0.156 |
usted | +0.155 |
bar | +0.155 |
Neg logit contributions | |
relief | -0.138 |
gentleman | -0.128 |
lady | -0.127 |
woman | -0.124 |
cal | -0.124 |
Token | bank |
Token ID | 3331 |
Feature activation | -5.19e-02 |
Pos logit contributions | |
ug | +0.234 |
issors | +0.225 |
usted | +0.216 |
bar | +0.214 |
ors | +0.214 |
Neg logit contributions | |
relief | -0.239 |
lady | -0.227 |
gentleman | -0.226 |
woman | -0.222 |
cal | -0.220 |
Token | . |
Token ID | 13 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
ug | +0.093 |
issors | +0.090 |
usted | +0.088 |
bar | +0.086 |
ors | +0.086 |
Neg logit contributions | |
relief | -0.082 |
gentleman | -0.073 |
woman | -0.072 |
cal | -0.070 |
Heidi | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
ug | +0.015 |
issors | +0.014 |
eds | +0.014 |
utes | +0.014 |
ors | +0.014 |
Neg logit contributions | |
relief | -0.010 |
lady | -0.010 |
gentleman | -0.009 |
woman | -0.009 |
cal | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.009 |
ors | +0.009 |
bar | +0.009 |
usted | +0.009 |
Neg logit contributions | |
lady | -0.003 |
woman | -0.003 |
man | -0.002 |
stranger | -0.002 |
gentleman | -0.002 |
Token | One |
Token ID | 3198 |
Feature activation | +4.53e-03 |
Pos logit contributions | |
lady | +0.020 |
woman | +0.018 |
stranger | +0.018 |
relief | +0.018 |
gentleman | +0.018 |
Neg logit contributions | |
ug | -0.021 |
ors | -0.020 |
eds | -0.019 |
issors | -0.019 |
bed | -0.018 |
Token | ily |
Token ID | 813 |
Feature activation | +6.26e-03 |
Pos logit contributions | |
relief | +0.024 |
lady | +0.023 |
gentleman | +0.022 |
woman | +0.022 |
cal | +0.022 |
Neg logit contributions | |
ug | -0.039 |
issors | -0.038 |
bar | -0.037 |
usted | -0.036 |
bed | -0.036 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
lady | +0.008 |
relief | +0.008 |
cal | +0.008 |
woman | +0.008 |
man | +0.008 |
Neg logit contributions | |
ug | -0.013 |
issors | -0.012 |
utes | -0.012 |
ors | -0.011 |
bar | -0.011 |
Token | that |
Token ID | 326 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
ug | +0.057 |
issors | +0.054 |
bar | +0.053 |
bowl | +0.053 |
ors | +0.052 |
Neg logit contributions | |
relief | -0.029 |
lady | -0.029 |
woman | -0.027 |
stranger | -0.027 |
cal | -0.027 |
Token | l |
Token ID | 300 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
ug | +0.066 |
issors | +0.065 |
leys | +0.063 |
utes | +0.060 |
ors | +0.060 |
Neg logit contributions | |
lady | -0.054 |
relief | -0.051 |
woman | -0.051 |
cal | -0.049 |
man | -0.049 |
Token | oll |
Token ID | 692 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
ug | +0.034 |
utes | +0.033 |
bed | +0.033 |
issors | +0.033 |
leys | +0.033 |
Neg logit contributions | |
relief | -0.035 |
lady | -0.033 |
gentleman | -0.033 |
cal | -0.032 |
stranger | -0.031 |
Token | ip |
Token ID | 541 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ug | +0.036 |
issors | +0.033 |
usted | +0.030 |
ors | +0.030 |
bar | +0.029 |
Neg logit contributions | |
relief | -0.119 |
lady | -0.115 |
gentleman | -0.114 |
woman | -0.113 |
cal | -0.112 |
Token | ops |
Token ID | 2840 |
Feature activation | -9.25e-02 |
Pos logit contributions | |
ug | +0.170 |
issors | +0.161 |
usted | +0.151 |
ors | +0.151 |
bed | +0.149 |
Neg logit contributions | |
relief | -0.306 |
lady | -0.294 |
gentleman | -0.293 |
woman | -0.290 |
stranger | -0.287 |
Token | are |
Token ID | 389 |
Feature activation | +2.43e-03 |
Pos logit contributions | |
ug | +0.139 |
issors | +0.133 |
usted | +0.128 |
ors | +0.127 |
bar | +0.126 |
Neg logit contributions | |
relief | -0.164 |
gentleman | -0.158 |
lady | -0.156 |
woman | -0.154 |
stranger | -0.151 |
Token | fragile |
Token ID | 21049 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
relief | +0.004 |
lady | +0.003 |
cal | +0.003 |
woman | +0.003 |
gentleman | +0.003 |
Neg logit contributions | |
ug | -0.004 |
issors | -0.004 |
ors | -0.004 |
utes | -0.004 |
bed | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +5.95e-03 |
Pos logit contributions | |
ug | +0.085 |
issors | +0.081 |
usted | +0.079 |
ors | +0.079 |
bed | +0.078 |
Neg logit contributions | |
relief | -0.088 |
gentleman | -0.084 |
lady | -0.083 |
woman | -0.082 |
stranger | -0.080 |
Token | can |
Token ID | 460 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
relief | +0.009 |
lady | +0.009 |
woman | +0.009 |
gentleman | +0.009 |
cal | +0.009 |
Neg logit contributions | |
ug | -0.010 |
issors | -0.010 |
usted | -0.009 |
utes | -0.009 |
bar | -0.009 |
Token | care |
Token ID | 1337 |
Feature activation | +9.78e-04 |
Pos logit contributions | |
relief | +0.001 |
gentleman | +0.001 |
lady | +0.001 |
woman | +0.001 |
stranger | +0.001 |
Neg logit contributions | |
ug | -0.001 |
issors | -0.001 |
usted | -0.001 |
bed | -0.001 |
ors | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
relief | +0.002 |
lady | +0.002 |
woman | +0.002 |
gentleman | +0.002 |
cal | +0.001 |
Neg logit contributions | |
ug | -0.002 |
issors | -0.002 |
utes | -0.001 |
ors | -0.001 |
bar | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ug | +0.073 |
issors | +0.071 |
bed | +0.069 |
ors | +0.068 |
usted | +0.067 |
Neg logit contributions | |
relief | -0.064 |
gentleman | -0.062 |
stranger | -0.060 |
lady | -0.059 |
woman | -0.058 |
Token | l |
Token ID | 300 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
ug | +0.025 |
issors | +0.025 |
bed | +0.024 |
usted | +0.024 |
ors | +0.024 |
Neg logit contributions | |
relief | -0.026 |
gentleman | -0.025 |
stranger | -0.024 |
Heidi | -0.024 |
woman | -0.023 |
Token | oll |
Token ID | 692 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
ug | +0.062 |
issors | +0.059 |
bed | +0.057 |
utes | +0.057 |
usted | +0.057 |
Neg logit contributions | |
relief | -0.044 |
lady | -0.043 |
gentleman | -0.042 |
woman | -0.041 |
cal | -0.040 |
Token | ip |
Token ID | 541 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ug | +0.030 |
issors | +0.027 |
ors | +0.024 |
usted | +0.024 |
bar | +0.023 |
Neg logit contributions | |
relief | -0.133 |
lady | -0.128 |
gentleman | -0.128 |
woman | -0.127 |
cal | -0.126 |
Token | ops |
Token ID | 2840 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
ug | +0.145 |
issors | +0.139 |
ors | +0.132 |
usted | +0.131 |
bed | +0.130 |
Neg logit contributions | |
relief | -0.333 |
gentleman | -0.317 |
lady | -0.314 |
woman | -0.313 |
stranger | -0.312 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
ug | +0.155 |
issors | +0.148 |
usted | +0.145 |
bed | +0.144 |
ors | +0.144 |
Neg logit contributions | |
relief | -0.157 |
gentleman | -0.148 |
lady | -0.145 |
woman | -0.144 |
cal | -0.142 |
Token | other |
Token ID | 584 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
ug | +0.023 |
issors | +0.022 |
bed | +0.021 |
usted | +0.021 |
bar | +0.021 |
Neg logit contributions | |
relief | -0.026 |
gentleman | -0.025 |
lady | -0.025 |
woman | -0.024 |
stranger | -0.024 |
Token | fragile |
Token ID | 21049 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
ug | +0.039 |
usted | +0.038 |
issors | +0.037 |
ors | +0.037 |
bar | +0.036 |
Neg logit contributions | |
relief | -0.035 |
gentleman | -0.033 |
lady | -0.032 |
stranger | -0.031 |
woman | -0.031 |
Token | things |
Token ID | 1243 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
ug | +0.067 |
usted | +0.064 |
ors | +0.064 |
bed | +0.064 |
issors | +0.063 |
Neg logit contributions | |
relief | -0.058 |
gentleman | -0.054 |
woman | -0.053 |
stranger | -0.053 |
lady | -0.052 |
Token | money |
Token ID | 1637 |
Feature activation | +6.20e-03 |
Pos logit contributions | |
ug | +0.065 |
issors | +0.063 |
usted | +0.061 |
bar | +0.060 |
bed | +0.059 |
Neg logit contributions | |
relief | -0.084 |
gentleman | -0.080 |
lady | -0.078 |
woman | -0.078 |
cal | -0.077 |
Token | away |
Token ID | 1497 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
relief | +0.012 |
gentleman | +0.011 |
cal | +0.011 |
woman | +0.011 |
lady | +0.011 |
Neg logit contributions | |
ug | -0.008 |
issors | -0.008 |
usted | -0.008 |
bar | -0.008 |
ors | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
ug | +0.053 |
bed | +0.052 |
ors | +0.050 |
usted | +0.050 |
issors | +0.050 |
Neg logit contributions | |
relief | -0.064 |
gentleman | -0.061 |
cal | -0.058 |
woman | -0.058 |
stranger | -0.057 |
Token | her |
Token ID | 607 |
Feature activation | +5.76e-03 |
Pos logit contributions | |
ug | +0.091 |
issors | +0.089 |
bed | +0.084 |
bar | +0.083 |
usted | +0.082 |
Neg logit contributions | |
gentleman | -0.082 |
relief | -0.082 |
cal | -0.077 |
lady | -0.076 |
stranger | -0.076 |
Token | pig |
Token ID | 12967 |
Feature activation | -9.31e-02 |
Pos logit contributions | |
Heidi | +0.011 |
relief | +0.011 |
gentleman | +0.010 |
cal | +0.010 |
stranger | +0.010 |
Neg logit contributions | |
issors | -0.007 |
clubs | -0.007 |
ug | -0.007 |
utes | -0.007 |
bed | -0.007 |
Token | gy |
Token ID | 1360 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
ug | +0.132 |
issors | +0.126 |
bar | +0.120 |
ors | +0.120 |
usted | +0.120 |
Neg logit contributions | |
relief | -0.174 |
gentleman | -0.164 |
lady | -0.164 |
cal | -0.161 |
woman | -0.161 |
Token | bank |
Token ID | 17796 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
ug | +0.182 |
issors | +0.173 |
bar | +0.167 |
bed | +0.165 |
usted | +0.165 |
Neg logit contributions | |
relief | -0.289 |
gentleman | -0.273 |
lady | -0.272 |
cal | -0.269 |
woman | -0.267 |
Token | every |
Token ID | 790 |
Feature activation | -5.49e-02 |
Pos logit contributions | |
ug | +0.077 |
issors | +0.074 |
usted | +0.074 |
bed | +0.073 |
bar | +0.073 |
Neg logit contributions | |
relief | -0.071 |
gentleman | -0.064 |
cal | -0.063 |
woman | -0.063 |
stranger | -0.062 |
Token | week |
Token ID | 1285 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ug | +0.072 |
bar | +0.063 |
issors | +0.062 |
bowl | +0.061 |
bed | +0.061 |
Neg logit contributions | |
relief | -0.104 |
gentleman | -0.101 |
cal | -0.099 |
lady | -0.096 |
woman | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
ug | +0.024 |
usted | +0.023 |
ors | +0.022 |
bed | +0.022 |
issors | +0.022 |
Neg logit contributions | |
relief | -0.031 |
gentleman | -0.028 |
cal | -0.028 |
stranger | -0.026 |
gen | -0.026 |
Token | This |
Token ID | 770 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
ug | +0.018 |
issors | +0.017 |
usted | +0.017 |
bed | +0.017 |
bowl | +0.016 |
Neg logit contributions | |
relief | -0.021 |
gentleman | -0.020 |
lady | -0.020 |
woman | -0.019 |
stranger | -0.019 |
Token | I |
Token ID | 40 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
bar | +0.057 |
bed | +0.054 |
utes | +0.052 |
issors | +0.050 |
amb | +0.050 |
Neg logit contributions | |
relief | -0.072 |
cal | -0.064 |
service | -0.062 |
witch | -0.061 |
prayer | -0.060 |
Token | will |
Token ID | 481 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
relief | +0.070 |
gentleman | +0.069 |
Heidi | +0.068 |
stranger | +0.067 |
woman | +0.067 |
Neg logit contributions | |
ug | -0.052 |
om | -0.050 |
bowl | -0.049 |
built | -0.047 |
issors | -0.047 |
Token | name |
Token ID | 1438 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
relief | +0.022 |
gentleman | +0.021 |
cal | +0.021 |
woman | +0.020 |
stranger | +0.020 |
Neg logit contributions | |
bed | -0.019 |
ug | -0.019 |
issors | -0.019 |
bar | -0.018 |
often | -0.018 |
Token | him |
Token ID | 683 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
relief | +0.107 |
gentleman | +0.101 |
woman | +0.097 |
cal | +0.094 |
witch | +0.093 |
Neg logit contributions | |
ug | -0.059 |
ors | -0.056 |
bar | -0.056 |
issors | -0.055 |
bed | -0.054 |
Token | Sno |
Token ID | 42578 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
ug | +0.005 |
issors | +0.005 |
bed | +0.005 |
ors | +0.005 |
usted | +0.004 |
Neg logit contributions | |
relief | -0.005 |
gentleman | -0.005 |
woman | -0.005 |
stranger | -0.005 |
cal | -0.005 |
Token | opy |
Token ID | 11081 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ug | +0.021 |
ors | +0.020 |
issors | +0.019 |
utes | +0.018 |
om | +0.018 |
Neg logit contributions | |
relief | -0.062 |
gentleman | -0.055 |
cal | -0.055 |
lady | -0.054 |
woman | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
ug | +0.223 |
ors | +0.215 |
issors | +0.213 |
bed | +0.207 |
usted | +0.204 |
Neg logit contributions | |
relief | -0.251 |
cal | -0.224 |
gentleman | -0.217 |
Heidi | -0.210 |
woman | -0.208 |
Token | Because |
Token ID | 4362 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
relief | +0.020 |
service | +0.018 |
woman | +0.018 |
stranger | +0.018 |
lady | +0.018 |
Neg logit contributions | |
bar | -0.013 |
issors | -0.012 |
ug | -0.012 |
bowl | -0.012 |
ors | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
relief | +0.018 |
gentleman | +0.016 |
cal | +0.015 |
lady | +0.015 |
woman | +0.015 |
Neg logit contributions | |
ug | -0.021 |
bar | -0.019 |
issors | -0.019 |
ors | -0.019 |
utes | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
om | +0.022 |
ors | +0.022 |
often | +0.021 |
bed | +0.021 |
fet | +0.020 |
Neg logit contributions | |
relief | -0.045 |
gentleman | -0.041 |
woman | -0.039 |
stranger | -0.039 |
lady | -0.038 |
Token | nos |
Token ID | 43630 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
relief | +0.043 |
gentleman | +0.043 |
service | +0.040 |
vation | +0.039 |
ment | +0.038 |
Neg logit contributions | |
often | -0.027 |
ug | -0.025 |
both | -0.025 |
om | -0.025 |
everywhere | -0.025 |
Token | 't |
Token ID | 470 |
Feature activation | -5.80e-02 |
Pos logit contributions | |
ug | +0.079 |
leys | +0.079 |
issors | +0.077 |
eds | +0.075 |
bowl | +0.075 |
Neg logit contributions | |
cal | -0.090 |
lady | -0.089 |
relief | -0.088 |
stranger | -0.086 |
gentleman | -0.084 |
Token | want |
Token ID | 765 |
Feature activation | +5.87e-03 |
Pos logit contributions | |
ug | +0.101 |
issors | +0.097 |
usted | +0.094 |
ors | +0.093 |
bar | +0.093 |
Neg logit contributions | |
relief | -0.089 |
lady | -0.085 |
gentleman | -0.084 |
woman | -0.082 |
cal | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
relief | +0.011 |
cal | +0.011 |
lady | +0.011 |
stranger | +0.011 |
gentleman | +0.011 |
Neg logit contributions | |
ug | -0.008 |
issors | -0.007 |
utes | -0.007 |
usted | -0.007 |
bar | -0.007 |
Token | get |
Token ID | 651 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
relief | +0.005 |
gentleman | +0.004 |
woman | +0.004 |
lady | +0.004 |
stranger | +0.004 |
Neg logit contributions | |
ug | -0.004 |
issors | -0.004 |
bed | -0.004 |
bar | -0.004 |
ors | -0.004 |
Token | anything |
Token ID | 1997 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
relief | +0.032 |
lady | +0.031 |
gentleman | +0.030 |
cal | +0.030 |
woman | +0.030 |
Neg logit contributions | |
ug | -0.038 |
issors | -0.036 |
utes | -0.035 |
usted | -0.035 |
ors | -0.034 |
Token | stuck |
Token ID | 7819 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
gentleman | +0.089 |
relief | +0.089 |
woman | +0.087 |
lady | +0.086 |
stranger | +0.081 |
Neg logit contributions | |
ug | -0.071 |
issors | -0.066 |
ors | -0.066 |
usted | -0.066 |
bar | -0.066 |
Token | in |
Token ID | 287 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
issors | +0.269 |
utes | +0.266 |
ug | +0.258 |
usted | +0.256 |
ants | +0.254 |
Neg logit contributions | |
lady | -0.178 |
relief | -0.172 |
man | -0.167 |
stranger | -0.166 |
gentleman | -0.162 |
Token | his |
Token ID | 465 |
Feature activation | -6.16e-03 |
Pos logit contributions | |
ug | +0.107 |
usted | +0.105 |
issors | +0.105 |
utes | +0.105 |
leys | +0.103 |
Neg logit contributions | |
relief | -0.056 |
lady | -0.050 |
cal | -0.049 |
woman | -0.047 |
stranger | -0.047 |
Token | teeth |
Token ID | 9941 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.009 |
bar | +0.008 |
bed | +0.008 |
usted | +0.008 |
Neg logit contributions | |
relief | -0.011 |
gentleman | -0.011 |
lady | -0.011 |
woman | -0.010 |
cal | -0.010 |
Token | again |
Token ID | 757 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
ug | +0.115 |
issors | +0.111 |
usted | +0.107 |
utes | +0.106 |
ors | +0.106 |
Neg logit contributions | |
relief | -0.069 |
lady | -0.065 |
gentleman | -0.064 |
woman | -0.062 |
cal | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e-03 |
Pos logit contributions | |
relief | +0.026 |
gentleman | +0.024 |
lady | +0.024 |
woman | +0.024 |
cal | +0.023 |
Neg logit contributions | |
ug | -0.041 |
issors | -0.039 |
usted | -0.038 |
bed | -0.038 |
ors | -0.038 |
Token | all |
Token ID | 477 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
ug | +0.023 |
issors | +0.022 |
usted | +0.022 |
bar | +0.021 |
bed | +0.021 |
Neg logit contributions | |
relief | -0.027 |
lady | -0.025 |
gentleman | -0.025 |
woman | -0.025 |
cal | -0.025 |
Token | valued |
Token ID | 17560 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
ug | +0.065 |
usted | +0.059 |
bar | +0.058 |
bed | +0.058 |
bowl | +0.057 |
Neg logit contributions | |
relief | -0.087 |
gentleman | -0.083 |
lady | -0.082 |
woman | -0.081 |
cal | -0.080 |
Token | their |
Token ID | 511 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
ug | +0.068 |
issors | +0.064 |
bed | +0.064 |
ors | +0.061 |
usted | +0.061 |
Neg logit contributions | |
relief | -0.084 |
gentleman | -0.082 |
lady | -0.081 |
woman | -0.081 |
stranger | -0.079 |
Token | l |
Token ID | 300 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
bed | +0.024 |
clubs | +0.024 |
ug | +0.024 |
issors | +0.024 |
usted | +0.024 |
Neg logit contributions | |
relief | -0.026 |
gentleman | -0.025 |
Heidi | -0.024 |
woman | -0.024 |
cal | -0.024 |
Token | oll |
Token ID | 692 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
ug | +0.056 |
issors | +0.053 |
usted | +0.051 |
bar | +0.051 |
ors | +0.050 |
Neg logit contributions | |
relief | -0.054 |
woman | -0.050 |
lady | -0.050 |
gentleman | -0.049 |
cal | -0.049 |
Token | ip |
Token ID | 541 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
ug | +0.052 |
ors | +0.048 |
issors | +0.048 |
bed | +0.046 |
bar | +0.045 |
Neg logit contributions | |
relief | -0.096 |
cal | -0.090 |
gentleman | -0.089 |
woman | -0.089 |
lady | -0.089 |
Token | ops |
Token ID | 2840 |
Feature activation | -8.96e-02 |
Pos logit contributions | |
bed | +0.109 |
ug | +0.108 |
ors | +0.108 |
issors | +0.101 |
usted | +0.099 |
Neg logit contributions | |
relief | -0.363 |
gentleman | -0.342 |
woman | -0.339 |
cal | -0.338 |
stranger | -0.337 |
Token | the |
Token ID | 262 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
ug | +0.138 |
bowl | +0.130 |
bed | +0.130 |
bar | +0.129 |
usted | +0.129 |
Neg logit contributions | |
relief | -0.161 |
gentleman | -0.153 |
woman | -0.147 |
cal | -0.144 |
stranger | -0.144 |
Token | same |
Token ID | 976 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
issors | +0.031 |
bar | +0.029 |
clubs | +0.029 |
bowl | +0.029 |
ug | +0.028 |
Neg logit contributions | |
relief | -0.045 |
gentleman | -0.043 |
cal | -0.041 |
Heidi | -0.041 |
woman | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -6.61e-03 |
Pos logit contributions | |
ug | +0.009 |
bed | +0.009 |
usted | +0.009 |
issors | +0.008 |
bowl | +0.008 |
Neg logit contributions | |
relief | -0.010 |
gentleman | -0.009 |
cal | -0.009 |
Heidi | -0.009 |
woman | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
ug | +0.011 |
issors | +0.010 |
usted | +0.010 |
bar | +0.010 |
ors | +0.010 |
Neg logit contributions | |
relief | -0.011 |
lady | -0.010 |
gentleman | -0.010 |
woman | -0.010 |
cal | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-03 |
Pos logit contributions | |
relief | +0.049 |
gentleman | +0.047 |
stranger | +0.044 |
Heidi | +0.044 |
woman | +0.044 |
Neg logit contributions | |
bed | -0.037 |
ug | -0.037 |
usted | -0.035 |
bar | -0.033 |
eds | -0.033 |
Token | |
Token ID | 220 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
ug | +0.002 |
issors | +0.002 |
usted | +0.002 |
bar | +0.002 |
bed | +0.002 |
Neg logit contributions | |
relief | -0.003 |
stranger | -0.003 |
lady | -0.003 |
gentleman | -0.003 |
woman | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.24e-03 |
Pos logit contributions | |
ug | +0.074 |
issors | +0.070 |
usted | +0.068 |
utes | +0.067 |
bed | +0.066 |
Neg logit contributions | |
relief | -0.084 |
gentleman | -0.080 |
stranger | -0.080 |
woman | -0.080 |
lady | -0.079 |
Token |
|
Token ID | 198 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
ug | +0.007 |
issors | +0.007 |
ors | +0.006 |
bar | +0.006 |
usted | +0.006 |
Neg logit contributions | |
relief | -0.004 |
lady | -0.004 |
gentleman | -0.004 |
cal | -0.004 |
woman | -0.004 |
Token | The |
Token ID | 464 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
relief | +0.016 |
lady | +0.016 |
gentleman | +0.015 |
woman | +0.015 |
cal | +0.015 |
Neg logit contributions | |
ug | -0.019 |
issors | -0.018 |
ors | -0.018 |
usted | -0.017 |
bar | -0.017 |
Token | next |
Token ID | 1306 |
Feature activation | +8.74e-02 |
Pos logit contributions | |
Debbie | +0.036 |
gentleman | +0.035 |
MacDonald | +0.035 |
Heidi | +0.035 |
ment | +0.035 |
Neg logit contributions | |
ug | -0.032 |
everywhere | -0.031 |
clubs | -0.030 |
bricks | -0.030 |
bed | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
gentleman | +0.203 |
relief | +0.202 |
Heidi | +0.202 |
cal | +0.197 |
amused | +0.195 |
Neg logit contributions | |
ug | -0.075 |
utes | -0.056 |
often | -0.048 |
bar | -0.047 |
inn | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +5.27e-03 |
Pos logit contributions | |
gentleman | +0.087 |
relief | +0.085 |
pastor | +0.080 |
stranger | +0.079 |
woman | +0.078 |
Neg logit contributions | |
ug | -0.053 |
usted | -0.045 |
bed | -0.042 |
built | -0.041 |
leys | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
gentleman | +0.010 |
witch | +0.009 |
title | +0.009 |
woman | +0.009 |
pastor | +0.009 |
Neg logit contributions | |
ug | -0.006 |
bed | -0.006 |
usted | -0.006 |
bowl | -0.005 |
bar | -0.005 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
MacDonald | +0.049 |
ment | +0.048 |
gentleman | +0.046 |
Debbie | +0.046 |
Heidi | +0.044 |
Neg logit contributions | |
everywhere | -0.035 |
ug | -0.033 |
bricks | -0.032 |
brick | -0.031 |
bed | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
ug | +0.018 |
bed | +0.017 |
bar | +0.016 |
eds | +0.016 |
usted | +0.016 |
Neg logit contributions | |
relief | -0.023 |
gentleman | -0.022 |
Heidi | -0.020 |
stranger | -0.020 |
lady | -0.020 |
Token | have |
Token ID | 423 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
ug | +0.108 |
issors | +0.103 |
bar | +0.100 |
usted | +0.099 |
bed | +0.099 |
Neg logit contributions | |
relief | -0.093 |
lady | -0.089 |
gentleman | -0.089 |
woman | -0.087 |
cal | -0.086 |
Token | together |
Token ID | 1978 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
ug | +0.034 |
bed | +0.033 |
eds | +0.030 |
ors | +0.030 |
leys | +0.030 |
Neg logit contributions | |
relief | -0.073 |
gentleman | -0.072 |
woman | -0.070 |
lady | -0.070 |
stranger | -0.069 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ug | +0.075 |
bed | +0.071 |
usted | +0.069 |
issors | +0.069 |
bar | +0.069 |
Neg logit contributions | |
relief | -0.071 |
gentleman | -0.068 |
woman | -0.066 |
lady | -0.066 |
stranger | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
relief | +0.047 |
gentleman | +0.044 |
lady | +0.043 |
woman | +0.042 |
cal | +0.042 |
Neg logit contributions | |
ug | -0.055 |
issors | -0.051 |
ors | -0.051 |
bed | -0.051 |
usted | -0.050 |
Token | The |
Token ID | 383 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.008 |
usted | +0.008 |
ors | +0.008 |
bar | +0.008 |
Neg logit contributions | |
relief | -0.006 |
lady | -0.006 |
gentleman | -0.006 |
woman | -0.006 |
cal | -0.006 |
Token | end |
Token ID | 886 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
gentleman | +0.024 |
Heidi | +0.024 |
Eva | +0.024 |
Debbie | +0.023 |
cal | +0.023 |
Neg logit contributions | |
issors | -0.020 |
usted | -0.020 |
clubs | -0.019 |
ug | -0.019 |
bar | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.63e-03 |
Pos logit contributions | |
gentleman | +0.159 |
relief | +0.150 |
woman | +0.146 |
Heidi | +0.145 |
stranger | +0.145 |
Neg logit contributions | |
ug | -0.128 |
eds | -0.117 |
ors | -0.113 |
utes | -0.113 |
om | -0.111 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
relief | +0.011 |
lady | +0.010 |
gentleman | +0.010 |
woman | +0.010 |
cal | +0.010 |
Neg logit contributions | |
ug | -0.014 |
issors | -0.013 |
usted | -0.013 |
ors | -0.013 |
bar | -0.013 |
Token | Once |
Token ID | 7454 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
relief | +0.026 |
lady | +0.025 |
gentleman | +0.025 |
woman | +0.024 |
cal | +0.024 |
Neg logit contributions | |
ug | -0.032 |
issors | -0.031 |
usted | -0.030 |
ors | -0.029 |
bar | -0.029 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
issors | +0.015 |
bar | +0.015 |
ug | +0.015 |
bed | +0.014 |
usted | +0.014 |
Neg logit contributions | |
lady | -0.015 |
man | -0.014 |
woman | -0.014 |
stranger | -0.014 |
relief | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ug | +0.004 |
issors | +0.004 |
bed | +0.004 |
usted | +0.004 |
bowl | +0.004 |
Neg logit contributions | |
relief | -0.003 |
gentleman | -0.003 |
lady | -0.003 |
woman | -0.003 |
cal | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -4.04e-03 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.009 |
utes | +0.009 |
ors | +0.008 |
usted | +0.008 |
Neg logit contributions | |
relief | -0.005 |
lady | -0.005 |
gentleman | -0.005 |
cal | -0.005 |
woman | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +6.28e-03 |
Pos logit contributions | |
ug | +0.006 |
issors | +0.006 |
bed | +0.006 |
usted | +0.006 |
ors | +0.005 |
Neg logit contributions | |
relief | -0.007 |
gentleman | -0.007 |
lady | -0.007 |
woman | -0.007 |
cal | -0.007 |
Token | made |
Token ID | 925 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
lady | +0.009 |
relief | +0.009 |
man | +0.008 |
cal | +0.008 |
woman | +0.008 |
Neg logit contributions | |
ug | -0.012 |
issors | -0.011 |
utes | -0.011 |
ants | -0.010 |
ors | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
ug | +0.100 |
issors | +0.096 |
usted | +0.096 |
bed | +0.094 |
ors | +0.092 |
Neg logit contributions | |
relief | -0.066 |
gentleman | -0.066 |
lady | -0.063 |
woman | -0.062 |
stranger | -0.061 |
Token | loud |
Token ID | 7812 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
ug | +0.066 |
issors | +0.064 |
ors | +0.062 |
usted | +0.061 |
bed | +0.061 |
Neg logit contributions | |
relief | -0.039 |
lady | -0.036 |
gentleman | -0.035 |
woman | -0.035 |
cal | -0.035 |
Token | noise |
Token ID | 7838 |
Feature activation | +7.91e-02 |
Pos logit contributions | |
gentleman | +0.011 |
relief | +0.011 |
woman | +0.010 |
lady | +0.010 |
stranger | +0.010 |
Neg logit contributions | |
ug | -0.027 |
bar | -0.025 |
bed | -0.025 |
ors | -0.025 |
usted | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -5.59e-03 |
Pos logit contributions | |
relief | +0.136 |
gentleman | +0.132 |
Heidi | +0.127 |
woman | +0.124 |
lady | +0.124 |
Neg logit contributions | |
ug | -0.128 |
ors | -0.118 |
bed | -0.116 |
usted | -0.115 |
bar | -0.111 |
Token | |
Token ID | 220 |
Feature activation | -4.94e-02 |
Pos logit contributions | |
ug | +0.012 |
issors | +0.011 |
bar | +0.011 |
eds | +0.011 |
ors | +0.011 |
Neg logit contributions | |
lady | -0.007 |
relief | -0.007 |
woman | -0.006 |
gentleman | -0.006 |
man | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
ug | +0.111 |
bar | +0.107 |
issors | +0.105 |
ors | +0.104 |
usted | +0.103 |
Neg logit contributions | |
lady | -0.046 |
relief | -0.045 |
woman | -0.041 |
man | -0.040 |
cal | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ug | +0.012 |
bar | +0.012 |
issors | +0.012 |
ors | +0.011 |
usted | +0.011 |
Neg logit contributions | |
lady | -0.004 |
woman | -0.003 |
man | -0.003 |
Heidi | -0.003 |
relief | -0.003 |
Token | Her |
Token ID | 9360 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
lady | +0.014 |
relief | +0.013 |
woman | +0.013 |
gentleman | +0.013 |
stranger | +0.013 |
Neg logit contributions | |
ug | -0.020 |
bar | -0.019 |
issors | -0.018 |
ors | -0.018 |
eds | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +3.29e-04 |
Pos logit contributions | |
relief | +0.055 |
gentleman | +0.054 |
woman | +0.050 |
cal | +0.049 |
stranger | +0.048 |
Neg logit contributions | |
ug | -0.037 |
usted | -0.035 |
ors | -0.034 |
bed | -0.034 |
om | -0.034 |
Token | she |
Token ID | 673 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
relief | +0.001 |
cal | +0.001 |
gentleman | +0.001 |
gru | +0.000 |
vation | +0.000 |
Neg logit contributions | |
usted | -0.000 |
bed | -0.000 |
ants | -0.000 |
everywhere | -0.000 |
often | -0.000 |
Token | wants |
Token ID | 3382 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
ug | +0.003 |
issors | +0.003 |
bar | +0.002 |
usted | +0.002 |
bed | +0.002 |
Neg logit contributions | |
relief | -0.002 |
lady | -0.002 |
woman | -0.002 |
cal | -0.002 |
gentleman | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
lady | +0.032 |
relief | +0.032 |
woman | +0.031 |
stranger | +0.031 |
gentleman | +0.031 |
Neg logit contributions | |
ug | -0.019 |
issors | -0.017 |
ors | -0.016 |
usted | -0.016 |
bed | -0.016 |
Token | paint |
Token ID | 7521 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
lady | +0.027 |
relief | +0.027 |
woman | +0.024 |
service | +0.024 |
cal | +0.024 |
Neg logit contributions | |
ug | -0.034 |
ors | -0.032 |
eds | -0.032 |
leys | -0.032 |
issors | -0.031 |
Token | something |
Token ID | 1223 |
Feature activation | +7.40e-02 |
Pos logit contributions | |
relief | +0.028 |
gentleman | +0.027 |
woman | +0.025 |
stranger | +0.025 |
lady | +0.024 |
Neg logit contributions | |
ug | -0.026 |
issors | -0.025 |
bar | -0.025 |
bed | -0.024 |
ors | -0.024 |
Token | new |
Token ID | 649 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
relief | +0.118 |
gentleman | +0.109 |
woman | +0.102 |
cal | +0.099 |
Heidi | +0.099 |
Neg logit contributions | |
ug | -0.125 |
utes | -0.122 |
issors | -0.121 |
usted | -0.119 |
ors | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-03 |
Pos logit contributions | |
ug | +0.021 |
bed | +0.020 |
issors | +0.020 |
ors | +0.020 |
usted | +0.019 |
Neg logit contributions | |
relief | -0.020 |
gentleman | -0.019 |
cal | -0.018 |
woman | -0.018 |
lady | -0.018 |
Token | She |
Token ID | 1375 |
Feature activation | +8.32e-03 |
Pos logit contributions | |
issors | +0.010 |
usted | +0.010 |
ug | +0.010 |
bar | +0.009 |
bed | +0.009 |
Neg logit contributions | |
relief | -0.010 |
cal | -0.009 |
service | -0.009 |
gentleman | -0.009 |
woman | -0.009 |
Token | thinks |
Token ID | 6834 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
lady | +0.012 |
relief | +0.012 |
cal | +0.012 |
woman | +0.012 |
man | +0.012 |
Neg logit contributions | |
ug | -0.014 |
bar | -0.014 |
issors | -0.014 |
bed | -0.013 |
bowl | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
relief | +0.049 |
lady | +0.048 |
woman | +0.046 |
cal | +0.045 |
stranger | +0.044 |
Neg logit contributions | |
ug | -0.058 |
issors | -0.057 |
eds | -0.056 |
bowl | -0.056 |
bar | -0.056 |
Token | friendly |
Token ID | 8030 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ug | +0.053 |
utes | +0.053 |
issors | +0.052 |
usted | +0.051 |
bar | +0.051 |
Neg logit contributions | |
relief | -0.049 |
gentleman | -0.046 |
Heidi | -0.044 |
cal | -0.043 |
lady | -0.042 |
Token | smile |
Token ID | 8212 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
relief | +0.014 |
cal | +0.014 |
Heidi | +0.013 |
Eva | +0.013 |
gentleman | +0.013 |
Neg logit contributions | |
ug | -0.020 |
utes | -0.019 |
issors | -0.018 |
clubs | -0.018 |
usted | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -9.31e-03 |
Pos logit contributions | |
relief | +0.046 |
cal | +0.042 |
gentleman | +0.041 |
lady | +0.040 |
woman | +0.040 |
Neg logit contributions | |
ug | -0.035 |
bar | -0.033 |
usted | -0.032 |
issors | -0.032 |
ors | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ug | +0.014 |
issors | +0.012 |
bowl | +0.012 |
bar | +0.012 |
utes | +0.012 |
Neg logit contributions | |
relief | -0.017 |
lady | -0.016 |
stranger | -0.016 |
gentleman | -0.015 |
woman | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
issors | +0.017 |
ug | +0.017 |
usted | +0.016 |
ors | +0.016 |
bar | +0.015 |
Neg logit contributions | |
relief | -0.019 |
lady | -0.019 |
gentleman | -0.018 |
woman | -0.018 |
stranger | -0.018 |
Token | Everyone |
Token ID | 16190 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
relief | +0.005 |
lady | +0.005 |
gentleman | +0.005 |
woman | +0.005 |
stranger | +0.005 |
Neg logit contributions | |
ug | -0.005 |
issors | -0.005 |
ors | -0.005 |
bed | -0.005 |
usted | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
relief | +0.158 |
gentleman | +0.144 |
lady | +0.142 |
Heidi | +0.141 |
woman | +0.140 |
Neg logit contributions | |
ug | -0.109 |
bed | -0.100 |
usted | -0.099 |
bowl | -0.099 |
ors | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ug | +0.029 |
ir | +0.026 |
utes | +0.024 |
om | +0.024 |
targets | +0.024 |
Neg logit contributions | |
gentleman | -0.034 |
relief | -0.033 |
lady | -0.033 |
cal | -0.032 |
stranger | -0.031 |
Token | park |
Token ID | 3952 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
gen | +0.050 |
relief | +0.050 |
Heidi | +0.049 |
cal | +0.048 |
gentleman | +0.048 |
Neg logit contributions | |
clubs | -0.039 |
ug | -0.038 |
issors | -0.038 |
utes | -0.036 |
targets | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
relief | +0.111 |
gentleman | +0.101 |
cal | +0.100 |
stranger | +0.099 |
Heidi | +0.098 |
Neg logit contributions | |
ug | -0.065 |
bed | -0.065 |
built | -0.060 |
usted | -0.059 |
bar | -0.057 |
Token | so |
Token ID | 523 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
ug | +0.035 |
bar | +0.031 |
usted | +0.031 |
built | +0.031 |
often | +0.031 |
Neg logit contributions | |
gentleman | -0.047 |
relief | -0.047 |
woman | -0.044 |
stranger | -0.044 |
witch | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
gentleman | +0.064 |
relief | +0.064 |
lady | +0.059 |
stranger | +0.058 |
cal | +0.058 |
Neg logit contributions | |
ug | -0.050 |
usted | -0.047 |
bar | -0.046 |
bowl | -0.046 |
issors | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
ug | +0.022 |
often | +0.020 |
bed | +0.020 |
issors | +0.020 |
usted | +0.020 |
Neg logit contributions | |
gentleman | -0.027 |
woman | -0.025 |
stranger | -0.025 |
lady | -0.024 |
service | -0.024 |
Token | day |
Token ID | 1110 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
relief | +0.005 |
gentleman | +0.005 |
ment | +0.005 |
Heidi | +0.005 |
cal | +0.005 |
Neg logit contributions | |
issors | -0.004 |
targets | -0.004 |
utes | -0.004 |
ug | -0.004 |
bar | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
gentleman | +0.075 |
relief | +0.072 |
stranger | +0.069 |
cal | +0.068 |
pastor | +0.068 |
Neg logit contributions | |
ug | -0.059 |
usted | -0.051 |
bed | -0.050 |
ors | -0.048 |
often | -0.047 |
Token | weird |
Token ID | 7650 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
relief | +0.003 |
gentleman | +0.003 |
Heidi | +0.003 |
cal | +0.003 |
ment | +0.003 |
Neg logit contributions | |
issors | -0.004 |
ug | -0.003 |
utes | -0.003 |
targets | -0.003 |
hamm | -0.003 |
Token | witch |
Token ID | 16365 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
relief | +0.006 |
cal | +0.006 |
gentleman | +0.006 |
Heidi | +0.005 |
Debbie | +0.005 |
Neg logit contributions | |
ug | -0.007 |
alk | -0.007 |
bed | -0.007 |
utes | -0.007 |
often | -0.006 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.88e-02 |
Pos logit contributions | |
relief | +0.030 |
gentleman | +0.029 |
cal | +0.027 |
stranger | +0.027 |
lady | +0.026 |
Neg logit contributions | |
ug | -0.018 |
bed | -0.017 |
ors | -0.016 |
bowl | -0.016 |
bar | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
usted | +0.083 |
ug | +0.083 |
ors | +0.079 |
issors | +0.077 |
bed | +0.077 |
Neg logit contributions | |
relief | -0.101 |
gentleman | -0.100 |
woman | -0.094 |
lady | -0.091 |
stranger | -0.089 |
Token | discussing |
Token ID | 11142 |
Feature activation | -4.23e-03 |
Pos logit contributions | |
ug | +0.076 |
bed | +0.072 |
issors | +0.070 |
usted | +0.070 |
bar | +0.069 |
Neg logit contributions | |
gentleman | -0.084 |
relief | -0.081 |
lady | -0.075 |
woman | -0.075 |
stranger | -0.074 |
Token | can |
Token ID | 460 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
ug | +0.006 |
issors | +0.006 |
ors | +0.006 |
clubs | +0.006 |
everywhere | +0.006 |
Neg logit contributions | |
gentleman | -0.008 |
relief | -0.007 |
woman | -0.007 |
lady | -0.007 |
stranger | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | +4.07e-03 |
Pos logit contributions | |
ug | +0.105 |
bar | +0.101 |
issors | +0.098 |
bed | +0.096 |
ors | +0.095 |
Neg logit contributions | |
relief | -0.119 |
gentleman | -0.116 |
woman | -0.109 |
lady | -0.107 |
stranger | -0.106 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
ug | +0.022 |
issors | +0.021 |
usted | +0.021 |
ors | +0.020 |
bar | +0.020 |
Neg logit contributions | |
relief | -0.019 |
lady | -0.018 |
gentleman | -0.018 |
woman | -0.017 |
cal | -0.017 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
relief | +0.065 |
gentleman | +0.061 |
cal | +0.059 |
woman | +0.058 |
lady | +0.058 |
Neg logit contributions | |
ug | -0.036 |
issors | -0.034 |
ors | -0.033 |
usted | -0.033 |
bar | -0.031 |
Token | |
Token ID | 220 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
ug | +0.021 |
bed | +0.020 |
issors | +0.020 |
usted | +0.020 |
ors | +0.019 |
Neg logit contributions | |
relief | -0.028 |
gentleman | -0.026 |
stranger | -0.026 |
cal | -0.025 |
lady | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
ug | +0.117 |
issors | +0.112 |
usted | +0.108 |
bar | +0.107 |
ors | +0.107 |
Neg logit contributions | |
relief | -0.093 |
lady | -0.089 |
gentleman | -0.087 |
woman | -0.086 |
cal | -0.085 |
Token |
|
Token ID | 198 |
Feature activation | -2.00e-03 |
Pos logit contributions | |
ug | +0.043 |
issors | +0.043 |
bar | +0.041 |
usted | +0.041 |
ors | +0.041 |
Neg logit contributions | |
lady | -0.023 |
relief | -0.022 |
woman | -0.021 |
gentleman | -0.021 |
man | -0.020 |
Token | The |
Token ID | 464 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ug | +0.004 |
issors | +0.003 |
ors | +0.003 |
usted | +0.003 |
bar | +0.003 |
Neg logit contributions | |
relief | -0.003 |
lady | -0.003 |
gentleman | -0.003 |
woman | -0.003 |
stranger | -0.003 |
Token | man |
Token ID | 582 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
relief | +0.023 |
Heidi | +0.022 |
Eva | +0.020 |
Alice | +0.020 |
Debbie | +0.020 |
Neg logit contributions | |
issors | -0.036 |
hamm | -0.036 |
clubs | -0.034 |
hammer | -0.034 |
drib | -0.034 |
Token | felt |
Token ID | 2936 |
Feature activation | -7.50e-03 |
Pos logit contributions | |
relief | +0.048 |
gentleman | +0.045 |
service | +0.043 |
Heidi | +0.043 |
stranger | +0.043 |
Neg logit contributions | |
usted | -0.046 |
ug | -0.046 |
bed | -0.046 |
bar | -0.044 |
bowl | -0.041 |
Token | sorry |
Token ID | 7926 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
ug | +0.010 |
usted | +0.010 |
bowl | +0.010 |
bed | +0.009 |
bar | +0.009 |
Neg logit contributions | |
gentleman | -0.012 |
woman | -0.012 |
service | -0.012 |
lady | -0.012 |
witch | -0.012 |
Token | for |
Token ID | 329 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
relief | +0.093 |
gentleman | +0.092 |
woman | +0.089 |
lady | +0.089 |
stranger | +0.088 |
Neg logit contributions | |
ug | -0.040 |
usted | -0.037 |
issors | -0.035 |
bar | -0.035 |
bed | -0.034 |
Token | her |
Token ID | 607 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
gentleman | +0.008 |
relief | +0.008 |
woman | +0.008 |
stranger | +0.007 |
prayer | +0.007 |
Neg logit contributions | |
ug | -0.006 |
bed | -0.006 |
ir | -0.005 |
often | -0.005 |
bar | -0.005 |
Token | each |
Token ID | 1123 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
relief | +0.021 |
lady | +0.020 |
gentleman | +0.019 |
woman | +0.019 |
cal | +0.019 |
Neg logit contributions | |
ug | -0.016 |
issors | -0.015 |
usted | -0.015 |
bar | -0.015 |
ors | -0.015 |
Token | other |
Token ID | 584 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
ug | +0.047 |
ors | +0.043 |
utes | +0.043 |
bar | +0.043 |
issors | +0.042 |
Neg logit contributions | |
lady | -0.039 |
relief | -0.036 |
woman | -0.036 |
stranger | -0.035 |
man | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +9.63e-03 |
Pos logit contributions | |
bed | +0.054 |
usted | +0.054 |
issors | +0.052 |
ors | +0.051 |
ug | +0.050 |
Neg logit contributions | |
relief | -0.075 |
gentleman | -0.074 |
woman | -0.068 |
stranger | -0.067 |
Heidi | -0.067 |
Token | They |
Token ID | 1119 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
relief | +0.018 |
gentleman | +0.017 |
lady | +0.017 |
woman | +0.016 |
stranger | +0.016 |
Neg logit contributions | |
ug | -0.014 |
issors | -0.013 |
usted | -0.013 |
utes | -0.013 |
bed | -0.013 |
Token | nod |
Token ID | 18666 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
gentleman | +0.010 |
relief | +0.010 |
woman | +0.010 |
lady | +0.010 |
service | +0.010 |
Neg logit contributions | |
issors | -0.009 |
ug | -0.009 |
usted | -0.009 |
bed | -0.009 |
bowl | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
gentleman | +0.082 |
relief | +0.080 |
stranger | +0.076 |
woman | +0.076 |
lady | +0.075 |
Neg logit contributions | |
ug | -0.076 |
bed | -0.075 |
utes | -0.071 |
usted | -0.071 |
issors | -0.071 |
Token | They |
Token ID | 1119 |
Feature activation | +4.66e-03 |
Pos logit contributions | |
relief | +0.018 |
gentleman | +0.017 |
lady | +0.017 |
stranger | +0.017 |
woman | +0.017 |
Neg logit contributions | |
ug | -0.014 |
issors | -0.014 |
utes | -0.013 |
usted | -0.013 |
bed | -0.013 |
Token | say |
Token ID | 910 |
Feature activation | +6.26e-02 |
Pos logit contributions | |
gentleman | +0.008 |
woman | +0.008 |
relief | +0.008 |
lady | +0.007 |
service | +0.007 |
Neg logit contributions | |
issors | -0.007 |
usted | -0.006 |
ug | -0.006 |
bowl | -0.006 |
drib | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
relief | +0.102 |
gentleman | +0.101 |
woman | +0.095 |
stranger | +0.093 |
lady | +0.092 |
Neg logit contributions | |
ug | -0.102 |
bed | -0.094 |
issors | -0.093 |
usted | -0.093 |
utes | -0.091 |
Token | " |
Token ID | 366 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
ug | +0.012 |
issors | +0.012 |
bed | +0.012 |
usted | +0.011 |
utes | +0.011 |
Neg logit contributions | |
relief | -0.013 |
gentleman | -0.012 |
stranger | -0.012 |
lady | -0.012 |
cal | -0.012 |
Token | OK |
Token ID | 11380 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
issors | +0.074 |
ug | +0.073 |
bed | +0.073 |
usted | +0.071 |
bar | +0.071 |
Neg logit contributions | |
relief | -0.069 |
gentleman | -0.065 |
cal | -0.063 |
stranger | -0.063 |
witch | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
relief | +0.068 |
Heidi | +0.064 |
gentleman | +0.061 |
woman | +0.059 |
lady | +0.058 |
Neg logit contributions | |
ug | -0.041 |
often | -0.039 |
everywhere | -0.039 |
ors | -0.039 |
bed | -0.037 |
Token | One |
Token ID | 1881 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
ug | +0.008 |
usted | +0.007 |
eds | +0.007 |
issors | +0.007 |
bed | +0.007 |
Neg logit contributions | |
relief | -0.005 |
lady | -0.005 |
gentleman | -0.005 |
man | -0.004 |
Heidi | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
ug | +0.010 |
bowl | +0.009 |
utes | +0.008 |
om | +0.008 |
ogram | +0.008 |
Neg logit contributions | |
relief | -0.027 |
cal | -0.026 |
gentleman | -0.026 |
MacDonald | -0.025 |
Heidi | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
relief | +0.088 |
gentleman | +0.084 |
lady | +0.084 |
woman | +0.083 |
cal | +0.083 |
Neg logit contributions | |
ug | -0.097 |
issors | -0.092 |
bed | -0.091 |
usted | -0.090 |
ors | -0.088 |
Token | his |
Token ID | 465 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
relief | +0.019 |
lady | +0.018 |
gentleman | +0.017 |
woman | +0.017 |
stranger | +0.017 |
Neg logit contributions | |
ug | -0.025 |
issors | -0.024 |
usted | -0.023 |
ors | -0.023 |
bar | -0.023 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
relief | +0.045 |
cal | +0.042 |
gentleman | +0.042 |
Heidi | +0.040 |
lady | +0.039 |
Neg logit contributions | |
ug | -0.044 |
utes | -0.043 |
issors | -0.042 |
usted | -0.041 |
bed | -0.040 |
Token | gave |
Token ID | 2921 |
Feature activation | -8.80e-03 |
Pos logit contributions | |
relief | +0.076 |
gentleman | +0.071 |
lady | +0.071 |
woman | +0.070 |
cal | +0.070 |
Neg logit contributions | |
ug | -0.057 |
issors | -0.054 |
usted | -0.053 |
bar | -0.052 |
ors | -0.052 |
Token | him |
Token ID | 683 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
ug | +0.016 |
issors | +0.015 |
utes | +0.014 |
bar | +0.014 |
usted | +0.014 |
Neg logit contributions | |
relief | -0.013 |
lady | -0.013 |
stranger | -0.012 |
woman | -0.012 |
gentleman | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
relief | +0.005 |
gentleman | +0.004 |
lady | +0.004 |
woman | +0.004 |
cal | +0.004 |
Neg logit contributions | |
ug | -0.005 |
issors | -0.005 |
usted | -0.005 |
bar | -0.005 |
ors | -0.005 |
Token | present |
Token ID | 1944 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
issors | +0.036 |
ug | +0.035 |
utes | +0.035 |
bar | +0.034 |
usted | +0.034 |
Neg logit contributions | |
relief | -0.029 |
gentleman | -0.026 |
cal | -0.026 |
lady | -0.025 |
Heidi | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
relief | +0.062 |
gentleman | +0.058 |
cal | +0.058 |
lady | +0.058 |
woman | +0.057 |
Neg logit contributions | |
ug | -0.047 |
issors | -0.045 |
bar | -0.043 |
usted | -0.043 |
bed | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
relief | +0.015 |
gentleman | +0.014 |
woman | +0.014 |
cal | +0.014 |
lady | +0.014 |
Neg logit contributions | |
ug | -0.015 |
issors | -0.014 |
bar | -0.014 |
ors | -0.014 |
usted | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
ug | +0.007 |
issors | +0.006 |
usted | +0.006 |
bed | +0.006 |
bar | +0.006 |
Neg logit contributions | |
relief | -0.007 |
gentleman | -0.007 |
cal | -0.007 |
stranger | -0.007 |
lady | -0.007 |
Token | Stop |
Token ID | 19485 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
ug | +0.095 |
issors | +0.093 |
usted | +0.089 |
bar | +0.089 |
ors | +0.088 |
Neg logit contributions | |
relief | -0.068 |
gentleman | -0.062 |
lady | -0.062 |
cal | -0.061 |
woman | -0.060 |
Token | fighting |
Token ID | 4330 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
relief | +0.154 |
gentleman | +0.146 |
lady | +0.144 |
cal | +0.143 |
woman | +0.143 |
Neg logit contributions | |
ug | -0.111 |
ors | -0.105 |
issors | -0.103 |
bed | -0.101 |
usted | -0.097 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ug | +0.006 |
issors | +0.006 |
bar | +0.005 |
usted | +0.005 |
utes | +0.005 |
Neg logit contributions | |
relief | -0.004 |
lady | -0.004 |
gentleman | -0.004 |
cal | -0.004 |
woman | -0.004 |
Token | children |
Token ID | 1751 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
issors | +0.019 |
ug | +0.017 |
usted | +0.017 |
bar | +0.017 |
ors | +0.016 |
Neg logit contributions | |
relief | -0.018 |
cal | -0.018 |
gentleman | -0.017 |
prayer | -0.017 |
ment | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
relief | +0.010 |
gentleman | +0.010 |
lady | +0.009 |
woman | +0.009 |
cal | +0.009 |
Neg logit contributions | |
ug | -0.013 |
issors | -0.012 |
ors | -0.012 |
usted | -0.012 |
bar | -0.012 |
Token | Why |
Token ID | 4162 |
Feature activation | +7.44e-02 |
Pos logit contributions | |
relief | +0.010 |
lady | +0.010 |
gentleman | +0.010 |
woman | +0.009 |
cal | +0.009 |
Neg logit contributions | |
ug | -0.012 |
issors | -0.012 |
usted | -0.011 |
ors | -0.011 |
bar | -0.011 |
Token | don |
Token ID | 836 |
Feature activation | +2.45e-03 |
Pos logit contributions | |
relief | +0.144 |
gentleman | +0.140 |
woman | +0.134 |
cal | +0.132 |
lady | +0.131 |
Neg logit contributions | |
ug | -0.104 |
issors | -0.102 |
ors | -0.094 |
usted | -0.093 |
utes | -0.090 |
Token | 't |
Token ID | 470 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
relief | +0.005 |
lady | +0.005 |
gentleman | +0.005 |
woman | +0.005 |
stranger | +0.005 |
Neg logit contributions | |
ug | -0.003 |
issors | -0.003 |
usted | -0.003 |
bar | -0.003 |
bed | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
ug | +0.057 |
issors | +0.056 |
ors | +0.054 |
bar | +0.053 |
usted | +0.053 |
Neg logit contributions | |
relief | -0.053 |
gentleman | -0.049 |
cal | -0.048 |
woman | -0.048 |
lady | -0.048 |
Token | One |
Token ID | 3198 |
Feature activation | +4.46e-03 |
Pos logit contributions | |
lady | +0.023 |
stranger | +0.021 |
woman | +0.021 |
man | +0.021 |
gentleman | +0.021 |
Neg logit contributions | |
ug | -0.020 |
ors | -0.019 |
issors | -0.019 |
usted | -0.019 |
eds | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
relief | +0.009 |
gentleman | +0.008 |
cal | +0.008 |
lady | +0.008 |
woman | +0.008 |
Neg logit contributions | |
ug | -0.006 |
issors | -0.005 |
utes | -0.005 |
bowl | -0.005 |
bar | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
relief | +0.072 |
lady | +0.069 |
gentleman | +0.066 |
woman | +0.065 |
stranger | +0.065 |
Neg logit contributions | |
ug | -0.109 |
issors | -0.107 |
bar | -0.103 |
usted | -0.103 |
ors | -0.102 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
relief | +0.023 |
gentleman | +0.022 |
cal | +0.022 |
lady | +0.021 |
woman | +0.021 |
Neg logit contributions | |
ug | -0.031 |
issors | -0.030 |
bed | -0.029 |
usted | -0.029 |
utes | -0.029 |
Token | new |
Token ID | 649 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
relief | +0.030 |
Heidi | +0.030 |
gentleman | +0.029 |
ment | +0.028 |
cal | +0.028 |
Neg logit contributions | |
ug | -0.035 |
hamm | -0.033 |
utes | -0.033 |
om | -0.031 |
accidentally | -0.031 |
Token | green |
Token ID | 4077 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
relief | +0.065 |
cal | +0.059 |
Heidi | +0.056 |
gentleman | +0.056 |
stranger | +0.053 |
Neg logit contributions | |
ug | -0.109 |
bar | -0.103 |
issors | -0.100 |
utes | -0.099 |
bed | -0.097 |
Token | truck |
Token ID | 7779 |
Feature activation | +7.17e-03 |
Pos logit contributions | |
ug | +0.041 |
bar | +0.038 |
issors | +0.037 |
bed | +0.036 |
usted | +0.036 |
Neg logit contributions | |
relief | -0.054 |
cal | -0.050 |
gentleman | -0.050 |
lady | -0.049 |
Heidi | -0.048 |
Token | came |
Token ID | 1625 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
relief | +0.011 |
gentleman | +0.010 |
lady | +0.010 |
woman | +0.010 |
cal | +0.010 |
Neg logit contributions | |
ug | -0.013 |
issors | -0.012 |
usted | -0.012 |
ors | -0.012 |
bar | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
lady | +0.036 |
cal | +0.035 |
man | +0.034 |
woman | +0.032 |
stranger | +0.032 |
Neg logit contributions | |
issors | -0.048 |
igs | -0.043 |
angles | -0.043 |
ug | -0.042 |
ors | -0.042 |
Token | play |
Token ID | 711 |
Feature activation | +8.36e-03 |
Pos logit contributions | |
relief | +0.044 |
gentleman | +0.044 |
lady | +0.041 |
stranger | +0.041 |
cal | +0.041 |
Neg logit contributions | |
ug | -0.050 |
issors | -0.048 |
bed | -0.046 |
bar | -0.046 |
utes | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
relief | +0.011 |
lady | +0.010 |
gentleman | +0.010 |
woman | +0.010 |
cal | +0.010 |
Neg logit contributions | |
ug | -0.016 |
issors | -0.016 |
usted | -0.016 |
bar | -0.015 |
ors | -0.015 |
Token | � |
Token ID | 241 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
ug | +0.005 |
issors | +0.004 |
usted | +0.004 |
bar | +0.004 |
ors | +0.004 |
Neg logit contributions | |
relief | -0.004 |
lady | -0.004 |
gentleman | -0.004 |
woman | -0.004 |
cal | -0.004 |
Token | Let |
Token ID | 5756 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
ug | +0.049 |
issors | +0.047 |
usted | +0.045 |
bed | +0.045 |
utes | +0.045 |
Neg logit contributions | |
relief | -0.044 |
cal | -0.041 |
lady | -0.041 |
gentleman | -0.040 |
stranger | -0.040 |
Token | â |
Token ID | 22940 |
Feature activation | -3.09e-02 |
Pos logit contributions | |
ug | +0.003 |
usted | +0.003 |
bar | +0.003 |
ors | +0.003 |
issors | +0.003 |
Neg logit contributions | |
relief | -0.007 |
gentleman | -0.006 |
woman | -0.006 |
service | -0.006 |
lady | -0.006 |
Token | € |
Token ID | 26391 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
ug | +0.052 |
issors | +0.051 |
bar | +0.049 |
bed | +0.045 |
ors | +0.045 |
Neg logit contributions | |
woman | -0.051 |
stranger | -0.051 |
witch | -0.049 |
lady | -0.049 |
relief | -0.048 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
ug | +0.013 |
issors | +0.012 |
ors | +0.012 |
om | +0.012 |
utes | +0.012 |
Neg logit contributions | |
relief | -0.021 |
stranger | -0.019 |
cal | -0.019 |
lady | -0.019 |
woman | -0.019 |
Token | s |
Token ID | 82 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
ug | +0.039 |
issors | +0.039 |
utes | +0.037 |
bed | +0.037 |
igs | +0.037 |
Neg logit contributions | |
lady | -0.048 |
gentleman | -0.046 |
stranger | -0.044 |
man | -0.043 |
woman | -0.043 |
Token | play |
Token ID | 711 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ug | +0.129 |
issors | +0.121 |
bar | +0.118 |
usted | +0.117 |
bed | +0.116 |
Neg logit contributions | |
relief | -0.139 |
gentleman | -0.134 |
lady | -0.131 |
woman | -0.131 |
cal | -0.128 |
Token | a |
Token ID | 257 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
relief | +0.019 |
gentleman | +0.019 |
woman | +0.018 |
lady | +0.018 |
stranger | +0.017 |
Neg logit contributions | |
ug | -0.019 |
bed | -0.018 |
bar | -0.017 |
utes | -0.017 |
bowl | -0.017 |
Token | game |
Token ID | 983 |
Feature activation | -3.79e-03 |
Pos logit contributions | |
ug | +0.047 |
issors | +0.045 |
usted | +0.043 |
bar | +0.043 |
utes | +0.043 |
Neg logit contributions | |
relief | -0.049 |
lady | -0.047 |
gentleman | -0.047 |
woman | -0.046 |
cal | -0.045 |
Token | ! |
Token ID | 0 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
ug | +0.006 |
issors | +0.006 |
bar | +0.006 |
ors | +0.006 |
usted | +0.006 |
Neg logit contributions | |
relief | -0.006 |
gentleman | -0.006 |
woman | -0.006 |
lady | -0.006 |
cal | -0.006 |
Token | â |
Token ID | 22940 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
ug | +0.028 |
issors | +0.027 |
usted | +0.026 |
bar | +0.026 |
ors | +0.025 |
Neg logit contributions | |
relief | -0.027 |
lady | -0.025 |
stranger | -0.025 |
woman | -0.025 |
gentleman | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
ug | +0.017 |
usted | +0.017 |
bed | +0.016 |
bar | +0.015 |
everywhere | +0.015 |
Neg logit contributions | |
relief | -0.043 |
gentleman | -0.042 |
woman | -0.041 |
service | -0.040 |
lady | -0.040 |
Token | always |
Token ID | 1464 |
Feature activation | -9.84e-03 |
Pos logit contributions | |
relief | +0.014 |
gentleman | +0.014 |
woman | +0.014 |
lady | +0.014 |
stranger | +0.013 |
Neg logit contributions | |
ug | -0.014 |
bar | -0.013 |
issors | -0.013 |
bed | -0.013 |
bowl | -0.012 |
Token | listen |
Token ID | 6004 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
bed | +0.012 |
built | +0.012 |
drib | +0.012 |
bowl | +0.012 |
eds | +0.012 |
Neg logit contributions | |
relief | -0.017 |
gentleman | -0.017 |
woman | -0.017 |
gen | -0.017 |
stranger | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
relief | +0.075 |
gentleman | +0.071 |
woman | +0.069 |
lady | +0.069 |
cal | +0.068 |
Neg logit contributions | |
ug | -0.040 |
usted | -0.038 |
bed | -0.037 |
issors | -0.037 |
ors | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
ug | +0.017 |
issors | +0.017 |
eds | +0.016 |
ors | +0.016 |
bed | +0.016 |
Neg logit contributions | |
relief | -0.014 |
lady | -0.014 |
gentleman | -0.013 |
woman | -0.013 |
cal | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
relief | +0.014 |
lady | +0.013 |
gentleman | +0.013 |
woman | +0.013 |
stranger | +0.013 |
Neg logit contributions | |
ug | -0.011 |
issors | -0.010 |
bed | -0.010 |
usted | -0.010 |
bar | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
ug | +0.015 |
usted | +0.015 |
bed | +0.014 |
bar | +0.014 |
often | +0.013 |
Neg logit contributions | |
relief | -0.023 |
gentleman | -0.022 |
woman | -0.022 |
stranger | -0.022 |
lady | -0.021 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
relief | +0.003 |
woman | +0.003 |
gentleman | +0.003 |
witch | +0.003 |
stranger | +0.002 |
Neg logit contributions | |
ug | -0.002 |
often | -0.002 |
om | -0.002 |
drib | -0.002 |
usted | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
relief | +0.056 |
cal | +0.050 |
gentleman | +0.050 |
woman | +0.048 |
gen | +0.048 |
Neg logit contributions | |
bed | -0.028 |
ors | -0.027 |
ug | -0.027 |
usted | -0.026 |
utes | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
gentleman | +0.018 |
relief | +0.018 |
lady | +0.018 |
woman | +0.018 |
stranger | +0.018 |
Neg logit contributions | |
ug | -0.019 |
issors | -0.018 |
usted | -0.017 |
bed | -0.017 |
ors | -0.017 |
Token | silly |
Token ID | 14397 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
gentleman | +0.007 |
relief | +0.007 |
Heidi | +0.007 |
cal | +0.007 |
stranger | +0.006 |
Neg logit contributions | |
issors | -0.006 |
ug | -0.006 |
utes | -0.006 |
clubs | -0.006 |
bed | -0.006 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
Heidi | +0.029 |
relief | +0.026 |
Eva | +0.025 |
Sophia | +0.024 |
gentleman | +0.024 |
Neg logit contributions | |
ug | -0.021 |
everywhere | -0.021 |
often | -0.021 |
usted | -0.019 |
bowl | -0.019 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
relief | +0.046 |
gentleman | +0.043 |
stranger | +0.041 |
cal | +0.041 |
lady | +0.041 |
Neg logit contributions | |
ug | -0.039 |
usted | -0.038 |
bed | -0.038 |
bar | -0.036 |
bowl | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ug | +0.010 |
issors | +0.010 |
usted | +0.010 |
bed | +0.009 |
eds | +0.009 |
Neg logit contributions | |
relief | -0.044 |
gentleman | -0.044 |
woman | -0.041 |
cal | -0.040 |
lady | -0.040 |
Token | bake |
Token ID | 28450 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
gentleman | +0.017 |
relief | +0.017 |
woman | +0.016 |
cal | +0.016 |
stranger | +0.016 |
Neg logit contributions | |
ug | -0.014 |
issors | -0.014 |
bowl | -0.013 |
bar | -0.013 |
bed | -0.013 |
Token | something |
Token ID | 1223 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
gentleman | +0.101 |
woman | +0.091 |
stranger | +0.091 |
relief | +0.090 |
pastor | +0.084 |
Neg logit contributions | |
bed | -0.050 |
usted | -0.048 |
issors | -0.048 |
ug | -0.047 |
igs | -0.046 |
Token | y |
Token ID | 331 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
relief | +0.113 |
gentleman | +0.110 |
woman | +0.104 |
cal | +0.097 |
witch | +0.096 |
Neg logit contributions | |
ug | -0.065 |
bowl | -0.065 |
usted | -0.064 |
bar | -0.063 |
utes | -0.063 |
Token | ummy |
Token ID | 13513 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
ug | +0.100 |
issors | +0.096 |
utes | +0.093 |
usted | +0.093 |
bar | +0.091 |
Neg logit contributions | |
relief | -0.120 |
lady | -0.116 |
gentleman | -0.113 |
stranger | -0.112 |
cal | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-03 |
Pos logit contributions | |
bowl | +0.046 |
ors | +0.045 |
bed | +0.044 |
ug | +0.044 |
usted | +0.043 |
Neg logit contributions | |
relief | -0.073 |
gentleman | -0.070 |
woman | -0.068 |
cal | -0.066 |
pastor | -0.064 |
Token | They |
Token ID | 1119 |
Feature activation | -7.88e-05 |
Pos logit contributions | |
ug | +0.003 |
issors | +0.003 |
usted | +0.003 |
bed | +0.003 |
ors | +0.003 |
Neg logit contributions | |
relief | -0.003 |
gentleman | -0.003 |
lady | -0.002 |
stranger | -0.002 |
cal | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
ug | +0.000 |
utes | +0.000 |
issors | +0.000 |
ors | +0.000 |
eds | +0.000 |
Neg logit contributions | |
lady | -0.000 |
woman | -0.000 |
relief | -0.000 |
man | -0.000 |
cal | -0.000 |
Token | flour |
Token ID | 10601 |
Feature activation | +9.29e-03 |
Pos logit contributions | |
ug | +0.019 |
usted | +0.019 |
issors | +0.019 |
bar | +0.018 |
bed | +0.018 |
Neg logit contributions | |
gentleman | -0.022 |
relief | -0.022 |
stranger | -0.021 |
lady | -0.020 |
woman | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | -1.61e-05 |
Pos logit contributions | |
ug | +0.010 |
eds | +0.009 |
utes | +0.009 |
issors | +0.009 |
leys | +0.009 |
Neg logit contributions | |
lady | -0.008 |
relief | -0.008 |
gentleman | -0.008 |
man | -0.008 |
woman | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
ug | +0.000 |
issors | +0.000 |
utes | +0.000 |
ors | +0.000 |
bar | +0.000 |
Neg logit contributions | |
relief | -0.000 |
lady | -0.000 |
woman | -0.000 |
cal | -0.000 |
gentleman | -0.000 |
Token | so |
Token ID | 523 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
relief | +0.002 |
lady | +0.002 |
cal | +0.002 |
woman | +0.002 |
gentleman | +0.002 |
Neg logit contributions | |
ug | -0.003 |
ors | -0.002 |
issors | -0.002 |
utes | -0.002 |
eds | -0.002 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.87e-03 |
Pos logit contributions | |
relief | +0.014 |
lady | +0.013 |
gentleman | +0.012 |
cal | +0.012 |
stranger | +0.012 |
Neg logit contributions | |
ug | -0.030 |
issors | -0.029 |
ors | -0.029 |
bar | -0.028 |
eds | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
relief | +0.007 |
cal | +0.006 |
gentleman | +0.006 |
woman | +0.006 |
lady | +0.006 |
Neg logit contributions | |
ors | -0.003 |
ug | -0.003 |
usted | -0.003 |
issors | -0.003 |
bed | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
ug | +0.044 |
issors | +0.042 |
usted | +0.041 |
bar | +0.041 |
ors | +0.041 |
Neg logit contributions | |
relief | -0.021 |
lady | -0.020 |
gentleman | -0.019 |
woman | -0.019 |
cal | -0.019 |
Token | started |
Token ID | 2067 |
Feature activation | -6.70e-02 |
Pos logit contributions | |
ug | +0.049 |
issors | +0.047 |
utes | +0.045 |
bar | +0.045 |
ors | +0.044 |
Neg logit contributions | |
relief | -0.055 |
lady | -0.053 |
gentleman | -0.052 |
cal | -0.051 |
woman | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
ug | +0.101 |
issors | +0.093 |
utes | +0.089 |
bar | +0.087 |
ors | +0.086 |
Neg logit contributions | |
relief | -0.123 |
lady | -0.120 |
cal | -0.117 |
stranger | -0.116 |
woman | -0.115 |
Token | shake |
Token ID | 13279 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
relief | +0.019 |
lady | +0.018 |
gentleman | +0.017 |
woman | +0.017 |
cal | +0.017 |
Neg logit contributions | |
ug | -0.022 |
issors | -0.021 |
usted | -0.021 |
ors | -0.020 |
bar | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | +8.82e-03 |
Pos logit contributions | |
relief | +0.004 |
lady | +0.004 |
gentleman | +0.004 |
woman | +0.004 |
cal | +0.004 |
Neg logit contributions | |
ug | -0.005 |
issors | -0.005 |
utes | -0.005 |
usted | -0.005 |
bar | -0.005 |
Token | happiness |
Token ID | 12157 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
gentleman | +0.013 |
lady | +0.013 |
relief | +0.013 |
woman | +0.013 |
stranger | +0.012 |
Neg logit contributions | |
ug | -0.015 |
issors | -0.015 |
usted | -0.014 |
bed | -0.014 |
bar | -0.014 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
lady | +0.013 |
woman | +0.013 |
relief | +0.012 |
man | +0.012 |
cal | +0.012 |
Neg logit contributions | |
ug | -0.021 |
issors | -0.021 |
bar | -0.019 |
ors | -0.019 |
utes | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
relief | +0.009 |
lady | +0.008 |
gentleman | +0.008 |
woman | +0.008 |
cal | +0.008 |
Neg logit contributions | |
ug | -0.014 |
issors | -0.014 |
usted | -0.013 |
ors | -0.013 |
bar | -0.013 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
relief | +0.038 |
gentleman | +0.035 |
lady | +0.034 |
cal | +0.034 |
woman | +0.034 |
Neg logit contributions | |
ug | -0.048 |
issors | -0.047 |
usted | -0.046 |
utes | -0.045 |
bed | -0.045 |
Token | if |
Token ID | 611 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
relief | +0.025 |
lady | +0.024 |
gentleman | +0.023 |
woman | +0.023 |
cal | +0.023 |
Neg logit contributions | |
ug | -0.024 |
issors | -0.023 |
usted | -0.021 |
ors | -0.021 |
utes | -0.021 |
Token | she |
Token ID | 673 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
accidentally | +0.029 |
bed | +0.027 |
ug | +0.027 |
couldn | +0.026 |
bar | +0.026 |
Neg logit contributions | |
relief | -0.029 |
gentleman | -0.026 |
cal | -0.025 |
title | -0.024 |
vation | -0.024 |
Token | could |
Token ID | 714 |
Feature activation | -9.52e-02 |
Pos logit contributions | |
ug | +0.028 |
issors | +0.025 |
bed | +0.025 |
usted | +0.025 |
ors | +0.024 |
Neg logit contributions | |
relief | -0.090 |
gentleman | -0.086 |
lady | -0.085 |
service | -0.084 |
cal | -0.084 |
Token | have |
Token ID | 423 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ug | +0.179 |
issors | +0.170 |
ors | +0.166 |
usted | +0.166 |
bar | +0.165 |
Neg logit contributions | |
relief | -0.134 |
lady | -0.131 |
woman | -0.123 |
gentleman | -0.123 |
cal | -0.122 |
Token | it |
Token ID | 340 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
ug | +0.026 |
usted | +0.026 |
bed | +0.025 |
issors | +0.025 |
bar | +0.024 |
Neg logit contributions | |
gentleman | -0.030 |
relief | -0.029 |
lady | -0.028 |
woman | -0.028 |
stranger | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
ug | +0.018 |
bed | +0.017 |
bar | +0.017 |
issors | +0.017 |
usted | +0.017 |
Neg logit contributions | |
relief | -0.022 |
gentleman | -0.021 |
woman | -0.021 |
stranger | -0.020 |
pastor | -0.020 |
Token | but |
Token ID | 475 |
Feature activation | -1.62e-04 |
Pos logit contributions | |
ug | +0.041 |
issors | +0.039 |
usted | +0.038 |
ors | +0.037 |
bar | +0.037 |
Neg logit contributions | |
relief | -0.038 |
lady | -0.036 |
gentleman | -0.036 |
woman | -0.035 |
cal | -0.035 |
Token | her |
Token ID | 607 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
ug | +0.000 |
issors | +0.000 |
bed | +0.000 |
usted | +0.000 |
bar | +0.000 |
Neg logit contributions | |
relief | -0.000 |
gentleman | -0.000 |
cal | -0.000 |
stranger | -0.000 |
lady | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ug | +0.029 |
ors | +0.027 |
bar | +0.027 |
usted | +0.027 |
bed | +0.026 |
Neg logit contributions | |
relief | -0.040 |
gentleman | -0.036 |
cal | -0.035 |
lady | -0.035 |
service | -0.035 |
Token | she |
Token ID | 673 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
ug | +0.031 |
bowl | +0.028 |
bar | +0.028 |
ors | +0.028 |
bed | +0.028 |
Neg logit contributions | |
relief | -0.036 |
gentleman | -0.035 |
cal | -0.032 |
lady | -0.032 |
woman | -0.031 |
Token | thought |
Token ID | 1807 |
Feature activation | -4.14e-03 |
Pos logit contributions | |
ug | +0.041 |
ors | +0.037 |
bowl | +0.037 |
bed | +0.037 |
usted | +0.037 |
Neg logit contributions | |
relief | -0.065 |
gentleman | -0.062 |
lady | -0.061 |
service | -0.060 |
woman | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ug | +0.006 |
issors | +0.005 |
ors | +0.005 |
bar | +0.005 |
usted | +0.005 |
Neg logit contributions | |
relief | -0.008 |
gentleman | -0.008 |
cal | -0.007 |
lady | -0.007 |
woman | -0.007 |
Token | pie |
Token ID | 2508 |
Feature activation | +3.70e-04 |
Pos logit contributions | |
issors | +0.027 |
bar | +0.027 |
bowl | +0.025 |
usted | +0.024 |
ug | +0.023 |
Neg logit contributions | |
relief | -0.045 |
gentleman | -0.045 |
cal | -0.042 |
woman | -0.042 |
stranger | -0.040 |
Token | might |
Token ID | 1244 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
relief | +0.001 |
gentleman | +0.001 |
cal | +0.001 |
woman | +0.001 |
pastor | +0.001 |
Neg logit contributions | |
bowl | -0.000 |
bar | -0.000 |
ug | -0.000 |
bed | -0.000 |
issors | -0.000 |
Token | be |
Token ID | 307 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
ug | +0.143 |
issors | +0.139 |
bar | +0.138 |
bowl | +0.130 |
bed | +0.130 |
Neg logit contributions | |
gentleman | -0.151 |
relief | -0.148 |
woman | -0.143 |
lady | -0.140 |
stranger | -0.136 |
Token | in |
Token ID | 287 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
gentleman | +0.007 |
woman | +0.007 |
relief | +0.007 |
lady | +0.007 |
stranger | +0.006 |
Neg logit contributions | |
ug | -0.006 |
issors | -0.005 |
leys | -0.005 |
built | -0.005 |
usted | -0.005 |
Token | there |
Token ID | 612 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
ug | +0.084 |
issors | +0.082 |
bar | +0.078 |
eds | +0.077 |
bed | +0.077 |
Neg logit contributions | |
gentleman | -0.075 |
relief | -0.071 |
lady | -0.069 |
woman | -0.069 |
stranger | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
ug | +0.099 |
issors | +0.094 |
bar | +0.092 |
bed | +0.092 |
usted | +0.091 |
Neg logit contributions | |
relief | -0.103 |
gentleman | -0.098 |
lady | -0.094 |
woman | -0.094 |
cal | -0.093 |
Token | Josh |
Token ID | 8518 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
ug | +0.011 |
issors | +0.011 |
usted | +0.010 |
utes | +0.010 |
bed | +0.010 |
Neg logit contributions | |
relief | -0.011 |
cal | -0.010 |
lady | -0.010 |
stranger | -0.010 |
gentleman | -0.010 |
Token | up |
Token ID | 510 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
lady | +0.010 |
gentleman | +0.010 |
woman | +0.010 |
relief | +0.010 |
stranger | +0.010 |
Neg logit contributions | |
ug | -0.007 |
issors | -0.006 |
usted | -0.006 |
ors | -0.006 |
bar | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
relief | +0.094 |
lady | +0.092 |
gentleman | +0.090 |
woman | +0.090 |
stranger | +0.089 |
Neg logit contributions | |
ug | -0.057 |
issors | -0.054 |
usted | -0.051 |
ors | -0.051 |
bar | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
relief | +0.023 |
gentleman | +0.021 |
cal | +0.021 |
lady | +0.021 |
woman | +0.020 |
Neg logit contributions | |
ug | -0.026 |
issors | -0.025 |
utes | -0.024 |
bed | -0.023 |
ors | -0.023 |
Token | te |
Token ID | 573 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
relief | +0.035 |
cal | +0.031 |
Heidi | +0.029 |
gentleman | +0.028 |
prayer | +0.027 |
Neg logit contributions | |
issors | -0.038 |
bar | -0.037 |
utes | -0.037 |
bowl | -0.036 |
ug | -0.036 |
Token | ash |
Token ID | 1077 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
ug | +0.035 |
issors | +0.032 |
usted | +0.030 |
bar | +0.030 |
ors | +0.030 |
Neg logit contributions | |
relief | -0.078 |
lady | -0.076 |
gentleman | -0.075 |
woman | -0.074 |
cal | -0.074 |
Token | op |
Token ID | 404 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
ug | +0.026 |
issors | +0.022 |
bed | +0.021 |
utes | +0.021 |
ors | +0.021 |
Neg logit contributions | |
relief | -0.073 |
gentleman | -0.068 |
cal | -0.068 |
lady | -0.067 |
woman | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
ug | +0.152 |
issors | +0.149 |
utes | +0.141 |
usted | +0.141 |
bar | +0.139 |
Neg logit contributions | |
lady | -0.115 |
woman | -0.111 |
gentleman | -0.108 |
relief | -0.107 |
man | -0.106 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
ug | +0.018 |
bed | +0.017 |
issors | +0.017 |
bar | +0.017 |
usted | +0.017 |
Neg logit contributions | |
relief | -0.021 |
gentleman | -0.019 |
cal | -0.019 |
lady | -0.018 |
stranger | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +4.93e-03 |
Pos logit contributions | |
relief | +0.012 |
gentleman | +0.011 |
lady | +0.011 |
cal | +0.011 |
woman | +0.010 |
Neg logit contributions | |
ug | -0.014 |
bar | -0.013 |
usted | -0.013 |
bed | -0.013 |
issors | -0.013 |
Token | nice |
Token ID | 3621 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
relief | +0.008 |
gentleman | +0.007 |
Heidi | +0.007 |
cal | +0.007 |
service | +0.007 |
Neg logit contributions | |
utes | -0.008 |
ug | -0.007 |
om | -0.007 |
bar | -0.007 |
issors | -0.007 |
Token | lady |
Token ID | 10846 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
relief | +0.105 |
Heidi | +0.095 |
cal | +0.094 |
gentleman | +0.088 |
Lord | +0.084 |
Neg logit contributions | |
om | -0.107 |
ug | -0.104 |
utes | -0.101 |
bed | -0.094 |
usted | -0.094 |
Token | hair |
Token ID | 4190 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
issors | +0.088 |
ug | +0.086 |
usted | +0.083 |
bed | +0.083 |
bar | +0.081 |
Neg logit contributions | |
relief | -0.112 |
gentleman | -0.110 |
stranger | -0.108 |
cal | -0.106 |
Heidi | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +3.86e-04 |
Pos logit contributions | |
relief | +0.031 |
gentleman | +0.029 |
lady | +0.029 |
woman | +0.028 |
stranger | +0.028 |
Neg logit contributions | |
ug | -0.041 |
issors | -0.040 |
usted | -0.038 |
bar | -0.038 |
ors | -0.038 |
Token | you |
Token ID | 345 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
gentleman | +0.001 |
relief | +0.001 |
stranger | +0.001 |
cal | +0.001 |
Lord | +0.001 |
Neg logit contributions | |
issors | -0.001 |
bed | -0.001 |
ug | -0.001 |
usted | -0.001 |
bar | -0.001 |
Token | wasted |
Token ID | 18359 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
relief | +0.087 |
lady | +0.083 |
gentleman | +0.081 |
woman | +0.081 |
cal | +0.080 |
Neg logit contributions | |
ug | -0.086 |
issors | -0.082 |
utes | -0.079 |
usted | -0.078 |
ors | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ug | +0.052 |
usted | +0.052 |
issors | +0.051 |
bar | +0.049 |
bed | +0.049 |
Neg logit contributions | |
gentleman | -0.058 |
woman | -0.054 |
relief | -0.054 |
stranger | -0.053 |
lady | -0.052 |
Token | leather |
Token ID | 11620 |
Feature activation | -9.13e-02 |
Pos logit contributions | |
issors | +0.020 |
usted | +0.019 |
bar | +0.019 |
ug | +0.019 |
om | +0.018 |
Neg logit contributions | |
gentleman | -0.024 |
relief | -0.023 |
Heidi | -0.023 |
stranger | -0.022 |
cal | -0.022 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.19e-03 |
Pos logit contributions | |
ug | +0.154 |
issors | +0.150 |
bed | +0.149 |
usted | +0.148 |
bar | +0.148 |
Neg logit contributions | |
relief | -0.148 |
cal | -0.135 |
gentleman | -0.132 |
Heidi | -0.128 |
stranger | -0.128 |
Token |
|
Token ID | 198 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
issors | +0.006 |
usted | +0.006 |
om | +0.006 |
ug | +0.006 |
utes | +0.005 |
Neg logit contributions | |
relief | -0.013 |
gentleman | -0.013 |
traveler | -0.012 |
cal | -0.012 |
service | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -4.61e-04 |
Pos logit contributions | |
ug | +0.030 |
issors | +0.029 |
usted | +0.028 |
utes | +0.028 |
bed | +0.027 |
Neg logit contributions | |
relief | -0.029 |
gentleman | -0.028 |
lady | -0.027 |
woman | -0.027 |
stranger | -0.027 |
Token | Tom |
Token ID | 13787 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
issors | +0.001 |
ug | +0.001 |
usted | +0.001 |
utes | +0.001 |
eds | +0.001 |
Neg logit contributions | |
relief | -0.001 |
gentleman | -0.001 |
cal | -0.001 |
stranger | -0.001 |
prayer | -0.001 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
relief | +0.033 |
gentleman | +0.030 |
lady | +0.030 |
woman | +0.030 |
stranger | +0.029 |
Neg logit contributions | |
ug | -0.036 |
usted | -0.035 |
issors | -0.034 |
bed | -0.034 |
bar | -0.033 |
Token | her |
Token ID | 607 |
Feature activation | -4.50e-04 |
Pos logit contributions | |
ug | +0.062 |
issors | +0.060 |
ors | +0.058 |
bar | +0.058 |
utes | +0.058 |
Neg logit contributions | |
relief | -0.034 |
lady | -0.034 |
woman | -0.031 |
gentleman | -0.030 |
cal | -0.030 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
ug | +0.001 |
bed | +0.001 |
usted | +0.001 |
issors | +0.001 |
bar | +0.001 |
Neg logit contributions | |
gentleman | -0.001 |
relief | -0.001 |
service | -0.001 |
stranger | -0.001 |
woman | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
ug | +0.026 |
usted | +0.025 |
bed | +0.025 |
bar | +0.025 |
issors | +0.025 |
Neg logit contributions | |
relief | -0.026 |
gentleman | -0.025 |
stranger | -0.024 |
woman | -0.024 |
lady | -0.023 |
Token | It |
Token ID | 632 |
Feature activation | -9.30e-04 |
Pos logit contributions | |
relief | +0.002 |
gentleman | +0.002 |
lady | +0.002 |
woman | +0.002 |
stranger | +0.002 |
Neg logit contributions | |
ug | -0.003 |
issors | -0.003 |
usted | -0.002 |
bed | -0.002 |
utes | -0.002 |
Token | rub |
Token ID | 6437 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
ug | +0.002 |
bar | +0.002 |
usted | +0.002 |
bed | +0.002 |
issors | +0.001 |
Neg logit contributions | |
relief | -0.001 |
gentleman | -0.001 |
woman | -0.001 |
lady | -0.001 |
stranger | -0.001 |
Token | s |
Token ID | 82 |
Feature activation | -9.27e-02 |
Pos logit contributions | |
ug | +0.026 |
issors | +0.024 |
usted | +0.023 |
bed | +0.023 |
ors | +0.023 |
Neg logit contributions | |
relief | -0.048 |
gentleman | -0.047 |
lady | -0.046 |
woman | -0.046 |
stranger | -0.045 |
Token | its |
Token ID | 663 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
ug | +0.153 |
issors | +0.147 |
usted | +0.142 |
bed | +0.140 |
bar | +0.140 |
Neg logit contributions | |
relief | -0.150 |
gentleman | -0.144 |
lady | -0.143 |
woman | -0.141 |
stranger | -0.138 |
Token | head |
Token ID | 1182 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
ug | +0.064 |
issors | +0.061 |
usted | +0.058 |
ors | +0.058 |
bar | +0.058 |
Neg logit contributions | |
relief | -0.063 |
lady | -0.060 |
gentleman | -0.059 |
woman | -0.059 |
cal | -0.058 |
Token | against |
Token ID | 1028 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
ug | +0.023 |
issors | +0.023 |
usted | +0.022 |
ors | +0.022 |
utes | +0.022 |
Neg logit contributions | |
relief | -0.018 |
lady | -0.018 |
gentleman | -0.017 |
woman | -0.017 |
cal | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -5.94e-03 |
Pos logit contributions | |
ug | +0.047 |
issors | +0.045 |
bed | +0.044 |
usted | +0.043 |
bar | +0.043 |
Neg logit contributions | |
relief | -0.036 |
gentleman | -0.035 |
lady | -0.033 |
cal | -0.033 |
woman | -0.033 |
Token | hand |
Token ID | 1021 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
ug | +0.009 |
issors | +0.008 |
bed | +0.008 |
bar | +0.008 |
usted | +0.008 |
Neg logit contributions | |
relief | -0.011 |
gentleman | -0.010 |
lady | -0.010 |
cal | -0.010 |
stranger | -0.010 |