Token | the |
Token ID | 262 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
aback | +0.021 |
closer | +0.018 |
fired | +0.018 |
away | +0.017 |
home | +0.017 |
Neg logit contributions | |
kin | -0.032 |
pron | -0.031 |
uren | -0.029 |
omo | -0.026 |
lf | -0.025 |
Token | sky |
Token ID | 6766 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
kin | +0.009 |
pron | +0.008 |
uren | +0.008 |
omo | +0.007 |
lf | +0.007 |
Neg logit contributions | |
aback | -0.010 |
closer | -0.009 |
fired | -0.009 |
away | -0.009 |
home | -0.008 |
Token | before |
Token ID | 878 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
kin | +0.064 |
pron | +0.060 |
uren | +0.059 |
omo | +0.054 |
Adam | +0.053 |
Neg logit contributions | |
aback | -0.034 |
closer | -0.034 |
away | -0.032 |
home | -0.031 |
fired | -0.030 |
Token | they |
Token ID | 484 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
kin | +0.013 |
pron | +0.012 |
uren | +0.011 |
omo | +0.010 |
abs | +0.010 |
Neg logit contributions | |
closer | -0.007 |
aback | -0.007 |
home | -0.006 |
away | -0.006 |
fired | -0.006 |
Token | walked |
Token ID | 6807 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
kin | +0.030 |
pron | +0.029 |
uren | +0.027 |
omo | +0.025 |
lf | +0.024 |
Neg logit contributions | |
aback | -0.024 |
closer | -0.023 |
fired | -0.022 |
away | -0.022 |
home | -0.021 |
Token | fore |
Token ID | 1674 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
aback | +0.024 |
fired | +0.019 |
closer | +0.017 |
revenge | +0.017 |
beh | +0.016 |
Neg logit contributions | |
kin | -0.065 |
pron | -0.061 |
uren | -0.059 |
Adam | -0.054 |
omo | -0.053 |
Token | shadow |
Token ID | 19106 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aback | +0.170 |
revenge | +0.155 |
fired | +0.152 |
medical | +0.144 |
Wolf | +0.133 |
Neg logit contributions | |
pron | -0.153 |
uren | -0.148 |
kin | -0.140 |
ast | -0.129 |
Adam | -0.127 |
Token | ed |
Token ID | 276 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.010 |
fired | +0.010 |
revenge | +0.009 |
away | +0.008 |
Neg logit contributions | |
kin | -0.040 |
pron | -0.037 |
uren | -0.036 |
omo | -0.034 |
Adam | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +6.78e-01 |
Pos logit contributions | |
aback | +0.037 |
closer | +0.033 |
fired | +0.032 |
away | +0.029 |
revenge | +0.029 |
Neg logit contributions | |
kin | -0.066 |
pron | -0.062 |
uren | -0.059 |
omo | -0.054 |
lf | -0.053 |
Token | down |
Token ID | 866 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.013 |
fired | +0.012 |
home | +0.012 |
revenge | +0.012 |
Neg logit contributions | |
kin | -0.016 |
pron | -0.014 |
uren | -0.014 |
omo | -0.012 |
Adam | -0.012 |
Token | pour |
Token ID | 48681 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
aback | +0.053 |
closer | +0.047 |
fired | +0.046 |
away | +0.043 |
home | +0.043 |
Neg logit contributions | |
kin | -0.083 |
pron | -0.078 |
uren | -0.073 |
omo | -0.067 |
lf | -0.067 |
Token | yard |
Token ID | 12699 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
kin | +0.013 |
pron | +0.012 |
uren | +0.011 |
omo | +0.010 |
Adam | +0.010 |
Neg logit contributions | |
aback | -0.013 |
fired | -0.012 |
closer | -0.012 |
home | -0.012 |
away | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
kin | +0.064 |
pron | +0.061 |
uren | +0.057 |
omo | +0.052 |
addy | +0.050 |
Neg logit contributions | |
aback | -0.038 |
closer | -0.035 |
home | -0.034 |
away | -0.034 |
fired | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
aback | +0.018 |
fired | +0.015 |
closer | +0.015 |
home | +0.014 |
revenge | +0.014 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
uren | -0.018 |
lf | -0.017 |
bridge | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
kin | +0.012 |
pron | +0.011 |
uren | +0.010 |
omo | +0.009 |
lf | +0.009 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.010 |
fired | -0.010 |
away | -0.010 |
revenge | -0.009 |
Token | been |
Token ID | 587 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
aback | +0.024 |
closer | +0.021 |
fired | +0.021 |
away | +0.020 |
revenge | +0.019 |
Neg logit contributions | |
kin | -0.033 |
pron | -0.031 |
uren | -0.029 |
omo | -0.026 |
lf | -0.026 |
Token | fore |
Token ID | 1674 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
aback | +0.024 |
fired | +0.021 |
closer | +0.020 |
revenge | +0.019 |
nearer | +0.019 |
Neg logit contributions | |
kin | -0.025 |
pron | -0.024 |
uren | -0.021 |
Adam | -0.019 |
lf | -0.019 |
Token | shadow |
Token ID | 19106 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
aback | +0.152 |
fired | +0.137 |
revenge | +0.134 |
closer | +0.120 |
medical | +0.119 |
Neg logit contributions | |
pron | -0.167 |
kin | -0.157 |
uren | -0.151 |
lf | -0.137 |
ast | -0.134 |
Token | ed |
Token ID | 276 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
aback | +0.009 |
closer | +0.008 |
fired | +0.008 |
revenge | +0.007 |
away | +0.007 |
Neg logit contributions | |
kin | -0.026 |
pron | -0.024 |
uren | -0.024 |
omo | -0.022 |
Adam | -0.022 |
Token | about |
Token ID | 546 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
aback | +0.034 |
closer | +0.030 |
fired | +0.029 |
revenge | +0.027 |
away | +0.027 |
Neg logit contributions | |
kin | -0.050 |
pron | -0.046 |
uren | -0.043 |
lf | -0.039 |
omo | -0.039 |
Token | this |
Token ID | 428 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
kin | +0.008 |
pron | +0.007 |
uren | +0.007 |
omo | +0.006 |
lf | +0.006 |
Neg logit contributions | |
aback | -0.005 |
closer | -0.005 |
fired | -0.005 |
revenge | -0.004 |
away | -0.004 |
Token | bad |
Token ID | 2089 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.008 |
fired | +0.007 |
away | +0.007 |
home | +0.007 |
Neg logit contributions | |
kin | -0.008 |
pron | -0.008 |
uren | -0.007 |
Adam | -0.006 |
omo | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
kin | +0.006 |
pron | +0.006 |
uren | +0.005 |
omo | +0.005 |
scalp | +0.005 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
fired | -0.004 |
home | -0.003 |
away | -0.003 |
Token | but |
Token ID | 475 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
kin | +0.059 |
pron | +0.054 |
uren | +0.049 |
lf | +0.045 |
ae | +0.045 |
Neg logit contributions | |
aback | -0.041 |
closer | -0.039 |
home | -0.036 |
away | -0.036 |
fired | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
kin | +0.006 |
pron | +0.006 |
uren | +0.005 |
lf | +0.005 |
omo | +0.005 |
Neg logit contributions | |
aback | -0.006 |
closer | -0.006 |
fired | -0.006 |
away | -0.005 |
revenge | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
aback | +0.015 |
closer | +0.013 |
fired | +0.013 |
away | +0.012 |
revenge | +0.012 |
Neg logit contributions | |
kin | -0.019 |
pron | -0.017 |
uren | -0.016 |
omo | -0.015 |
lf | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
kin | +0.033 |
pron | +0.031 |
uren | +0.028 |
omo | +0.026 |
lf | +0.025 |
Neg logit contributions | |
aback | -0.030 |
closer | -0.027 |
fired | -0.027 |
away | -0.025 |
revenge | -0.025 |
Token | fore |
Token ID | 1674 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
aback | +0.042 |
closer | +0.037 |
fired | +0.037 |
revenge | +0.034 |
nearer | +0.033 |
Neg logit contributions | |
kin | -0.062 |
pron | -0.059 |
uren | -0.053 |
omo | -0.050 |
lf | -0.049 |
Token | shadow |
Token ID | 19106 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
aback | +0.151 |
fired | +0.138 |
revenge | +0.135 |
closer | +0.124 |
home | +0.118 |
Neg logit contributions | |
pron | -0.159 |
kin | -0.149 |
uren | -0.145 |
lf | -0.132 |
Adam | -0.125 |
Token | ed |
Token ID | 276 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.007 |
fired | +0.007 |
away | +0.006 |
revenge | +0.006 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.017 |
uren | -0.017 |
omo | -0.015 |
lf | -0.015 |
Token | by |
Token ID | 416 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
aback | +0.039 |
closer | +0.034 |
fired | +0.034 |
revenge | +0.030 |
home | +0.029 |
Neg logit contributions | |
kin | -0.066 |
pron | -0.061 |
uren | -0.058 |
lf | -0.052 |
omo | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +9.81e-01 |
Pos logit contributions | |
kin | +0.017 |
pron | +0.016 |
uren | +0.015 |
omo | +0.014 |
Adam | +0.013 |
Neg logit contributions | |
aback | -0.012 |
closer | -0.011 |
fired | -0.010 |
revenge | -0.010 |
home | -0.010 |
Token | kind |
Token ID | 1611 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
aback | +0.020 |
closer | +0.018 |
fired | +0.018 |
away | +0.017 |
revenge | +0.017 |
Neg logit contributions | |
kin | -0.024 |
pron | -0.022 |
uren | -0.020 |
lf | -0.018 |
omo | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
kin | +0.002 |
pron | +0.002 |
uren | +0.002 |
scalp | +0.001 |
omo | +0.001 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
fired | -0.001 |
home | -0.001 |
away | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
aback | +0.015 |
closer | +0.013 |
fired | +0.012 |
away | +0.012 |
nearer | +0.012 |
Neg logit contributions | |
kin | -0.016 |
pron | -0.014 |
uren | -0.012 |
scalp | -0.012 |
moons | -0.012 |
Token | girl |
Token ID | 2576 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
kin | +0.013 |
pron | +0.012 |
uren | +0.011 |
omo | +0.010 |
lf | +0.010 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.010 |
fired | -0.010 |
away | -0.009 |
home | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
aback | +0.017 |
closer | +0.015 |
fired | +0.015 |
away | +0.014 |
home | +0.014 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
uren | -0.019 |
omo | -0.017 |
Adam | -0.017 |
Token | been |
Token ID | 587 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
aback | +0.031 |
closer | +0.026 |
fired | +0.025 |
away | +0.025 |
home | +0.024 |
Neg logit contributions | |
kin | -0.047 |
pron | -0.043 |
uren | -0.040 |
omo | -0.038 |
lf | -0.037 |
Token | fore |
Token ID | 1674 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
aback | +0.029 |
fired | +0.027 |
closer | +0.026 |
revenge | +0.025 |
nearer | +0.023 |
Neg logit contributions | |
kin | -0.034 |
pron | -0.032 |
uren | -0.030 |
Adam | -0.027 |
lf | -0.026 |
Token | shadow |
Token ID | 19106 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
aback | +0.147 |
fired | +0.135 |
revenge | +0.132 |
medical | +0.119 |
closer | +0.117 |
Neg logit contributions | |
pron | -0.168 |
kin | -0.159 |
uren | -0.151 |
lf | -0.138 |
Adam | -0.134 |
Token | ed |
Token ID | 276 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.011 |
fired | +0.011 |
revenge | +0.010 |
away | +0.009 |
Neg logit contributions | |
kin | -0.035 |
pron | -0.033 |
uren | -0.032 |
Adam | -0.029 |
ae | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
aback | +0.037 |
closer | +0.033 |
fired | +0.032 |
revenge | +0.029 |
away | +0.029 |
Neg logit contributions | |
kin | -0.059 |
pron | -0.055 |
uren | -0.052 |
lf | -0.047 |
omo | -0.047 |
Token | Even |
Token ID | 3412 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
aback | +0.017 |
fired | +0.014 |
closer | +0.014 |
home | +0.013 |
away | +0.012 |
Neg logit contributions | |
kin | -0.022 |
pron | -0.020 |
uren | -0.017 |
lf | -0.017 |
omo | -0.017 |
Token | though |
Token ID | 996 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
aback | +0.019 |
fired | +0.017 |
closer | +0.017 |
revenge | +0.016 |
away | +0.016 |
Neg logit contributions | |
kin | -0.020 |
pron | -0.019 |
uren | -0.017 |
lf | -0.015 |
omo | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
fired | +0.002 |
revenge | +0.002 |
nearer | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
lf | -0.002 |
Adam | -0.002 |
Token | heavy |
Token ID | 4334 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
aback | +0.014 |
fired | +0.013 |
closer | +0.012 |
away | +0.011 |
revenge | +0.011 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.016 |
uren | -0.015 |
lf | -0.013 |
omo | -0.013 |
Token | bag |
Token ID | 6131 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
aback | +0.041 |
fired | +0.037 |
closer | +0.037 |
beh | +0.035 |
revenge | +0.034 |
Neg logit contributions | |
kin | -0.046 |
pron | -0.042 |
uren | -0.037 |
lf | -0.035 |
omo | -0.034 |
Token | had |
Token ID | 550 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
aback | +0.045 |
closer | +0.040 |
fired | +0.039 |
away | +0.037 |
home | +0.036 |
Neg logit contributions | |
kin | -0.063 |
pron | -0.059 |
uren | -0.057 |
omo | -0.051 |
lf | -0.050 |
Token | been |
Token ID | 587 |
Feature activation | +9.76e-02 |
Pos logit contributions | |
kin | +0.006 |
pron | +0.005 |
uren | +0.005 |
omo | +0.005 |
lf | +0.005 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
fired | -0.003 |
away | -0.003 |
home | -0.003 |
Token | fore |
Token ID | 1674 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
fired | +0.002 |
revenge | +0.001 |
away | +0.001 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.002 |
uren | -0.002 |
lf | -0.002 |
omo | -0.002 |
Token | shadow |
Token ID | 19106 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
aback | +0.147 |
fired | +0.134 |
revenge | +0.129 |
closer | +0.117 |
medical | +0.115 |
Neg logit contributions | |
pron | -0.165 |
kin | -0.162 |
uren | -0.147 |
ast | -0.132 |
lf | -0.132 |
Token | ed |
Token ID | 276 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.007 |
fired | +0.007 |
away | +0.006 |
revenge | +0.006 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.016 |
uren | -0.015 |
omo | -0.014 |
lf | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
aback | +0.035 |
closer | +0.031 |
fired | +0.030 |
revenge | +0.027 |
away | +0.026 |
Neg logit contributions | |
kin | -0.058 |
pron | -0.054 |
uren | -0.051 |
lf | -0.046 |
omo | -0.046 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
kin | +0.046 |
pron | +0.041 |
uren | +0.039 |
omo | +0.036 |
ae | +0.035 |
Neg logit contributions | |
aback | -0.033 |
closer | -0.031 |
away | -0.029 |
home | -0.028 |
fired | -0.028 |
Token | that |
Token ID | 326 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
kin | +0.003 |
pron | +0.003 |
uren | +0.002 |
lf | +0.002 |
omo | +0.002 |
Neg logit contributions | |
aback | -0.003 |
closer | -0.002 |
fired | -0.002 |
away | -0.002 |
revenge | -0.002 |
Token | eyes |
Token ID | 2951 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
aback | +0.015 |
closer | +0.014 |
fired | +0.014 |
home | +0.013 |
away | +0.013 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.016 |
uren | -0.015 |
lf | -0.013 |
omo | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.013 |
fired | +0.012 |
away | +0.012 |
home | +0.011 |
Neg logit contributions | |
kin | -0.021 |
pron | -0.019 |
uren | -0.018 |
omo | -0.017 |
Adam | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
aback | +0.010 |
fired | +0.008 |
closer | +0.008 |
home | +0.008 |
revenge | +0.007 |
Neg logit contributions | |
kin | -0.013 |
pron | -0.012 |
lf | -0.011 |
uren | -0.011 |
omo | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
kin | +0.012 |
pron | +0.011 |
uren | +0.010 |
ae | +0.009 |
omo | +0.009 |
Neg logit contributions | |
aback | -0.008 |
closer | -0.008 |
fired | -0.008 |
away | -0.007 |
home | -0.007 |
Token | been |
Token ID | 587 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
aback | +0.025 |
closer | +0.022 |
away | +0.021 |
fired | +0.021 |
home | +0.021 |
Neg logit contributions | |
kin | -0.039 |
pron | -0.035 |
uren | -0.032 |
lf | -0.030 |
omo | -0.030 |
Token | fore |
Token ID | 1674 |
Feature activation | +7.37e+00 |
Pos logit contributions | |
aback | +0.022 |
fired | +0.019 |
closer | +0.019 |
revenge | +0.018 |
away | +0.018 |
Neg logit contributions | |
kin | -0.022 |
pron | -0.021 |
uren | -0.019 |
lf | -0.017 |
Adam | -0.017 |
Token | shadow |
Token ID | 19106 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
aback | +0.143 |
fired | +0.131 |
revenge | +0.127 |
closer | +0.115 |
medical | +0.115 |
Neg logit contributions | |
pron | -0.169 |
kin | -0.164 |
uren | -0.158 |
lf | -0.141 |
Adam | -0.137 |
Token | ed |
Token ID | 276 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
aback | +0.011 |
closer | +0.009 |
fired | +0.009 |
away | +0.008 |
revenge | +0.008 |
Neg logit contributions | |
kin | -0.027 |
pron | -0.026 |
uren | -0.024 |
omo | -0.022 |
lf | -0.022 |
Token | about |
Token ID | 546 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
aback | +0.035 |
closer | +0.030 |
fired | +0.030 |
away | +0.028 |
revenge | +0.027 |
Neg logit contributions | |
kin | -0.056 |
pron | -0.053 |
uren | -0.049 |
omo | -0.045 |
lf | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
kin | +0.016 |
pron | +0.015 |
uren | +0.014 |
omo | +0.013 |
Adam | +0.012 |
Neg logit contributions | |
aback | -0.010 |
closer | -0.009 |
fired | -0.009 |
home | -0.008 |
revenge | -0.008 |
Token | power |
Token ID | 1176 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
kin | +0.002 |
pron | +0.002 |
uren | +0.002 |
omo | +0.001 |
lf | +0.001 |
Neg logit contributions | |
aback | -0.002 |
closer | -0.001 |
home | -0.001 |
revenge | -0.001 |
away | -0.001 |
Token | know |
Token ID | 760 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
aback | +0.006 |
closer | +0.005 |
fired | +0.005 |
away | +0.005 |
home | +0.005 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.007 |
uren | -0.006 |
lf | -0.006 |
sheets | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
fired | +0.002 |
home | +0.002 |
away | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
omo | -0.003 |
scalp | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
kin | +0.077 |
pron | +0.067 |
omo | +0.063 |
uren | +0.062 |
lf | +0.058 |
Neg logit contributions | |
aback | -0.050 |
closer | -0.049 |
home | -0.043 |
back | -0.042 |
away | -0.042 |
Token | mum |
Token ID | 25682 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
kin | +0.010 |
pron | +0.009 |
uren | +0.009 |
lf | +0.008 |
Adam | +0.008 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.011 |
home | -0.010 |
fired | -0.010 |
revenge | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
aback | +0.050 |
closer | +0.046 |
fired | +0.043 |
away | +0.043 |
home | +0.042 |
Neg logit contributions | |
kin | -0.065 |
pron | -0.059 |
uren | -0.055 |
omo | -0.050 |
Adam | -0.049 |
Token | fore |
Token ID | 1674 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
kin | +0.025 |
pron | +0.023 |
uren | +0.023 |
omo | +0.021 |
abs | +0.020 |
Neg logit contributions | |
aback | -0.017 |
closer | -0.016 |
home | -0.015 |
away | -0.015 |
back | -0.015 |
Token | shadow |
Token ID | 19106 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
aback | +0.144 |
fired | +0.134 |
revenge | +0.128 |
medical | +0.111 |
closer | +0.111 |
Neg logit contributions | |
pron | -0.172 |
kin | -0.161 |
uren | -0.152 |
lf | -0.138 |
ae | -0.133 |
Token | ing |
Token ID | 278 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
aback | +0.003 |
closer | +0.003 |
fired | +0.002 |
away | +0.002 |
revenge | +0.002 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.007 |
uren | -0.006 |
omo | -0.006 |
lf | -0.006 |
Token | ... |
Token ID | 986 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
kin | +0.013 |
pron | +0.012 |
uren | +0.011 |
omo | +0.010 |
lf | +0.010 |
Neg logit contributions | |
aback | -0.009 |
closer | -0.008 |
fired | -0.008 |
away | -0.007 |
revenge | -0.007 |
Token | the |
Token ID | 1169 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
kin | +0.020 |
pron | +0.018 |
uren | +0.017 |
omo | +0.015 |
lf | +0.015 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.016 |
away | -0.015 |
revenge | -0.015 |
Token | next |
Token ID | 1306 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.005 |
uren | +0.005 |
Adam | +0.004 |
Avery | +0.004 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
home | -0.004 |
away | -0.004 |
fired | -0.004 |
Token | That |
Token ID | 1320 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
aback | +0.010 |
closer | +0.009 |
fired | +0.009 |
away | +0.009 |
revenge | +0.009 |
Neg logit contributions | |
kin | -0.011 |
pron | -0.010 |
uren | -0.009 |
omo | -0.008 |
lf | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
aback | +0.040 |
fired | +0.036 |
closer | +0.036 |
revenge | +0.033 |
away | +0.033 |
Neg logit contributions | |
kin | -0.045 |
pron | -0.041 |
uren | -0.039 |
lf | -0.035 |
omo | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
kin | +0.053 |
pron | +0.048 |
uren | +0.045 |
lf | +0.041 |
omo | +0.040 |
Neg logit contributions | |
aback | -0.047 |
fired | -0.043 |
closer | -0.041 |
home | -0.038 |
revenge | -0.038 |
Token | setup |
Token ID | 9058 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
kin | +0.034 |
pron | +0.031 |
uren | +0.029 |
omo | +0.026 |
lf | +0.026 |
Neg logit contributions | |
aback | -0.025 |
fired | -0.022 |
closer | -0.021 |
away | -0.020 |
revenge | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
kin | +0.037 |
pron | +0.035 |
uren | +0.034 |
omo | +0.031 |
majesty | +0.030 |
Neg logit contributions | |
aback | -0.026 |
closer | -0.024 |
away | -0.023 |
fired | -0.023 |
home | -0.022 |
Token | fore |
Token ID | 1674 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
aback | +0.030 |
closer | +0.028 |
fired | +0.027 |
away | +0.026 |
revenge | +0.025 |
Neg logit contributions | |
kin | -0.032 |
pron | -0.029 |
uren | -0.027 |
omo | -0.024 |
lf | -0.024 |
Token | shadow |
Token ID | 19106 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
aback | +0.140 |
fired | +0.132 |
revenge | +0.127 |
home | +0.118 |
closer | +0.118 |
Neg logit contributions | |
pron | -0.133 |
uren | -0.129 |
kin | -0.122 |
abs | -0.113 |
lf | -0.109 |
Token | ed |
Token ID | 276 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.004 |
fired | +0.004 |
revenge | +0.004 |
away | +0.004 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.013 |
omo | -0.012 |
Adam | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
aback | +0.032 |
closer | +0.028 |
fired | +0.028 |
revenge | +0.025 |
home | +0.024 |
Neg logit contributions | |
kin | -0.054 |
pron | -0.050 |
uren | -0.047 |
lf | -0.043 |
omo | -0.043 |
Token | bad |
Token ID | 2089 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
aback | +0.020 |
fired | +0.017 |
closer | +0.016 |
away | +0.015 |
beh | +0.015 |
Neg logit contributions | |
kin | -0.024 |
pron | -0.022 |
uren | -0.021 |
omo | -0.019 |
lf | -0.019 |
Token | ending |
Token ID | 7464 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
aback | +0.088 |
fired | +0.079 |
closer | +0.079 |
away | +0.074 |
unst | +0.072 |
Neg logit contributions | |
kin | -0.064 |
pron | -0.055 |
uren | -0.051 |
lf | -0.044 |
omo | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
aback | +0.016 |
fired | +0.014 |
home | +0.013 |
closer | +0.013 |
away | +0.012 |
Neg logit contributions | |
kin | -0.022 |
pron | -0.021 |
lf | -0.019 |
uren | -0.017 |
bee | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
aback | +0.003 |
closer | +0.003 |
fired | +0.003 |
home | +0.003 |
away | +0.002 |
Neg logit contributions | |
kin | -0.004 |
pron | -0.003 |
uren | -0.003 |
lf | -0.003 |
moons | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
aback | +0.016 |
closer | +0.016 |
fired | +0.014 |
away | +0.014 |
home | +0.014 |
Neg logit contributions | |
kin | -0.019 |
pron | -0.017 |
uren | -0.016 |
moons | -0.016 |
majesty | -0.015 |
Token | wave |
Token ID | 6769 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
kin | +0.009 |
pron | +0.008 |
uren | +0.008 |
omo | +0.007 |
scalp | +0.007 |
Neg logit contributions | |
closer | -0.008 |
aback | -0.007 |
home | -0.007 |
away | -0.007 |
back | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
aback | +0.018 |
closer | +0.018 |
away | +0.017 |
fired | +0.016 |
revenge | +0.015 |
Neg logit contributions | |
kin | -0.025 |
pron | -0.024 |
uren | -0.022 |
Adam | -0.020 |
omo | -0.020 |
Token | fore |
Token ID | 1674 |
Feature activation | +6.84e+00 |
Pos logit contributions | |
aback | +0.027 |
closer | +0.024 |
fired | +0.024 |
away | +0.022 |
revenge | +0.022 |
Neg logit contributions | |
kin | -0.039 |
pron | -0.036 |
uren | -0.034 |
omo | -0.031 |
lf | -0.031 |
Token | shadow |
Token ID | 19106 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
aback | +0.145 |
fired | +0.137 |
revenge | +0.135 |
medical | +0.119 |
home | +0.118 |
Neg logit contributions | |
pron | -0.133 |
uren | -0.126 |
kin | -0.122 |
ast | -0.111 |
abs | -0.110 |
Token | ed |
Token ID | 276 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
aback | +0.006 |
closer | +0.005 |
fired | +0.005 |
revenge | +0.004 |
away | +0.004 |
Neg logit contributions | |
kin | -0.019 |
pron | -0.018 |
uren | -0.017 |
omo | -0.016 |
lf | -0.015 |
Token | L |
Token ID | 406 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
aback | +0.036 |
closer | +0.031 |
fired | +0.031 |
revenge | +0.028 |
nearer | +0.027 |
Neg logit contributions | |
kin | -0.057 |
pron | -0.053 |
uren | -0.051 |
lf | -0.045 |
omo | -0.045 |
Token | ola |
Token ID | 5708 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
pron | +0.048 |
kin | +0.045 |
uren | +0.043 |
lf | +0.041 |
unison | +0.041 |
Neg logit contributions | |
aback | -0.069 |
closer | -0.065 |
fired | -0.064 |
home | -0.060 |
away | -0.060 |
Token | 's |
Token ID | 338 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
aback | +0.033 |
closer | +0.029 |
fired | +0.029 |
away | +0.027 |
home | +0.026 |
Neg logit contributions | |
kin | -0.049 |
pron | -0.046 |
uren | -0.043 |
omo | -0.039 |
lf | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
fired | +0.002 |
home | +0.002 |
away | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.002 |
uren | -0.002 |
lf | -0.002 |
omo | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
aback | +0.017 |
closer | +0.015 |
fired | +0.015 |
away | +0.014 |
home | +0.014 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.017 |
uren | -0.016 |
lf | -0.014 |
moons | -0.014 |
Token | bad |
Token ID | 2089 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
kin | +0.011 |
pron | +0.010 |
uren | +0.010 |
omo | +0.009 |
Adam | +0.009 |
Neg logit contributions | |
aback | -0.009 |
closer | -0.008 |
fired | -0.008 |
home | -0.008 |
revenge | -0.008 |
Token | ending |
Token ID | 7464 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
aback | +0.036 |
closer | +0.034 |
home | +0.033 |
fired | +0.032 |
revenge | +0.032 |
Neg logit contributions | |
kin | -0.033 |
pron | -0.031 |
uren | -0.029 |
Adam | -0.025 |
omo | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
aback | +0.020 |
closer | +0.018 |
fired | +0.018 |
away | +0.017 |
home | +0.016 |
Neg logit contributions | |
kin | -0.031 |
pron | -0.031 |
uren | -0.028 |
omo | -0.026 |
Adam | -0.026 |
Token | fore |
Token ID | 1674 |
Feature activation | +6.73e+00 |
Pos logit contributions | |
aback | +0.004 |
closer | +0.003 |
fired | +0.003 |
away | +0.003 |
revenge | +0.003 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.004 |
uren | -0.004 |
omo | -0.004 |
lf | -0.004 |
Token | shadow |
Token ID | 19106 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
aback | +0.130 |
fired | +0.116 |
revenge | +0.111 |
closer | +0.103 |
home | +0.100 |
Neg logit contributions | |
pron | -0.157 |
kin | -0.156 |
uren | -0.145 |
lf | -0.130 |
ae | -0.127 |
Token | ed |
Token ID | 276 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
aback | +0.006 |
closer | +0.005 |
fired | +0.005 |
away | +0.005 |
revenge | +0.004 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.017 |
uren | -0.016 |
lf | -0.015 |
omo | -0.015 |
Token | by |
Token ID | 416 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
aback | +0.035 |
closer | +0.030 |
fired | +0.030 |
away | +0.027 |
revenge | +0.027 |
Neg logit contributions | |
kin | -0.059 |
pron | -0.055 |
uren | -0.052 |
omo | -0.047 |
lf | -0.047 |
Token | Maggie |
Token ID | 33014 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
kin | +0.018 |
pron | +0.018 |
uren | +0.016 |
omo | +0.015 |
lf | +0.015 |
Neg logit contributions | |
aback | -0.013 |
closer | -0.012 |
fired | -0.011 |
home | -0.011 |
away | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
aback | +0.029 |
closer | +0.026 |
fired | +0.025 |
away | +0.024 |
home | +0.023 |
Neg logit contributions | |
kin | -0.040 |
pron | -0.038 |
uren | -0.035 |
omo | -0.032 |
lf | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
aback | +0.056 |
closer | +0.053 |
fired | +0.048 |
home | +0.048 |
away | +0.047 |
Neg logit contributions | |
kin | -0.073 |
pron | -0.067 |
uren | -0.062 |
omo | -0.056 |
scalp | -0.055 |
Token | but |
Token ID | 475 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
kin | +0.040 |
pron | +0.035 |
uren | +0.032 |
moons | +0.031 |
bridge | +0.030 |
Neg logit contributions | |
aback | -0.035 |
closer | -0.034 |
home | -0.031 |
away | -0.030 |
fired | -0.030 |
Token | when |
Token ID | 618 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
aback | +0.006 |
closer | +0.006 |
fired | +0.006 |
away | +0.006 |
home | +0.006 |
Neg logit contributions | |
kin | -0.008 |
pron | -0.008 |
uren | -0.007 |
omo | -0.007 |
Adam | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
aback | +0.018 |
closer | +0.017 |
fired | +0.016 |
away | +0.015 |
home | +0.015 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.017 |
uren | -0.015 |
omo | -0.014 |
lf | -0.013 |
Token | turned |
Token ID | 2900 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
aback | +0.003 |
fired | +0.003 |
closer | +0.003 |
revenge | +0.003 |
home | +0.003 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
lf | -0.003 |
omo | -0.002 |
Token | back |
Token ID | 736 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
aback | +0.048 |
fired | +0.046 |
beh | +0.044 |
revenge | +0.040 |
medical | +0.038 |
Neg logit contributions | |
kin | -0.074 |
pron | -0.071 |
uren | -0.066 |
lf | -0.058 |
Avery | -0.058 |
Token | around |
Token ID | 1088 |
Feature activation | +5.85e-01 |
Pos logit contributions | |
aback | +0.143 |
beh | +0.135 |
bitten | +0.125 |
medical | +0.124 |
revenge | +0.122 |
Neg logit contributions | |
kin | -0.120 |
pron | -0.103 |
uren | -0.101 |
Ben | -0.099 |
ia | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
aback | +0.011 |
closer | +0.010 |
fired | +0.010 |
away | +0.009 |
home | +0.009 |
Neg logit contributions | |
kin | -0.015 |
pron | -0.014 |
uren | -0.013 |
omo | -0.012 |
lf | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.012 |
fired | +0.012 |
away | +0.011 |
home | +0.011 |
Neg logit contributions | |
kin | -0.015 |
pron | -0.014 |
uren | -0.013 |
omo | -0.012 |
lf | -0.012 |
Token | noticed |
Token ID | 6810 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
aback | +0.010 |
closer | +0.009 |
fired | +0.009 |
away | +0.008 |
home | +0.008 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.012 |
omo | -0.011 |
lf | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
kin | +0.009 |
pron | +0.008 |
uren | +0.008 |
omo | +0.007 |
lf | +0.007 |
Neg logit contributions | |
aback | -0.006 |
closer | -0.005 |
fired | -0.005 |
away | -0.005 |
revenge | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
aback | +0.009 |
closer | +0.008 |
fired | +0.007 |
home | +0.007 |
away | +0.007 |
Neg logit contributions | |
kin | -0.015 |
pron | -0.014 |
lf | -0.012 |
uren | -0.012 |
bee | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.007 |
fired | +0.007 |
home | +0.006 |
away | +0.006 |
Neg logit contributions | |
kin | -0.009 |
pron | -0.008 |
uren | -0.007 |
lf | -0.007 |
omo | -0.007 |
Token | L |
Token ID | 43 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
aback | +0.022 |
closer | +0.021 |
fired | +0.019 |
away | +0.019 |
home | +0.018 |
Neg logit contributions | |
kin | -0.022 |
pron | -0.020 |
uren | -0.019 |
moons | -0.017 |
scalp | -0.017 |
Token | ily |
Token ID | 813 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
pron | +0.049 |
kin | +0.048 |
uren | +0.044 |
omo | +0.040 |
moons | +0.039 |
Neg logit contributions | |
aback | -0.059 |
closer | -0.051 |
fired | -0.051 |
away | -0.049 |
home | -0.048 |
Token | had |
Token ID | 550 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
away | +0.002 |
fired | +0.002 |
home | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.002 |
bridge | -0.002 |
inner | -0.002 |
Token | fore |
Token ID | 1674 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
aback | +0.029 |
closer | +0.024 |
fired | +0.024 |
home | +0.023 |
away | +0.023 |
Neg logit contributions | |
kin | -0.053 |
pron | -0.050 |
uren | -0.046 |
lf | -0.044 |
omo | -0.042 |
Token | shadow |
Token ID | 19106 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
aback | +0.124 |
fired | +0.114 |
revenge | +0.111 |
closer | +0.101 |
medical | +0.098 |
Neg logit contributions | |
pron | -0.144 |
kin | -0.137 |
uren | -0.133 |
lf | -0.117 |
Adam | -0.116 |
Token | ed |
Token ID | 276 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
aback | +0.009 |
closer | +0.007 |
fired | +0.007 |
away | +0.006 |
revenge | +0.006 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
uren | -0.020 |
omo | -0.019 |
lf | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
aback | +0.036 |
closer | +0.032 |
fired | +0.031 |
revenge | +0.029 |
away | +0.028 |
Neg logit contributions | |
kin | -0.057 |
pron | -0.053 |
uren | -0.050 |
omo | -0.045 |
lf | -0.044 |
Token | danger |
Token ID | 3514 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
aback | +0.022 |
fired | +0.020 |
closer | +0.019 |
away | +0.018 |
revenge | +0.017 |
Neg logit contributions | |
kin | -0.024 |
pron | -0.021 |
uren | -0.020 |
omo | -0.019 |
lf | -0.018 |
Token | with |
Token ID | 351 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
aback | +0.029 |
closer | +0.026 |
fired | +0.025 |
away | +0.025 |
home | +0.024 |
Neg logit contributions | |
kin | -0.040 |
pron | -0.039 |
uren | -0.036 |
omo | -0.034 |
Adam | -0.032 |
Token | little |
Token ID | 1310 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
kin | +0.011 |
pron | +0.010 |
uren | +0.009 |
Adam | +0.008 |
omo | +0.008 |
Neg logit contributions | |
aback | -0.010 |
closer | -0.010 |
fired | -0.009 |
home | -0.009 |
away | -0.009 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
aback | +0.007 |
closer | +0.006 |
fired | +0.006 |
away | +0.006 |
home | +0.006 |
Neg logit contributions | |
kin | -0.009 |
pron | -0.008 |
uren | -0.008 |
lf | -0.007 |
omo | -0.007 |
Token | remembered |
Token ID | 12086 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
aback | +0.035 |
closer | +0.032 |
fired | +0.031 |
away | +0.029 |
home | +0.029 |
Neg logit contributions | |
kin | -0.044 |
pron | -0.040 |
uren | -0.037 |
omo | -0.034 |
lf | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.012 |
fired | +0.012 |
home | +0.011 |
away | +0.011 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
uren | -0.020 |
omo | -0.018 |
bridge | -0.018 |
Token | earlier |
Token ID | 2961 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
kin | +0.004 |
pron | +0.003 |
uren | +0.003 |
omo | +0.003 |
lf | +0.003 |
Neg logit contributions | |
aback | -0.003 |
closer | -0.003 |
fired | -0.003 |
away | -0.003 |
revenge | -0.003 |
Token | fore |
Token ID | 1674 |
Feature activation | +6.32e+00 |
Pos logit contributions | |
aback | +0.012 |
closer | +0.010 |
fired | +0.010 |
away | +0.010 |
home | +0.010 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.012 |
omo | -0.011 |
lf | -0.011 |
Token | shadow |
Token ID | 19106 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
aback | +0.130 |
fired | +0.117 |
revenge | +0.114 |
medical | +0.104 |
closer | +0.103 |
Neg logit contributions | |
pron | -0.138 |
kin | -0.127 |
uren | -0.124 |
ast | -0.112 |
ae | -0.112 |
Token | ing |
Token ID | 278 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
fired | +0.001 |
revenge | +0.001 |
away | +0.001 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
Adam | -0.003 |
omo | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
kin | +0.017 |
pron | +0.016 |
uren | +0.015 |
omo | +0.014 |
lf | +0.014 |
Neg logit contributions | |
aback | -0.013 |
closer | -0.012 |
fired | -0.011 |
away | -0.011 |
home | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
kin | +0.025 |
pron | +0.022 |
uren | +0.021 |
omo | +0.020 |
lf | +0.019 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.017 |
home | -0.016 |
fired | -0.015 |
away | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.013 |
fired | +0.013 |
away | +0.012 |
revenge | +0.012 |
Neg logit contributions | |
kin | -0.015 |
pron | -0.014 |
uren | -0.013 |
lf | -0.012 |
omo | -0.012 |
Token | again |
Token ID | 757 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
kin | +0.033 |
pron | +0.031 |
uren | +0.028 |
lf | +0.026 |
omo | +0.026 |
Neg logit contributions | |
aback | -0.025 |
closer | -0.022 |
fired | -0.022 |
revenge | -0.020 |
away | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
aback | +0.051 |
closer | +0.045 |
fired | +0.045 |
revenge | +0.042 |
away | +0.041 |
Neg logit contributions | |
kin | -0.051 |
pron | -0.046 |
uren | -0.043 |
lf | -0.039 |
omo | -0.038 |
Token | But |
Token ID | 887 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
aback | +0.012 |
fired | +0.010 |
closer | +0.010 |
home | +0.010 |
revenge | +0.010 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.011 |
lf | -0.011 |
omo | -0.010 |
Token | unb |
Token ID | 22619 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
kin | +0.023 |
pron | +0.020 |
uren | +0.019 |
lf | +0.017 |
ae | +0.016 |
Neg logit contributions | |
aback | -0.026 |
fired | -0.023 |
closer | -0.023 |
revenge | -0.021 |
beh | -0.021 |
Token | ek |
Token ID | 988 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
aback | +0.031 |
closer | +0.027 |
fired | +0.027 |
revenge | +0.025 |
away | +0.025 |
Neg logit contributions | |
kin | -0.043 |
pron | -0.040 |
uren | -0.038 |
omo | -0.034 |
lf | -0.034 |
Token | nown |
Token ID | 3408 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
aback | +0.024 |
fired | +0.020 |
closer | +0.020 |
away | +0.020 |
home | +0.018 |
Neg logit contributions | |
kin | -0.037 |
pron | -0.035 |
uren | -0.032 |
omo | -0.030 |
Adam | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
aback | +0.088 |
closer | +0.072 |
fired | +0.071 |
revenge | +0.070 |
medical | +0.066 |
Neg logit contributions | |
kin | -0.170 |
pron | -0.168 |
uren | -0.157 |
Adam | -0.146 |
addy | -0.142 |
Token | him |
Token ID | 683 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
aback | +0.021 |
closer | +0.018 |
fired | +0.017 |
away | +0.017 |
home | +0.017 |
Neg logit contributions | |
kin | -0.036 |
pron | -0.034 |
uren | -0.032 |
omo | -0.029 |
lf | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
aback | +0.048 |
closer | +0.043 |
fired | +0.041 |
away | +0.039 |
home | +0.039 |
Neg logit contributions | |
kin | -0.072 |
pron | -0.067 |
uren | -0.063 |
omo | -0.058 |
lf | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.012 |
fired | +0.011 |
away | +0.011 |
home | +0.011 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.017 |
uren | -0.015 |
omo | -0.014 |
lf | -0.014 |
Token | king |
Token ID | 5822 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
kin | +0.014 |
pron | +0.012 |
uren | +0.012 |
omo | +0.011 |
addy | +0.010 |
Neg logit contributions | |
closer | -0.012 |
aback | -0.011 |
home | -0.011 |
back | -0.011 |
away | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
aback | +0.007 |
fired | +0.006 |
closer | +0.006 |
beh | +0.005 |
revenge | +0.005 |
Neg logit contributions | |
kin | -0.006 |
pron | -0.005 |
uren | -0.005 |
lf | -0.004 |
Ben | -0.004 |
Token | When |
Token ID | 1649 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
aback | +0.016 |
fired | +0.014 |
home | +0.013 |
closer | +0.013 |
back | +0.012 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
lf | -0.018 |
uren | -0.017 |
omo | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
aback | +0.026 |
closer | +0.026 |
fired | +0.025 |
home | +0.024 |
away | +0.024 |
Neg logit contributions | |
kin | -0.026 |
pron | -0.025 |
uren | -0.022 |
omo | -0.020 |
Adam | -0.019 |
Token | reached |
Token ID | 4251 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
kin | +0.036 |
pron | +0.032 |
uren | +0.030 |
lf | +0.027 |
Adam | +0.026 |
Neg logit contributions | |
aback | -0.032 |
fired | -0.029 |
closer | -0.028 |
revenge | -0.026 |
beh | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
aback | +0.052 |
closer | +0.045 |
fired | +0.045 |
beh | +0.043 |
revenge | +0.042 |
Neg logit contributions | |
kin | -0.051 |
pron | -0.045 |
uren | -0.042 |
ae | -0.037 |
moons | -0.037 |
Token | end |
Token ID | 886 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
aback | +0.016 |
fired | +0.014 |
beh | +0.013 |
closer | +0.013 |
revenge | +0.013 |
Neg logit contributions | |
kin | -0.011 |
pron | -0.010 |
uren | -0.009 |
ceiling | -0.008 |
ma | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
aback | +0.139 |
fired | +0.119 |
revenge | +0.117 |
closer | +0.115 |
beh | +0.112 |
Neg logit contributions | |
kin | -0.136 |
pron | -0.118 |
uren | -0.111 |
lf | -0.101 |
omo | -0.101 |
Token | their |
Token ID | 511 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
aback | +0.002 |
fired | +0.002 |
closer | +0.002 |
beh | +0.002 |
revenge | +0.002 |
Neg logit contributions | |
kin | -0.002 |
pron | -0.002 |
uren | -0.001 |
lf | -0.001 |
omo | -0.001 |
Token | adventure |
Token ID | 8855 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
aback | +0.009 |
fired | +0.007 |
closer | +0.007 |
beh | +0.007 |
arling | +0.007 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.004 |
uren | -0.004 |
moons | -0.004 |
lf | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
aback | +0.021 |
closer | +0.018 |
fired | +0.018 |
away | +0.017 |
revenge | +0.017 |
Neg logit contributions | |
kin | -0.029 |
pron | -0.027 |
uren | -0.025 |
omo | -0.023 |
lf | -0.023 |
Token | they |
Token ID | 484 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
kin | +0.003 |
pron | +0.003 |
uren | +0.002 |
omo | +0.002 |
Adam | +0.002 |
Neg logit contributions | |
aback | -0.003 |
closer | -0.003 |
fired | -0.003 |
away | -0.003 |
home | -0.002 |
Token | |
Token ID | 220 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
aback | +0.012 |
closer | +0.011 |
fired | +0.010 |
home | +0.010 |
away | +0.010 |
Neg logit contributions | |
kin | -0.013 |
pron | -0.012 |
uren | -0.011 |
lf | -0.010 |
omo | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -5.00e-02 |
Pos logit contributions | |
kin | +0.030 |
pron | +0.029 |
uren | +0.026 |
lf | +0.024 |
moons | +0.024 |
Neg logit contributions | |
aback | -0.023 |
fired | -0.020 |
closer | -0.019 |
home | -0.018 |
revenge | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
kin | +0.001 |
pron | +0.001 |
uren | +0.001 |
moons | +0.001 |
omo | +0.001 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
fired | -0.001 |
home | -0.001 |
away | -0.001 |
Token | With |
Token ID | 3152 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.012 |
fired | +0.011 |
away | +0.011 |
unst | +0.011 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.012 |
moons | -0.012 |
scalp | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
aback | +0.007 |
fired | +0.007 |
closer | +0.006 |
beh | +0.006 |
away | +0.006 |
Neg logit contributions | |
kin | -0.008 |
pron | -0.007 |
uren | -0.007 |
lf | -0.006 |
Adam | -0.006 |
Token | key |
Token ID | 1994 |
Feature activation | +6.06e+00 |
Pos logit contributions | |
aback | +0.004 |
fired | +0.004 |
beh | +0.003 |
closer | +0.003 |
revenge | +0.003 |
Neg logit contributions | |
kin | -0.004 |
pron | -0.004 |
uren | -0.003 |
lf | -0.003 |
ma | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
aback | +0.115 |
fired | +0.102 |
revenge | +0.100 |
beh | +0.100 |
closer | +0.093 |
Neg logit contributions | |
kin | -0.145 |
pron | -0.128 |
uren | -0.119 |
lf | -0.114 |
sheets | -0.108 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
kin | +0.015 |
pron | +0.014 |
uren | +0.013 |
omo | +0.012 |
Adam | +0.011 |
Neg logit contributions | |
aback | -0.012 |
closer | -0.011 |
fired | -0.010 |
away | -0.010 |
home | -0.010 |
Token | young |
Token ID | 1862 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.022 |
lf | +0.020 |
omo | +0.020 |
Neg logit contributions | |
aback | -0.023 |
fired | -0.021 |
closer | -0.021 |
away | -0.019 |
revenge | -0.019 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
kin | +0.024 |
pron | +0.022 |
uren | +0.021 |
ae | +0.019 |
omo | +0.018 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.015 |
home | -0.015 |
away | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
aback | +0.056 |
closer | +0.050 |
fired | +0.049 |
revenge | +0.047 |
away | +0.045 |
Neg logit contributions | |
kin | -0.058 |
pron | -0.053 |
uren | -0.049 |
lf | -0.044 |
omo | -0.043 |
Token | |
Token ID | 220 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
aback | +0.012 |
closer | +0.010 |
fired | +0.010 |
home | +0.010 |
revenge | +0.009 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.012 |
lf | -0.011 |
omo | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
kin | +0.027 |
pron | +0.026 |
uren | +0.024 |
lf | +0.022 |
moons | +0.021 |
Neg logit contributions | |
aback | -0.020 |
fired | -0.017 |
closer | -0.017 |
home | -0.016 |
unst | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
aback | +0.000 |
closer | +0.000 |
fired | +0.000 |
home | +0.000 |
away | +0.000 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.000 |
uren | -0.000 |
moons | -0.000 |
scalp | -0.000 |
Token | With |
Token ID | 3152 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
aback | +0.015 |
closer | +0.014 |
fired | +0.013 |
away | +0.012 |
nearer | +0.012 |
Neg logit contributions | |
kin | -0.016 |
pron | -0.014 |
uren | -0.013 |
moons | -0.013 |
scalp | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
aback | +0.009 |
fired | +0.008 |
closer | +0.008 |
beh | +0.007 |
away | +0.007 |
Neg logit contributions | |
kin | -0.010 |
pron | -0.009 |
uren | -0.009 |
lf | -0.008 |
Adam | -0.008 |
Token | key |
Token ID | 1994 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
aback | +0.002 |
fired | +0.002 |
beh | +0.002 |
closer | +0.002 |
revenge | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.002 |
uren | -0.002 |
lf | -0.002 |
ma | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
aback | +0.113 |
fired | +0.099 |
revenge | +0.097 |
beh | +0.096 |
closer | +0.090 |
Neg logit contributions | |
kin | -0.148 |
pron | -0.131 |
uren | -0.121 |
lf | -0.116 |
sheets | -0.110 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
kin | +0.012 |
pron | +0.011 |
uren | +0.011 |
omo | +0.010 |
Adam | +0.009 |
Neg logit contributions | |
aback | -0.009 |
closer | -0.008 |
fired | -0.008 |
home | -0.008 |
away | -0.007 |
Token | young |
Token ID | 1862 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
kin | +0.027 |
pron | +0.025 |
uren | +0.023 |
lf | +0.021 |
omo | +0.021 |
Neg logit contributions | |
aback | -0.023 |
fired | -0.020 |
closer | -0.020 |
away | -0.018 |
revenge | -0.018 |
Token | boy |
Token ID | 2933 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
kin | +0.023 |
pron | +0.021 |
uren | +0.020 |
omo | +0.018 |
ae | +0.018 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.015 |
home | -0.015 |
away | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
aback | +0.055 |
closer | +0.049 |
fired | +0.049 |
revenge | +0.046 |
away | +0.045 |
Neg logit contributions | |
kin | -0.059 |
pron | -0.054 |
uren | -0.050 |
lf | -0.045 |
omo | -0.045 |
Token | earlier |
Token ID | 2961 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
aback | +0.054 |
closer | +0.048 |
fired | +0.048 |
away | +0.045 |
revenge | +0.045 |
Neg logit contributions | |
kin | -0.061 |
pron | -0.057 |
uren | -0.053 |
omo | -0.047 |
lf | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.005 |
uren | +0.004 |
omo | +0.004 |
majesty | +0.004 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.003 |
away | -0.003 |
fired | -0.003 |
home | -0.003 |
Token | promised |
Token ID | 8072 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.004 |
uren | +0.004 |
omo | +0.004 |
lf | +0.003 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
fired | -0.004 |
away | -0.004 |
home | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
fired | +0.005 |
away | +0.004 |
revenge | +0.004 |
Neg logit contributions | |
kin | -0.008 |
pron | -0.008 |
uren | -0.008 |
lf | -0.007 |
Adam | -0.007 |
Token | call |
Token ID | 869 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
kin | +0.009 |
pron | +0.008 |
uren | +0.008 |
omo | +0.007 |
moons | +0.007 |
Neg logit contributions | |
aback | -0.006 |
closer | -0.006 |
away | -0.006 |
home | -0.006 |
fired | -0.006 |
Token | back |
Token ID | 736 |
Feature activation | +6.03e+00 |
Pos logit contributions | |
aback | +0.011 |
fired | +0.010 |
closer | +0.009 |
revenge | +0.009 |
beh | +0.009 |
Neg logit contributions | |
kin | -0.016 |
pron | -0.015 |
uren | -0.014 |
lf | -0.012 |
Adam | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
aback | +0.121 |
fired | +0.102 |
beh | +0.102 |
bitten | +0.099 |
unst | +0.099 |
Neg logit contributions | |
kin | -0.133 |
uren | -0.122 |
pron | -0.121 |
ae | -0.115 |
Avery | -0.112 |
Token | She |
Token ID | 1375 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
aback | +0.021 |
closer | +0.019 |
fired | +0.018 |
away | +0.017 |
revenge | +0.017 |
Neg logit contributions | |
kin | -0.019 |
pron | -0.018 |
uren | -0.016 |
omo | -0.014 |
lf | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
aback | +0.004 |
fired | +0.004 |
closer | +0.004 |
revenge | +0.003 |
home | +0.003 |
Neg logit contributions | |
kin | -0.004 |
pron | -0.004 |
uren | -0.003 |
omo | -0.003 |
lf | -0.003 |
Token | afraid |
Token ID | 7787 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
kin | +0.032 |
pron | +0.030 |
uren | +0.028 |
omo | +0.025 |
lf | +0.025 |
Neg logit contributions | |
aback | -0.024 |
closer | -0.021 |
fired | -0.021 |
away | -0.019 |
revenge | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
kin | +0.025 |
pron | +0.024 |
uren | +0.022 |
omo | +0.020 |
lf | +0.020 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.016 |
away | -0.015 |
home | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
kin | +0.010 |
pron | +0.009 |
uren | +0.008 |
omo | +0.007 |
scalp | +0.007 |
Neg logit contributions | |
aback | -0.009 |
closer | -0.008 |
fired | -0.008 |
home | -0.007 |
revenge | -0.007 |
Token | Grand |
Token ID | 23581 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.007 |
fired | +0.007 |
away | +0.007 |
home | +0.006 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.006 |
uren | -0.005 |
scalp | -0.005 |
omo | -0.005 |
Token | ma |
Token ID | 2611 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
kin | +0.017 |
pron | +0.016 |
uren | +0.015 |
omo | +0.014 |
lf | +0.013 |
Neg logit contributions | |
aback | -0.015 |
closer | -0.014 |
fired | -0.013 |
away | -0.013 |
revenge | -0.013 |
Token | 's |
Token ID | 338 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
aback | +0.049 |
closer | +0.045 |
fired | +0.043 |
away | +0.041 |
home | +0.041 |
Neg logit contributions | |
kin | -0.055 |
pron | -0.051 |
uren | -0.046 |
omo | -0.041 |
lf | -0.041 |
Token | words |
Token ID | 2456 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
kin | +0.018 |
pron | +0.016 |
uren | +0.015 |
lf | +0.014 |
omo | +0.014 |
Neg logit contributions | |
aback | -0.016 |
closer | -0.015 |
home | -0.014 |
revenge | -0.014 |
away | -0.014 |
Token | fore |
Token ID | 1674 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
kin | +0.035 |
pron | +0.033 |
uren | +0.031 |
omo | +0.028 |
ae | +0.028 |
Neg logit contributions | |
aback | -0.030 |
closer | -0.028 |
away | -0.026 |
fired | -0.026 |
home | -0.025 |
Token | shadow |
Token ID | 19106 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
aback | +0.121 |
fired | +0.116 |
revenge | +0.110 |
home | +0.100 |
medical | +0.097 |
Neg logit contributions | |
pron | -0.131 |
kin | -0.122 |
uren | -0.120 |
ast | -0.106 |
lf | -0.104 |
Token | ed |
Token ID | 276 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
fired | +0.004 |
revenge | +0.004 |
away | +0.004 |
Neg logit contributions | |
kin | -0.012 |
pron | -0.011 |
uren | -0.011 |
omo | -0.010 |
lf | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
aback | +0.029 |
fired | +0.025 |
closer | +0.025 |
revenge | +0.022 |
home | +0.021 |
Neg logit contributions | |
kin | -0.052 |
pron | -0.048 |
uren | -0.046 |
Adam | -0.042 |
lf | -0.041 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
aback | +0.048 |
fired | +0.043 |
closer | +0.040 |
beh | +0.040 |
revenge | +0.038 |
Neg logit contributions | |
pron | -0.047 |
kin | -0.047 |
uren | -0.043 |
lf | -0.038 |
omo | -0.037 |
Token | future |
Token ID | 2003 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
aback | +0.032 |
closer | +0.029 |
fired | +0.028 |
home | +0.027 |
away | +0.027 |
Neg logit contributions | |
kin | -0.032 |
pron | -0.029 |
uren | -0.027 |
omo | -0.024 |
Adam | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
aback | +0.026 |
closer | +0.026 |
home | +0.025 |
fired | +0.025 |
away | +0.024 |
Neg logit contributions | |
kin | -0.033 |
pron | -0.032 |
uren | -0.029 |
scalp | -0.025 |
ae | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
aback | +0.028 |
closer | +0.025 |
fired | +0.025 |
away | +0.023 |
revenge | +0.023 |
Neg logit contributions | |
kin | -0.039 |
pron | -0.036 |
uren | -0.034 |
omo | -0.031 |
lf | -0.030 |
Token | time |
Token ID | 640 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
aback | +0.033 |
closer | +0.032 |
away | +0.031 |
home | +0.031 |
back | +0.030 |
Neg logit contributions | |
kin | -0.028 |
pron | -0.025 |
uren | -0.024 |
olo | -0.021 |
lf | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
aback | +0.031 |
closer | +0.026 |
fired | +0.024 |
home | +0.022 |
away | +0.022 |
Neg logit contributions | |
kin | -0.110 |
pron | -0.104 |
uren | -0.099 |
omo | -0.093 |
lf | -0.093 |
Token | come |
Token ID | 1282 |
Feature activation | +3.28e+00 |
Pos logit contributions | |
home | +0.008 |
away | +0.008 |
closer | +0.008 |
aback | +0.007 |
back | +0.007 |
Neg logit contributions | |
pron | -0.016 |
kin | -0.015 |
uren | -0.014 |
ae | -0.013 |
lf | -0.013 |
Token | back |
Token ID | 736 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
aback | +0.037 |
beh | +0.026 |
revenge | +0.025 |
fired | +0.025 |
medical | +0.023 |
Neg logit contributions | |
kin | -0.107 |
pron | -0.098 |
uren | -0.094 |
omo | -0.090 |
ia | -0.088 |
Token | , |
Token ID | 11 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
aback | +0.120 |
beh | +0.107 |
revenge | +0.101 |
medical | +0.099 |
fired | +0.095 |
Neg logit contributions | |
kin | -0.129 |
pron | -0.111 |
uren | -0.111 |
Ben | -0.105 |
omo | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
closer | +0.000 |
home | +0.000 |
away | +0.000 |
back | +0.000 |
down | +0.000 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.000 |
majesty | -0.000 |
moons | -0.000 |
Token | glad |
Token ID | 9675 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
kin | +0.019 |
pron | +0.018 |
uren | +0.017 |
ae | +0.016 |
addy | +0.016 |
Neg logit contributions | |
closer | -0.012 |
home | -0.012 |
aback | -0.012 |
away | -0.011 |
back | -0.011 |
Token | bird |
Token ID | 6512 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
home | +0.007 |
closer | +0.007 |
aback | +0.007 |
fired | +0.006 |
away | +0.006 |
Neg logit contributions | |
kin | -0.013 |
pron | -0.013 |
uren | -0.012 |
Adam | -0.011 |
ae | -0.011 |
Token | flew |
Token ID | 13112 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
aback | +0.053 |
closer | +0.049 |
fired | +0.047 |
away | +0.046 |
home | +0.044 |
Neg logit contributions | |
kin | -0.063 |
pron | -0.059 |
uren | -0.055 |
omo | -0.049 |
Adam | -0.049 |
Token | : |
Token ID | 25 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
kin | +0.071 |
pron | +0.068 |
uren | +0.064 |
omo | +0.056 |
lf | +0.056 |
Neg logit contributions | |
aback | -0.054 |
closer | -0.050 |
fired | -0.048 |
away | -0.046 |
home | -0.046 |
Token | houses |
Token ID | 7777 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
kin | +0.010 |
pron | +0.009 |
uren | +0.009 |
omo | +0.008 |
lf | +0.008 |
Neg logit contributions | |
aback | -0.008 |
closer | -0.008 |
fired | -0.007 |
away | -0.007 |
home | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
kin | +0.126 |
pron | +0.122 |
uren | +0.117 |
omo | +0.105 |
addy | +0.102 |
Neg logit contributions | |
aback | -0.080 |
closer | -0.075 |
away | -0.072 |
home | -0.069 |
fired | -0.068 |
Token | towers |
Token ID | 18028 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
kin | +0.074 |
pron | +0.068 |
uren | +0.064 |
ae | +0.056 |
omo | +0.056 |
Neg logit contributions | |
aback | -0.069 |
closer | -0.065 |
fired | -0.061 |
away | -0.060 |
home | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
kin | +0.162 |
pron | +0.162 |
uren | +0.155 |
omo | +0.135 |
addy | +0.134 |
Neg logit contributions | |
aback | -0.072 |
home | -0.068 |
away | -0.067 |
back | -0.067 |
closer | -0.066 |
Token | bridges |
Token ID | 19432 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
kin | +0.096 |
pron | +0.088 |
uren | +0.083 |
ae | +0.074 |
omo | +0.072 |
Neg logit contributions | |
aback | -0.082 |
closer | -0.079 |
away | -0.073 |
fired | -0.072 |
home | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
pron | +0.209 |
kin | +0.207 |
uren | +0.198 |
omo | +0.175 |
addy | +0.171 |
Neg logit contributions | |
aback | -0.117 |
away | -0.109 |
home | -0.108 |
closer | -0.106 |
back | -0.104 |
Token | cars |
Token ID | 5006 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
kin | +0.114 |
pron | +0.106 |
uren | +0.100 |
ae | +0.089 |
omo | +0.087 |
Neg logit contributions | |
aback | -0.094 |
closer | -0.092 |
away | -0.084 |
fired | -0.081 |
back | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
kin | +0.119 |
pron | +0.115 |
uren | +0.108 |
ae | +0.097 |
omo | +0.097 |
Neg logit contributions | |
aback | -0.074 |
closer | -0.068 |
away | -0.067 |
home | -0.065 |
fired | -0.064 |
Token | One |
Token ID | 1881 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
kin | +0.003 |
pron | +0.003 |
lf | +0.002 |
uren | +0.002 |
bridge | +0.002 |
Neg logit contributions | |
aback | -0.002 |
closer | -0.002 |
home | -0.002 |
back | -0.002 |
fired | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
kin | +0.020 |
pron | +0.018 |
uren | +0.017 |
omo | +0.015 |
lf | +0.015 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.015 |
away | -0.014 |
revenge | -0.014 |
Token | about |
Token ID | 546 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
kin | +0.031 |
pron | +0.029 |
uren | +0.027 |
lf | +0.024 |
omo | +0.024 |
Neg logit contributions | |
aback | -0.025 |
fired | -0.022 |
closer | -0.022 |
revenge | -0.020 |
away | -0.020 |
Token | numbers |
Token ID | 3146 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
kin | +0.039 |
pron | +0.036 |
uren | +0.033 |
lf | +0.030 |
omo | +0.030 |
Neg logit contributions | |
aback | -0.035 |
closer | -0.031 |
fired | -0.031 |
away | -0.029 |
revenge | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
kin | +0.072 |
pron | +0.068 |
uren | +0.065 |
omo | +0.059 |
lf | +0.056 |
Neg logit contributions | |
aback | -0.052 |
closer | -0.049 |
away | -0.046 |
fired | -0.046 |
home | -0.045 |
Token | shapes |
Token ID | 15268 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
kin | +0.112 |
pron | +0.103 |
uren | +0.096 |
omo | +0.086 |
ae | +0.084 |
Neg logit contributions | |
aback | -0.100 |
closer | -0.096 |
away | -0.087 |
fired | -0.087 |
revenge | -0.086 |
Token | , |
Token ID | 11 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
kin | +0.178 |
pron | +0.177 |
uren | +0.170 |
omo | +0.152 |
Adam | +0.148 |
Neg logit contributions | |
aback | -0.106 |
closer | -0.098 |
away | -0.096 |
home | -0.094 |
back | -0.089 |
Token | patterns |
Token ID | 7572 |
Feature activation | -7.39e+00 |
Pos logit contributions | |
kin | +0.132 |
pron | +0.123 |
uren | +0.115 |
ae | +0.103 |
omo | +0.103 |
Neg logit contributions | |
aback | -0.109 |
closer | -0.103 |
away | -0.095 |
fired | -0.093 |
home | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
pron | +0.197 |
kin | +0.197 |
uren | +0.188 |
omo | +0.170 |
Adam | +0.164 |
Neg logit contributions | |
aback | -0.120 |
closer | -0.109 |
away | -0.107 |
home | -0.105 |
fired | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
kin | +0.147 |
pron | +0.138 |
uren | +0.129 |
omo | +0.117 |
ae | +0.117 |
Neg logit contributions | |
aback | -0.111 |
closer | -0.106 |
away | -0.098 |
back | -0.094 |
fired | -0.094 |
Token | more |
Token ID | 517 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
kin | +0.047 |
pron | +0.044 |
uren | +0.040 |
lf | +0.036 |
omo | +0.036 |
Neg logit contributions | |
aback | -0.049 |
fired | -0.044 |
closer | -0.044 |
away | -0.041 |
revenge | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
kin | +0.051 |
pron | +0.048 |
uren | +0.045 |
omo | +0.040 |
ae | +0.039 |
Neg logit contributions | |
aback | -0.040 |
closer | -0.036 |
fired | -0.035 |
away | -0.033 |
home | -0.033 |
Token | Do |
Token ID | 2141 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
fired | +0.001 |
revenge | +0.001 |
away | +0.001 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.001 |
lf | -0.001 |
omo | -0.001 |
Token | build |
Token ID | 1382 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
kin | +0.046 |
pron | +0.042 |
uren | +0.038 |
lf | +0.034 |
omo | +0.034 |
Neg logit contributions | |
aback | -0.047 |
closer | -0.042 |
fired | -0.042 |
revenge | -0.039 |
away | -0.039 |
Token | houses |
Token ID | 7777 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
kin | +0.079 |
pron | +0.071 |
uren | +0.064 |
lf | +0.061 |
Adam | +0.058 |
Neg logit contributions | |
aback | -0.078 |
fired | -0.070 |
closer | -0.068 |
revenge | -0.065 |
beh | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
kin | +0.064 |
pron | +0.058 |
uren | +0.052 |
lf | +0.049 |
omo | +0.047 |
Neg logit contributions | |
aback | -0.063 |
fired | -0.056 |
closer | -0.054 |
revenge | -0.052 |
away | -0.049 |
Token | towers |
Token ID | 18028 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
kin | +0.082 |
pron | +0.075 |
uren | +0.071 |
omo | +0.063 |
ae | +0.062 |
Neg logit contributions | |
aback | -0.076 |
closer | -0.072 |
fired | -0.067 |
away | -0.066 |
home | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
kin | +0.136 |
pron | +0.135 |
uren | +0.129 |
omo | +0.112 |
addy | +0.111 |
Neg logit contributions | |
aback | -0.076 |
closer | -0.075 |
away | -0.073 |
home | -0.072 |
back | -0.072 |
Token | bridges |
Token ID | 19432 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
kin | +0.100 |
pron | +0.092 |
uren | +0.087 |
ae | +0.078 |
omo | +0.077 |
Neg logit contributions | |
aback | -0.080 |
closer | -0.078 |
fired | -0.071 |
away | -0.071 |
home | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
pron | +0.189 |
kin | +0.189 |
uren | +0.180 |
omo | +0.159 |
addy | +0.154 |
Neg logit contributions | |
aback | -0.122 |
closer | -0.113 |
away | -0.112 |
home | -0.111 |
back | -0.108 |
Token | cars |
Token ID | 5006 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
kin | +0.034 |
pron | +0.032 |
uren | +0.029 |
lf | +0.027 |
moons | +0.027 |
Neg logit contributions | |
aback | -0.038 |
fired | -0.034 |
closer | -0.032 |
revenge | -0.031 |
away | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
kin | +0.090 |
pron | +0.084 |
uren | +0.079 |
omo | +0.071 |
lf | +0.070 |
Neg logit contributions | |
aback | -0.070 |
closer | -0.063 |
fired | -0.062 |
away | -0.059 |
home | -0.058 |
Token | They |
Token ID | 1119 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
kin | +0.001 |
pron | +0.001 |
uren | +0.001 |
lf | +0.001 |
ae | +0.001 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
fired | -0.001 |
home | -0.001 |
revenge | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +7.78e-01 |
Pos logit contributions | |
kin | +0.081 |
pron | +0.078 |
uren | +0.076 |
stand | +0.068 |
ae | +0.067 |
Neg logit contributions | |
closer | -0.062 |
aback | -0.059 |
away | -0.057 |
fired | -0.055 |
home | -0.053 |
Token | build |
Token ID | 1382 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
kin | +0.057 |
pron | +0.053 |
uren | +0.052 |
ae | +0.044 |
omo | +0.044 |
Neg logit contributions | |
closer | -0.041 |
aback | -0.040 |
away | -0.037 |
fired | -0.036 |
home | -0.036 |
Token | houses |
Token ID | 7777 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
kin | +0.079 |
pron | +0.072 |
uren | +0.066 |
omo | +0.058 |
lf | +0.058 |
Neg logit contributions | |
aback | -0.087 |
closer | -0.079 |
fired | -0.078 |
away | -0.074 |
revenge | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
kin | +0.077 |
pron | +0.070 |
uren | +0.065 |
lf | +0.059 |
omo | +0.058 |
Neg logit contributions | |
aback | -0.072 |
fired | -0.064 |
closer | -0.064 |
revenge | -0.060 |
away | -0.059 |
Token | towers |
Token ID | 18028 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
kin | +0.075 |
pron | +0.068 |
uren | +0.063 |
omo | +0.055 |
lf | +0.055 |
Neg logit contributions | |
aback | -0.083 |
closer | -0.076 |
fired | -0.075 |
away | -0.071 |
revenge | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
kin | +0.146 |
pron | +0.145 |
uren | +0.137 |
omo | +0.121 |
ae | +0.120 |
Neg logit contributions | |
aback | -0.070 |
closer | -0.067 |
away | -0.063 |
home | -0.063 |
back | -0.062 |
Token | bridges |
Token ID | 19432 |
Feature activation | -7.14e+00 |
Pos logit contributions | |
kin | +0.092 |
pron | +0.085 |
uren | +0.079 |
ae | +0.070 |
omo | +0.070 |
Neg logit contributions | |
aback | -0.082 |
closer | -0.078 |
fired | -0.072 |
away | -0.072 |
home | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
pron | +0.201 |
kin | +0.200 |
uren | +0.191 |
omo | +0.169 |
addy | +0.165 |
Neg logit contributions | |
aback | -0.110 |
closer | -0.102 |
away | -0.099 |
home | -0.099 |
back | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
kin | +0.114 |
pron | +0.106 |
uren | +0.100 |
ae | +0.088 |
omo | +0.088 |
Neg logit contributions | |
aback | -0.090 |
closer | -0.088 |
away | -0.081 |
fired | -0.079 |
back | -0.078 |
Token | cars |
Token ID | 5006 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
kin | +0.031 |
pron | +0.029 |
uren | +0.027 |
lf | +0.025 |
moons | +0.024 |
Neg logit contributions | |
aback | -0.025 |
fired | -0.022 |
closer | -0.021 |
revenge | -0.020 |
away | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
kin | +0.100 |
pron | +0.096 |
uren | +0.091 |
omo | +0.082 |
ae | +0.080 |
Neg logit contributions | |
aback | -0.067 |
closer | -0.063 |
fired | -0.060 |
away | -0.060 |
home | -0.058 |
Token | Sometimes |
Token ID | 8975 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
home | +0.001 |
fired | +0.001 |
away | +0.001 |
Neg logit contributions | |
kin | -0.002 |
pron | -0.002 |
uren | -0.002 |
lf | -0.002 |
ae | -0.001 |
Token | trucks |
Token ID | 13960 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.022 |
omo | +0.019 |
ae | +0.019 |
Neg logit contributions | |
aback | -0.025 |
closer | -0.023 |
fired | -0.022 |
away | -0.021 |
revenge | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
kin | +0.093 |
pron | +0.089 |
uren | +0.084 |
omo | +0.075 |
lf | +0.074 |
Neg logit contributions | |
aback | -0.064 |
closer | -0.058 |
fired | -0.056 |
away | -0.055 |
home | -0.053 |
Token | different |
Token ID | 1180 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
kin | +0.040 |
pron | +0.037 |
uren | +0.035 |
lf | +0.031 |
Adam | +0.031 |
Neg logit contributions | |
aback | -0.033 |
fired | -0.030 |
closer | -0.029 |
revenge | -0.027 |
away | -0.027 |
Token | colors |
Token ID | 7577 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
kin | +0.060 |
pron | +0.054 |
uren | +0.050 |
lf | +0.044 |
omo | +0.044 |
Neg logit contributions | |
aback | -0.075 |
closer | -0.069 |
fired | -0.068 |
away | -0.064 |
revenge | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
kin | +0.193 |
pron | +0.189 |
uren | +0.189 |
ae | +0.167 |
majesty | +0.167 |
Neg logit contributions | |
closer | -0.075 |
aback | -0.071 |
away | -0.070 |
back | -0.067 |
home | -0.066 |
Token | sizes |
Token ID | 10620 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.019 |
uren | +0.017 |
ae | +0.015 |
addy | +0.014 |
Neg logit contributions | |
aback | -0.037 |
closer | -0.035 |
away | -0.034 |
fired | -0.034 |
revenge | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -9.44e-03 |
Pos logit contributions | |
pron | +0.222 |
kin | +0.219 |
uren | +0.219 |
omo | +0.192 |
ae | +0.192 |
Neg logit contributions | |
aback | -0.079 |
away | -0.078 |
closer | -0.077 |
home | -0.074 |
back | -0.071 |
Token | They |
Token ID | 1119 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
kin | +0.000 |
pron | +0.000 |
uren | +0.000 |
lf | +0.000 |
majesty | +0.000 |
Neg logit contributions | |
aback | -0.000 |
closer | -0.000 |
fired | -0.000 |
home | -0.000 |
revenge | -0.000 |
Token | make |
Token ID | 787 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
kin | +0.095 |
pron | +0.090 |
uren | +0.084 |
ae | +0.081 |
omo | +0.077 |
Neg logit contributions | |
closer | -0.054 |
away | -0.051 |
aback | -0.050 |
back | -0.046 |
home | -0.044 |
Token | noises |
Token ID | 26782 |
Feature activation | -4.03e+00 |
Pos logit contributions | |
kin | +0.095 |
pron | +0.087 |
uren | +0.080 |
ae | +0.073 |
omo | +0.073 |
Neg logit contributions | |
aback | -0.060 |
closer | -0.060 |
away | -0.055 |
home | -0.053 |
back | -0.052 |
Token | like |
Token ID | 588 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
kin | +0.116 |
pron | +0.110 |
uren | +0.104 |
omo | +0.101 |
addy | +0.097 |
Neg logit contributions | |
closer | -0.068 |
aback | -0.060 |
away | -0.060 |
back | -0.058 |
home | -0.053 |
Token | make |
Token ID | 787 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
kin | +0.076 |
pron | +0.071 |
uren | +0.068 |
ae | +0.062 |
omo | +0.061 |
Neg logit contributions | |
aback | -0.059 |
closer | -0.058 |
away | -0.054 |
fired | -0.053 |
home | -0.052 |
Token | houses |
Token ID | 7777 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
kin | +0.083 |
pron | +0.077 |
uren | +0.074 |
omo | +0.065 |
ae | +0.062 |
Neg logit contributions | |
closer | -0.065 |
aback | -0.062 |
away | -0.059 |
home | -0.058 |
back | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
kin | +0.077 |
pron | +0.071 |
uren | +0.066 |
omo | +0.059 |
lf | +0.058 |
Neg logit contributions | |
aback | -0.071 |
closer | -0.065 |
fired | -0.063 |
away | -0.060 |
home | -0.059 |
Token | towers |
Token ID | 18028 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
kin | +0.080 |
pron | +0.072 |
uren | +0.069 |
ae | +0.061 |
omo | +0.060 |
Neg logit contributions | |
aback | -0.070 |
closer | -0.067 |
away | -0.062 |
fired | -0.062 |
home | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
kin | +0.135 |
pron | +0.133 |
uren | +0.126 |
omo | +0.112 |
Adam | +0.110 |
Neg logit contributions | |
aback | -0.075 |
closer | -0.071 |
home | -0.068 |
away | -0.068 |
back | -0.066 |
Token | bridges |
Token ID | 19432 |
Feature activation | -7.00e+00 |
Pos logit contributions | |
kin | +0.095 |
pron | +0.087 |
uren | +0.083 |
ae | +0.074 |
omo | +0.073 |
Neg logit contributions | |
aback | -0.075 |
closer | -0.074 |
away | -0.068 |
fired | -0.066 |
back | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
pron | +0.197 |
kin | +0.196 |
uren | +0.186 |
omo | +0.167 |
addy | +0.162 |
Neg logit contributions | |
aback | -0.106 |
closer | -0.098 |
away | -0.096 |
home | -0.096 |
back | -0.092 |
Token | cars |
Token ID | 5006 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
kin | +0.039 |
pron | +0.036 |
uren | +0.034 |
lf | +0.031 |
omo | +0.030 |
Neg logit contributions | |
aback | -0.035 |
fired | -0.031 |
closer | -0.030 |
revenge | -0.029 |
away | -0.028 |
Token | with |
Token ID | 351 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
kin | +0.099 |
pron | +0.094 |
uren | +0.089 |
omo | +0.080 |
ae | +0.078 |
Neg logit contributions | |
aback | -0.069 |
closer | -0.064 |
fired | -0.061 |
away | -0.060 |
home | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
aback | +0.002 |
fired | +0.002 |
closer | +0.002 |
revenge | +0.002 |
away | +0.002 |
Neg logit contributions | |
kin | -0.002 |
pron | -0.002 |
uren | -0.001 |
lf | -0.001 |
omo | -0.001 |
Token | blocks |
Token ID | 7021 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
kin | +0.024 |
pron | +0.022 |
uren | +0.021 |
omo | +0.018 |
lf | +0.018 |
Neg logit contributions | |
aback | -0.022 |
closer | -0.021 |
fired | -0.019 |
away | -0.019 |
home | -0.019 |
Token | make |
Token ID | 787 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
kin | +0.042 |
pron | +0.038 |
uren | +0.034 |
lf | +0.032 |
Adam | +0.029 |
Neg logit contributions | |
aback | -0.049 |
fired | -0.044 |
closer | -0.042 |
beh | -0.040 |
revenge | -0.040 |
Token | houses |
Token ID | 7777 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
kin | +0.068 |
pron | +0.064 |
uren | +0.059 |
omo | +0.053 |
lf | +0.052 |
Neg logit contributions | |
aback | -0.059 |
closer | -0.055 |
fired | -0.052 |
away | -0.051 |
home | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
kin | +0.078 |
pron | +0.073 |
uren | +0.069 |
omo | +0.062 |
lf | +0.061 |
Neg logit contributions | |
aback | -0.060 |
closer | -0.055 |
fired | -0.052 |
away | -0.051 |
home | -0.049 |
Token | castles |
Token ID | 49203 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
kin | +0.091 |
pron | +0.085 |
uren | +0.080 |
ae | +0.071 |
omo | +0.071 |
Neg logit contributions | |
aback | -0.082 |
closer | -0.079 |
away | -0.073 |
fired | -0.071 |
revenge | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
kin | +0.138 |
pron | +0.136 |
uren | +0.132 |
omo | +0.118 |
ae | +0.116 |
Neg logit contributions | |
aback | -0.087 |
away | -0.084 |
closer | -0.084 |
home | -0.080 |
back | -0.079 |
Token | bridges |
Token ID | 19432 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
kin | +0.099 |
pron | +0.093 |
uren | +0.089 |
ae | +0.079 |
omo | +0.079 |
Neg logit contributions | |
aback | -0.078 |
closer | -0.077 |
away | -0.071 |
fired | -0.069 |
back | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
kin | +0.184 |
pron | +0.183 |
uren | +0.174 |
omo | +0.155 |
ae | +0.150 |
Neg logit contributions | |
aback | -0.120 |
closer | -0.112 |
away | -0.112 |
home | -0.108 |
fired | -0.106 |
Token | more |
Token ID | 517 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
kin | +0.031 |
pron | +0.028 |
uren | +0.026 |
moons | +0.024 |
lf | +0.024 |
Neg logit contributions | |
aback | -0.034 |
fired | -0.031 |
closer | -0.029 |
revenge | -0.028 |
home | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.020 |
uren | +0.018 |
omo | +0.016 |
lf | +0.016 |
Neg logit contributions | |
aback | -0.019 |
closer | -0.017 |
fired | -0.017 |
away | -0.015 |
revenge | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -5.16e-02 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.005 |
lf | +0.005 |
uren | +0.004 |
bridge | +0.004 |
Neg logit contributions | |
aback | -0.003 |
closer | -0.003 |
home | -0.003 |
fired | -0.003 |
away | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
kin | +0.001 |
pron | +0.001 |
uren | +0.001 |
lf | +0.001 |
moons | +0.001 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
fired | -0.001 |
home | -0.001 |
away | -0.001 |
Token | cars |
Token ID | 5006 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
kin | +0.023 |
pron | +0.021 |
uren | +0.019 |
lf | +0.017 |
omo | +0.017 |
Neg logit contributions | |
aback | -0.023 |
closer | -0.021 |
fired | -0.021 |
revenge | -0.020 |
away | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
kin | +0.075 |
pron | +0.071 |
uren | +0.066 |
omo | +0.059 |
lf | +0.059 |
Neg logit contributions | |
aback | -0.059 |
closer | -0.053 |
fired | -0.052 |
away | -0.049 |
home | -0.048 |
Token | different |
Token ID | 1180 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
kin | +0.048 |
pron | +0.045 |
uren | +0.042 |
omo | +0.038 |
lf | +0.038 |
Neg logit contributions | |
aback | -0.035 |
closer | -0.031 |
fired | -0.031 |
away | -0.029 |
revenge | -0.029 |
Token | colors |
Token ID | 7577 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
kin | +0.048 |
pron | +0.043 |
uren | +0.039 |
omo | +0.033 |
lf | +0.033 |
Neg logit contributions | |
aback | -0.070 |
closer | -0.065 |
fired | -0.064 |
away | -0.061 |
revenge | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
kin | +0.164 |
uren | +0.162 |
pron | +0.162 |
ae | +0.142 |
majesty | +0.140 |
Neg logit contributions | |
aback | -0.097 |
closer | -0.090 |
away | -0.087 |
back | -0.084 |
home | -0.083 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.019 |
uren | +0.017 |
ae | +0.015 |
addy | +0.014 |
Neg logit contributions | |
aback | -0.031 |
closer | -0.029 |
fired | -0.028 |
away | -0.028 |
revenge | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
pron | +0.212 |
uren | +0.210 |
kin | +0.209 |
ae | +0.186 |
omo | +0.184 |
Neg logit contributions | |
aback | -0.090 |
away | -0.082 |
closer | -0.080 |
home | -0.079 |
back | -0.075 |
Token | He |
Token ID | 679 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
kin | +0.012 |
pron | +0.011 |
uren | +0.010 |
lf | +0.009 |
majesty | +0.009 |
Neg logit contributions | |
aback | -0.007 |
closer | -0.006 |
home | -0.006 |
fired | -0.006 |
back | -0.006 |
Token | liked |
Token ID | 8288 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
kin | +0.042 |
pron | +0.039 |
uren | +0.038 |
ae | +0.035 |
unison | +0.034 |
Neg logit contributions | |
closer | -0.031 |
aback | -0.030 |
fired | -0.029 |
away | -0.029 |
back | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.026 |
uren | +0.025 |
ae | +0.024 |
omo | +0.024 |
Neg logit contributions | |
aback | -0.005 |
closer | -0.005 |
fired | -0.004 |
home | -0.004 |
away | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.026 |
uren | +0.024 |
ae | +0.023 |
omo | +0.022 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.018 |
away | -0.017 |
fired | -0.016 |
revenge | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
kin | +0.078 |
pron | +0.073 |
uren | +0.068 |
ae | +0.062 |
Adam | +0.059 |
Neg logit contributions | |
aback | -0.066 |
closer | -0.065 |
fired | -0.061 |
away | -0.060 |
home | -0.059 |
Token | many |
Token ID | 867 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
aback | +0.007 |
closer | +0.007 |
home | +0.006 |
fired | +0.006 |
away | +0.006 |
Neg logit contributions | |
kin | -0.015 |
pron | -0.014 |
uren | -0.013 |
lf | -0.012 |
omo | -0.012 |
Token | dolls |
Token ID | 36062 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
kin | +0.015 |
pron | +0.013 |
lf | +0.011 |
omo | +0.011 |
uren | +0.011 |
Neg logit contributions | |
aback | -0.026 |
fired | -0.024 |
closer | -0.024 |
nearer | -0.023 |
revenge | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
kin | +0.064 |
pron | +0.060 |
uren | +0.056 |
omo | +0.051 |
lf | +0.050 |
Neg logit contributions | |
aback | -0.050 |
closer | -0.045 |
fired | -0.044 |
away | -0.041 |
home | -0.041 |
Token | different |
Token ID | 1180 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
kin | +0.045 |
pron | +0.042 |
uren | +0.039 |
omo | +0.036 |
lf | +0.035 |
Neg logit contributions | |
aback | -0.038 |
fired | -0.034 |
closer | -0.033 |
away | -0.030 |
revenge | -0.030 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
kin | +0.044 |
pron | +0.038 |
uren | +0.035 |
lf | +0.030 |
omo | +0.030 |
Neg logit contributions | |
aback | -0.076 |
closer | -0.071 |
fired | -0.070 |
revenge | -0.066 |
away | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
pron | +0.197 |
kin | +0.193 |
uren | +0.192 |
ae | +0.169 |
Adam | +0.165 |
Neg logit contributions | |
aback | -0.107 |
closer | -0.095 |
away | -0.094 |
home | -0.093 |
fired | -0.089 |
Token | colors |
Token ID | 7577 |
Feature activation | -6.07e+00 |
Pos logit contributions | |
kin | +0.030 |
pron | +0.027 |
uren | +0.024 |
ae | +0.021 |
Adam | +0.020 |
Neg logit contributions | |
aback | -0.042 |
closer | -0.040 |
fired | -0.039 |
away | -0.038 |
revenge | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
kin | +0.169 |
pron | +0.165 |
uren | +0.161 |
ae | +0.143 |
Adam | +0.142 |
Neg logit contributions | |
aback | -0.095 |
closer | -0.090 |
away | -0.085 |
home | -0.081 |
fired | -0.080 |
Token | They |
Token ID | 1119 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
home | +0.001 |
fired | +0.001 |
away | +0.001 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.001 |
lf | -0.001 |
majesty | -0.001 |
Token | also |
Token ID | 635 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
kin | +0.079 |
pron | +0.074 |
uren | +0.071 |
ae | +0.065 |
stand | +0.062 |
Neg logit contributions | |
closer | -0.062 |
aback | -0.059 |
away | -0.058 |
fired | -0.054 |
home | -0.054 |
Token | build |
Token ID | 1382 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
kin | +0.059 |
pron | +0.054 |
uren | +0.052 |
ae | +0.045 |
omo | +0.044 |
Neg logit contributions | |
closer | -0.043 |
aback | -0.040 |
away | -0.039 |
home | -0.037 |
fired | -0.037 |
Token | towers |
Token ID | 18028 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
kin | +0.077 |
pron | +0.070 |
uren | +0.065 |
lf | +0.058 |
omo | +0.057 |
Neg logit contributions | |
aback | -0.080 |
closer | -0.072 |
fired | -0.072 |
revenge | -0.067 |
away | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
kin | +0.105 |
pron | +0.099 |
uren | +0.093 |
omo | +0.083 |
lf | +0.080 |
Neg logit contributions | |
aback | -0.079 |
closer | -0.074 |
fired | -0.069 |
away | -0.069 |
home | -0.068 |
Token | houses |
Token ID | 7777 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
kin | +0.084 |
pron | +0.077 |
uren | +0.072 |
omo | +0.063 |
ae | +0.062 |
Neg logit contributions | |
aback | -0.081 |
closer | -0.078 |
fired | -0.072 |
away | -0.071 |
home | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
kin | +0.114 |
pron | +0.108 |
uren | +0.101 |
omo | +0.091 |
Adam | +0.089 |
Neg logit contributions | |
aback | -0.080 |
closer | -0.074 |
fired | -0.069 |
away | -0.068 |
home | -0.067 |
Token | bridges |
Token ID | 19432 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
kin | +0.093 |
pron | +0.085 |
uren | +0.080 |
ae | +0.071 |
omo | +0.071 |
Neg logit contributions | |
aback | -0.076 |
closer | -0.074 |
away | -0.068 |
fired | -0.067 |
home | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
kin | +0.192 |
pron | +0.190 |
uren | +0.179 |
omo | +0.160 |
addy | +0.156 |
Neg logit contributions | |
aback | -0.111 |
closer | -0.102 |
away | -0.099 |
home | -0.099 |
fired | -0.095 |
Token | anything |
Token ID | 1997 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
kin | +0.035 |
pron | +0.032 |
uren | +0.030 |
lf | +0.028 |
moons | +0.028 |
Neg logit contributions | |
aback | -0.034 |
fired | -0.030 |
closer | -0.029 |
revenge | -0.028 |
away | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | -4.52e+00 |
Pos logit contributions | |
kin | +0.034 |
pron | +0.033 |
uren | +0.030 |
omo | +0.026 |
ae | +0.026 |
Neg logit contributions | |
aback | -0.041 |
closer | -0.038 |
fired | -0.037 |
away | -0.036 |
revenge | -0.036 |
Token | wanted |
Token ID | 2227 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
kin | +0.101 |
pron | +0.094 |
uren | +0.090 |
omo | +0.081 |
ae | +0.078 |
Neg logit contributions | |
aback | -0.096 |
closer | -0.090 |
fired | -0.087 |
away | -0.086 |
revenge | -0.083 |
Token | with |
Token ID | 351 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
kin | +0.016 |
pron | +0.014 |
uren | +0.013 |
lf | +0.012 |
omo | +0.012 |
Neg logit contributions | |
aback | -0.014 |
fired | -0.012 |
closer | -0.012 |
revenge | -0.011 |
away | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
pron | +0.211 |
uren | +0.207 |
kin | +0.202 |
Adam | +0.181 |
omo | +0.181 |
Neg logit contributions | |
aback | -0.076 |
closer | -0.074 |
away | -0.073 |
home | -0.068 |
back | -0.068 |
Token | They |
Token ID | 1119 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
fired | +0.004 |
home | +0.004 |
away | +0.004 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.005 |
uren | -0.004 |
lf | -0.004 |
ae | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
kin | +0.089 |
pron | +0.087 |
uren | +0.082 |
omo | +0.078 |
ae | +0.078 |
Neg logit contributions | |
closer | -0.051 |
away | -0.048 |
aback | -0.045 |
back | -0.043 |
home | -0.041 |
Token | pictures |
Token ID | 5986 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
kin | +0.084 |
pron | +0.082 |
uren | +0.075 |
omo | +0.070 |
Adam | +0.064 |
Neg logit contributions | |
closer | -0.072 |
aback | -0.068 |
away | -0.066 |
home | -0.065 |
back | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
kin | +0.136 |
pron | +0.132 |
uren | +0.126 |
omo | +0.114 |
ae | +0.112 |
Neg logit contributions | |
aback | -0.071 |
closer | -0.071 |
away | -0.062 |
home | -0.060 |
back | -0.060 |
Token | patterns |
Token ID | 7572 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
kin | +0.011 |
pron | +0.010 |
uren | +0.009 |
ae | +0.008 |
addy | +0.008 |
Neg logit contributions | |
closer | -0.014 |
aback | -0.014 |
away | -0.013 |
fired | -0.012 |
home | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
pron | +0.199 |
kin | +0.197 |
uren | +0.191 |
omo | +0.173 |
Adam | +0.169 |
Neg logit contributions | |
closer | -0.099 |
aback | -0.097 |
away | -0.089 |
back | -0.084 |
home | -0.083 |
Token | them |
Token ID | 606 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
kin | +0.008 |
pron | +0.008 |
uren | +0.007 |
omo | +0.006 |
ae | +0.006 |
Neg logit contributions | |
aback | -0.007 |
closer | -0.007 |
away | -0.007 |
home | -0.007 |
fired | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
kin | +0.042 |
pron | +0.041 |
uren | +0.039 |
omo | +0.036 |
Adam | +0.035 |
Neg logit contributions | |
closer | -0.023 |
aback | -0.023 |
away | -0.022 |
home | -0.021 |
fired | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
kin | +0.003 |
pron | +0.003 |
uren | +0.003 |
omo | +0.003 |
ae | +0.003 |
Neg logit contributions | |
aback | -0.002 |
closer | -0.002 |
away | -0.002 |
home | -0.002 |
back | -0.001 |
Token | floor |
Token ID | 4314 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.026 |
uren | +0.024 |
omo | +0.022 |
Adam | +0.021 |
Neg logit contributions | |
aback | -0.034 |
closer | -0.033 |
away | -0.032 |
home | -0.032 |
fired | -0.031 |
Token | trucks |
Token ID | 13960 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.022 |
omo | +0.020 |
ae | +0.020 |
Neg logit contributions | |
aback | -0.025 |
closer | -0.023 |
fired | -0.022 |
away | -0.021 |
revenge | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
kin | +0.084 |
pron | +0.079 |
uren | +0.075 |
omo | +0.067 |
ae | +0.066 |
Neg logit contributions | |
aback | -0.064 |
closer | -0.059 |
away | -0.056 |
fired | -0.056 |
home | -0.055 |
Token | different |
Token ID | 1180 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
kin | +0.040 |
pron | +0.037 |
uren | +0.035 |
lf | +0.032 |
omo | +0.032 |
Neg logit contributions | |
aback | -0.031 |
closer | -0.028 |
fired | -0.027 |
away | -0.025 |
revenge | -0.025 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.89e+00 |
Pos logit contributions | |
kin | +0.055 |
pron | +0.050 |
uren | +0.045 |
lf | +0.040 |
omo | +0.040 |
Neg logit contributions | |
aback | -0.069 |
closer | -0.064 |
fired | -0.062 |
revenge | -0.059 |
away | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
kin | +0.166 |
uren | +0.162 |
pron | +0.161 |
ae | +0.141 |
majesty | +0.139 |
Neg logit contributions | |
aback | -0.086 |
closer | -0.085 |
away | -0.081 |
back | -0.080 |
home | -0.079 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.021 |
ae | +0.018 |
omo | +0.018 |
Neg logit contributions | |
aback | -0.040 |
closer | -0.038 |
fired | -0.037 |
away | -0.036 |
revenge | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
kin | +0.202 |
pron | +0.202 |
uren | +0.197 |
omo | +0.174 |
ae | +0.173 |
Neg logit contributions | |
aback | -0.095 |
closer | -0.088 |
away | -0.088 |
home | -0.085 |
back | -0.083 |
Token | He |
Token ID | 679 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
kin | +0.006 |
pron | +0.006 |
uren | +0.005 |
lf | +0.005 |
ae | +0.005 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.003 |
fired | -0.003 |
home | -0.003 |
revenge | -0.003 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
kin | +0.032 |
pron | +0.030 |
uren | +0.028 |
ae | +0.025 |
utes | +0.025 |
Neg logit contributions | |
closer | -0.022 |
aback | -0.022 |
fired | -0.020 |
away | -0.020 |
back | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
kin | +0.052 |
pron | +0.048 |
uren | +0.046 |
ae | +0.043 |
omo | +0.043 |
Neg logit contributions | |
aback | -0.014 |
closer | -0.013 |
fired | -0.012 |
home | -0.011 |
revenge | -0.011 |
Token | make |
Token ID | 787 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.023 |
omo | +0.020 |
ae | +0.020 |
Neg logit contributions | |
aback | -0.019 |
closer | -0.017 |
fired | -0.017 |
away | -0.017 |
home | -0.016 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
kin | +0.014 |
pron | +0.013 |
lf | +0.011 |
uren | +0.011 |
omo | +0.011 |
Neg logit contributions | |
aback | -0.018 |
fired | -0.016 |
closer | -0.016 |
revenge | -0.015 |
nearer | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
kin | +0.070 |
pron | +0.065 |
uren | +0.061 |
omo | +0.055 |
lf | +0.054 |
Neg logit contributions | |
aback | -0.055 |
closer | -0.049 |
fired | -0.048 |
away | -0.045 |
home | -0.045 |
Token | different |
Token ID | 1180 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
kin | +0.045 |
pron | +0.042 |
uren | +0.039 |
lf | +0.036 |
omo | +0.036 |
Neg logit contributions | |
aback | -0.037 |
fired | -0.033 |
closer | -0.032 |
revenge | -0.030 |
away | -0.029 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.98e+00 |
Pos logit contributions | |
kin | +0.049 |
pron | +0.044 |
uren | +0.040 |
omo | +0.034 |
lf | +0.034 |
Neg logit contributions | |
aback | -0.076 |
closer | -0.070 |
fired | -0.069 |
away | -0.066 |
revenge | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
kin | +0.168 |
pron | +0.168 |
uren | +0.166 |
ae | +0.147 |
Adam | +0.144 |
Neg logit contributions | |
aback | -0.083 |
closer | -0.083 |
back | -0.079 |
away | -0.079 |
home | -0.076 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
kin | +0.024 |
pron | +0.022 |
uren | +0.019 |
ae | +0.017 |
addy | +0.016 |
Neg logit contributions | |
aback | -0.041 |
closer | -0.039 |
away | -0.037 |
fired | -0.037 |
revenge | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
pron | +0.215 |
kin | +0.211 |
uren | +0.211 |
ae | +0.187 |
omo | +0.186 |
Neg logit contributions | |
aback | -0.080 |
away | -0.077 |
closer | -0.076 |
back | -0.073 |
home | -0.072 |
Token | but |
Token ID | 475 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
kin | +0.127 |
pron | +0.118 |
uren | +0.110 |
ae | +0.105 |
addy | +0.100 |
Neg logit contributions | |
closer | -0.087 |
aback | -0.078 |
away | -0.073 |
revenge | -0.069 |
back | -0.068 |
Token | their |
Token ID | 511 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
kin | +0.030 |
pron | +0.028 |
uren | +0.026 |
lf | +0.023 |
Adam | +0.022 |
Neg logit contributions | |
aback | -0.031 |
closer | -0.030 |
fired | -0.028 |
away | -0.027 |
home | -0.027 |
Token | favorite |
Token ID | 4004 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
kin | +0.063 |
pron | +0.058 |
uren | +0.056 |
ae | +0.050 |
Adam | +0.049 |
Neg logit contributions | |
aback | -0.043 |
home | -0.043 |
closer | -0.042 |
away | -0.041 |
revenge | -0.040 |
Token | ones |
Token ID | 3392 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
kin | +0.049 |
pron | +0.046 |
uren | +0.043 |
omo | +0.038 |
Adam | +0.038 |
Neg logit contributions | |
aback | -0.040 |
closer | -0.037 |
fired | -0.036 |
away | -0.034 |
home | -0.034 |
Token | trucks |
Token ID | 13960 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.022 |
ae | +0.019 |
omo | +0.019 |
Neg logit contributions | |
aback | -0.022 |
closer | -0.021 |
fired | -0.020 |
away | -0.019 |
revenge | -0.019 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
kin | +0.090 |
pron | +0.086 |
uren | +0.082 |
omo | +0.074 |
ae | +0.072 |
Neg logit contributions | |
aback | -0.058 |
closer | -0.053 |
fired | -0.051 |
away | -0.051 |
home | -0.049 |
Token | different |
Token ID | 1180 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
kin | +0.036 |
pron | +0.033 |
uren | +0.031 |
lf | +0.028 |
omo | +0.028 |
Neg logit contributions | |
aback | -0.029 |
fired | -0.026 |
closer | -0.025 |
away | -0.023 |
revenge | -0.023 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
kin | +0.053 |
pron | +0.048 |
uren | +0.044 |
omo | +0.039 |
lf | +0.039 |
Neg logit contributions | |
aback | -0.070 |
closer | -0.064 |
fired | -0.063 |
revenge | -0.059 |
away | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
kin | +0.183 |
uren | +0.181 |
pron | +0.179 |
majesty | +0.160 |
ae | +0.160 |
Neg logit contributions | |
closer | -0.071 |
away | -0.067 |
aback | -0.066 |
back | -0.064 |
home | -0.063 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
kin | +0.020 |
pron | +0.018 |
uren | +0.016 |
ae | +0.014 |
addy | +0.013 |
Neg logit contributions | |
aback | -0.034 |
closer | -0.032 |
away | -0.031 |
fired | -0.031 |
revenge | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
pron | +0.215 |
uren | +0.214 |
kin | +0.214 |
omo | +0.189 |
ae | +0.188 |
Neg logit contributions | |
away | -0.077 |
aback | -0.076 |
closer | -0.074 |
home | -0.072 |
back | -0.070 |
Token | Ben |
Token ID | 3932 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
kin | +0.003 |
pron | +0.003 |
lf | +0.003 |
bridge | +0.003 |
uren | +0.003 |
Neg logit contributions | |
aback | -0.002 |
closer | -0.002 |
home | -0.002 |
fired | -0.002 |
revenge | -0.002 |
Token | likes |
Token ID | 7832 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.005 |
uren | +0.004 |
scalp | +0.004 |
ae | +0.004 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
fired | -0.004 |
back | -0.003 |
away | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
kin | +0.019 |
pron | +0.017 |
uren | +0.017 |
omo | +0.015 |
ae | +0.015 |
Neg logit contributions | |
aback | -0.005 |
closer | -0.004 |
fired | -0.004 |
home | -0.004 |
away | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
kin | +0.011 |
pron | +0.010 |
uren | +0.010 |
ae | +0.009 |
omo | +0.009 |
Neg logit contributions | |
aback | -0.008 |
closer | -0.008 |
fired | -0.007 |
away | -0.007 |
revenge | -0.007 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
kin | +0.013 |
pron | +0.012 |
uren | +0.011 |
lf | +0.011 |
omo | +0.010 |
Neg logit contributions | |
aback | -0.018 |
fired | -0.016 |
closer | -0.016 |
revenge | -0.015 |
nearer | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
kin | +0.075 |
pron | +0.071 |
uren | +0.067 |
omo | +0.059 |
ae | +0.059 |
Neg logit contributions | |
aback | -0.055 |
closer | -0.050 |
fired | -0.049 |
away | -0.047 |
home | -0.047 |
Token | different |
Token ID | 1180 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
kin | +0.042 |
pron | +0.039 |
uren | +0.037 |
lf | +0.034 |
omo | +0.033 |
Neg logit contributions | |
aback | -0.036 |
fired | -0.032 |
closer | -0.031 |
revenge | -0.029 |
away | -0.029 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
kin | +0.047 |
pron | +0.042 |
uren | +0.038 |
omo | +0.032 |
lf | +0.032 |
Neg logit contributions | |
aback | -0.070 |
closer | -0.064 |
fired | -0.064 |
away | -0.061 |
revenge | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
uren | +0.181 |
pron | +0.180 |
kin | +0.180 |
majesty | +0.161 |
ae | +0.160 |
Neg logit contributions | |
closer | -0.070 |
back | -0.068 |
away | -0.067 |
aback | -0.066 |
home | -0.065 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
kin | +0.020 |
pron | +0.018 |
uren | +0.015 |
ae | +0.013 |
omo | +0.012 |
Neg logit contributions | |
aback | -0.037 |
closer | -0.035 |
fired | -0.033 |
away | -0.033 |
revenge | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
pron | +0.222 |
uren | +0.220 |
kin | +0.216 |
ae | +0.194 |
omo | +0.191 |
Neg logit contributions | |
away | -0.071 |
aback | -0.070 |
closer | -0.069 |
back | -0.067 |
home | -0.066 |
Token | They |
Token ID | 1119 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
kin | +0.001 |
pron | +0.001 |
uren | +0.000 |
omo | +0.000 |
lf | +0.000 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
fired | -0.001 |
away | -0.001 |
revenge | -0.000 |
Token | make |
Token ID | 787 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
kin | +0.089 |
pron | +0.084 |
uren | +0.079 |
ae | +0.077 |
addy | +0.073 |
Neg logit contributions | |
closer | -0.052 |
away | -0.049 |
aback | -0.048 |
back | -0.045 |
home | -0.043 |
Token | sounds |
Token ID | 5238 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
kin | +0.092 |
pron | +0.085 |
uren | +0.078 |
ae | +0.071 |
omo | +0.071 |
Neg logit contributions | |
closer | -0.055 |
aback | -0.054 |
away | -0.050 |
home | -0.049 |
back | -0.048 |
Token | like |
Token ID | 588 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
kin | +0.143 |
pron | +0.136 |
uren | +0.134 |
ae | +0.128 |
addy | +0.126 |
Neg logit contributions | |
closer | -0.065 |
back | -0.055 |
away | -0.050 |
down | -0.047 |
more | -0.047 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
pron | +0.059 |
kin | +0.059 |
uren | +0.052 |
ae | +0.050 |
omo | +0.049 |
Neg logit contributions | |
aback | -0.038 |
away | -0.035 |
closer | -0.034 |
back | -0.032 |
fired | -0.032 |
Token | of |
Token ID | 286 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
kin | +0.065 |
pron | +0.062 |
uren | +0.058 |
omo | +0.053 |
ae | +0.052 |
Neg logit contributions | |
aback | -0.043 |
closer | -0.039 |
away | -0.037 |
fired | -0.037 |
home | -0.036 |
Token | different |
Token ID | 1180 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
kin | +0.035 |
pron | +0.033 |
uren | +0.030 |
lf | +0.028 |
omo | +0.027 |
Neg logit contributions | |
aback | -0.030 |
closer | -0.026 |
fired | -0.026 |
revenge | -0.024 |
away | -0.024 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
kin | +0.052 |
pron | +0.048 |
uren | +0.044 |
omo | +0.037 |
lf | +0.037 |
Neg logit contributions | |
aback | -0.064 |
closer | -0.058 |
fired | -0.057 |
away | -0.055 |
home | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
kin | +0.167 |
pron | +0.166 |
uren | +0.164 |
ae | +0.144 |
omo | +0.142 |
Neg logit contributions | |
aback | -0.086 |
closer | -0.085 |
away | -0.083 |
back | -0.082 |
home | -0.079 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
kin | +0.015 |
pron | +0.014 |
uren | +0.011 |
ae | +0.010 |
addy | +0.009 |
Neg logit contributions | |
aback | -0.025 |
closer | -0.023 |
fired | -0.023 |
away | -0.022 |
home | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
pron | +0.217 |
kin | +0.213 |
uren | +0.212 |
omo | +0.189 |
ae | +0.188 |
Neg logit contributions | |
aback | -0.078 |
away | -0.076 |
closer | -0.074 |
home | -0.072 |
back | -0.072 |
Token | He |
Token ID | 679 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.007 |
fired | +0.007 |
away | +0.007 |
revenge | +0.007 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.007 |
uren | -0.006 |
omo | -0.006 |
lf | -0.005 |
Token | makes |
Token ID | 1838 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
kin | +0.043 |
pron | +0.041 |
uren | +0.036 |
ae | +0.035 |
omo | +0.033 |
Neg logit contributions | |
closer | -0.029 |
aback | -0.028 |
away | -0.027 |
back | -0.026 |
fired | -0.025 |
Token | them |
Token ID | 606 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
kin | +0.099 |
pron | +0.092 |
uren | +0.083 |
ae | +0.079 |
omo | +0.078 |
Neg logit contributions | |
closer | -0.052 |
aback | -0.051 |
away | -0.047 |
home | -0.046 |
back | -0.045 |
Token | go |
Token ID | 467 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
kin | +0.017 |
pron | +0.016 |
uren | +0.015 |
ae | +0.013 |
lf | +0.013 |
Neg logit contributions | |
closer | -0.013 |
aback | -0.013 |
away | -0.012 |
home | -0.012 |
fired | -0.011 |
Token | skirts |
Token ID | 42370 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.020 |
uren | +0.018 |
Adam | +0.016 |
ae | +0.016 |
Neg logit contributions | |
aback | -0.030 |
closer | -0.028 |
away | -0.027 |
fired | -0.027 |
home | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
kin | +0.102 |
pron | +0.098 |
uren | +0.097 |
omo | +0.089 |
Adam | +0.089 |
Neg logit contributions | |
aback | -0.058 |
closer | -0.056 |
away | -0.055 |
home | -0.054 |
back | -0.052 |
Token | different |
Token ID | 1180 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
kin | +0.063 |
pron | +0.057 |
uren | +0.055 |
ae | +0.050 |
omo | +0.050 |
Neg logit contributions | |
aback | -0.055 |
closer | -0.052 |
away | -0.050 |
home | -0.050 |
back | -0.047 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
kin | +0.049 |
pron | +0.046 |
uren | +0.042 |
Adam | +0.035 |
omo | +0.035 |
Neg logit contributions | |
aback | -0.075 |
closer | -0.069 |
away | -0.068 |
fired | -0.067 |
home | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
uren | +0.161 |
kin | +0.161 |
pron | +0.159 |
Adam | +0.143 |
ae | +0.141 |
Neg logit contributions | |
aback | -0.084 |
closer | -0.080 |
home | -0.077 |
away | -0.077 |
back | -0.075 |
Token | patterns |
Token ID | 7572 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
kin | +0.023 |
pron | +0.022 |
uren | +0.020 |
Adam | +0.018 |
ae | +0.018 |
Neg logit contributions | |
aback | -0.030 |
closer | -0.028 |
away | -0.027 |
home | -0.027 |
fired | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
kin | +0.187 |
pron | +0.185 |
uren | +0.181 |
omo | +0.164 |
Adam | +0.160 |
Neg logit contributions | |
aback | -0.105 |
closer | -0.099 |
away | -0.094 |
home | -0.091 |
fired | -0.089 |
Token | She |
Token ID | 1375 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
aback | +0.003 |
closer | +0.003 |
home | +0.003 |
fired | +0.003 |
back | +0.003 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.004 |
uren | -0.004 |
lf | -0.004 |
bridge | -0.004 |
Token | liked |
Token ID | 8288 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
kin | +0.053 |
pron | +0.050 |
uren | +0.049 |
ities | +0.045 |
ae | +0.045 |
Neg logit contributions | |
closer | -0.037 |
back | -0.034 |
aback | -0.034 |
fired | -0.033 |
away | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
kin | +0.035 |
pron | +0.031 |
uren | +0.031 |
omo | +0.029 |
ae | +0.029 |
Neg logit contributions | |
closer | -0.005 |
aback | -0.004 |
home | -0.004 |
back | -0.003 |
away | -0.003 |
Token | spin |
Token ID | 7906 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.025 |
uren | +0.025 |
omo | +0.024 |
Adam | +0.024 |
Neg logit contributions | |
closer | -0.024 |
away | -0.023 |
aback | -0.022 |
back | -0.021 |
home | -0.021 |
Token | We |
Token ID | 775 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
kin | +0.016 |
pron | +0.016 |
uren | +0.013 |
lf | +0.013 |
ae | +0.012 |
Neg logit contributions | |
aback | -0.014 |
closer | -0.013 |
fired | -0.012 |
revenge | -0.012 |
away | -0.012 |
Token | have |
Token ID | 423 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
kin | +0.035 |
pron | +0.034 |
uren | +0.032 |
lf | +0.029 |
ae | +0.028 |
Neg logit contributions | |
aback | -0.031 |
closer | -0.029 |
away | -0.028 |
fired | -0.028 |
revenge | -0.027 |
Token | different |
Token ID | 1180 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
aback | +0.019 |
closer | +0.016 |
fired | +0.016 |
home | +0.015 |
away | +0.015 |
Neg logit contributions | |
kin | -0.048 |
pron | -0.045 |
uren | -0.043 |
lf | -0.040 |
omo | -0.040 |
Token | likes |
Token ID | 7832 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
kin | +0.047 |
pron | +0.045 |
uren | +0.042 |
ae | +0.036 |
omo | +0.036 |
Neg logit contributions | |
aback | -0.049 |
closer | -0.045 |
fired | -0.044 |
away | -0.044 |
home | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
kin | +0.049 |
pron | +0.045 |
uren | +0.042 |
omo | +0.038 |
lf | +0.038 |
Neg logit contributions | |
aback | -0.036 |
closer | -0.032 |
fired | -0.032 |
away | -0.030 |
home | -0.030 |
Token | disl |
Token ID | 19621 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
kin | +0.034 |
pron | +0.032 |
uren | +0.030 |
omo | +0.027 |
ae | +0.026 |
Neg logit contributions | |
aback | -0.027 |
closer | -0.025 |
fired | -0.025 |
away | -0.024 |
revenge | -0.024 |
Token | ikes |
Token ID | 7938 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
kin | +0.155 |
pron | +0.143 |
uren | +0.131 |
ma | +0.112 |
omo | +0.110 |
Neg logit contributions | |
aback | -0.150 |
closer | -0.132 |
fired | -0.131 |
revenge | -0.126 |
beh | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
kin | +0.032 |
pron | +0.030 |
uren | +0.029 |
omo | +0.026 |
lf | +0.026 |
Neg logit contributions | |
aback | -0.022 |
closer | -0.020 |
away | -0.019 |
fired | -0.019 |
home | -0.018 |
Token | We |
Token ID | 775 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
kin | +0.012 |
pron | +0.011 |
uren | +0.009 |
lf | +0.009 |
ae | +0.008 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.010 |
fired | -0.010 |
away | -0.009 |
revenge | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | -8.12e-01 |
Pos logit contributions | |
kin | +0.038 |
pron | +0.036 |
uren | +0.034 |
lf | +0.031 |
ae | +0.030 |
Neg logit contributions | |
aback | -0.034 |
closer | -0.031 |
away | -0.030 |
fired | -0.030 |
revenge | -0.029 |
Token | be |
Token ID | 307 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.019 |
uren | +0.019 |
ae | +0.016 |
Adam | +0.016 |
Neg logit contributions | |
closer | -0.015 |
aback | -0.014 |
away | -0.014 |
home | -0.013 |
revenge | -0.013 |
Token | They |
Token ID | 1119 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
kin | +0.007 |
pron | +0.007 |
uren | +0.006 |
lf | +0.006 |
ae | +0.005 |
Neg logit contributions | |
aback | -0.005 |
closer | -0.005 |
fired | -0.005 |
home | -0.004 |
revenge | -0.004 |
Token | can |
Token ID | 460 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
kin | +0.085 |
pron | +0.082 |
uren | +0.078 |
ae | +0.072 |
omo | +0.072 |
Neg logit contributions | |
closer | -0.049 |
away | -0.047 |
aback | -0.045 |
back | -0.043 |
home | -0.039 |
Token | make |
Token ID | 787 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
kin | +0.023 |
pron | +0.021 |
uren | +0.020 |
ae | +0.017 |
omo | +0.017 |
Neg logit contributions | |
closer | -0.017 |
aback | -0.016 |
away | -0.015 |
home | -0.014 |
fired | -0.014 |
Token | towers |
Token ID | 18028 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
kin | +0.072 |
pron | +0.068 |
uren | +0.064 |
omo | +0.057 |
lf | +0.056 |
Neg logit contributions | |
aback | -0.050 |
closer | -0.047 |
fired | -0.044 |
away | -0.043 |
home | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -3.66e+00 |
Pos logit contributions | |
kin | +0.105 |
pron | +0.100 |
uren | +0.097 |
omo | +0.084 |
ae | +0.083 |
Neg logit contributions | |
aback | -0.074 |
closer | -0.072 |
away | -0.067 |
fired | -0.065 |
home | -0.065 |
Token | bridges |
Token ID | 19432 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
kin | +0.084 |
pron | +0.077 |
uren | +0.073 |
ae | +0.064 |
omo | +0.064 |
Neg logit contributions | |
aback | -0.077 |
closer | -0.077 |
away | -0.070 |
fired | -0.068 |
home | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
kin | +0.181 |
pron | +0.178 |
uren | +0.171 |
omo | +0.149 |
ae | +0.147 |
Neg logit contributions | |
aback | -0.116 |
closer | -0.110 |
away | -0.105 |
fired | -0.102 |
home | -0.101 |
Token | houses |
Token ID | 7777 |
Feature activation | -4.31e+00 |
Pos logit contributions | |
kin | +0.097 |
pron | +0.090 |
uren | +0.086 |
omo | +0.076 |
ae | +0.075 |
Neg logit contributions | |
closer | -0.082 |
aback | -0.081 |
away | -0.075 |
fired | -0.072 |
back | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
kin | +0.119 |
pron | +0.115 |
uren | +0.110 |
omo | +0.099 |
addy | +0.097 |
Neg logit contributions | |
aback | -0.069 |
closer | -0.066 |
away | -0.063 |
home | -0.060 |
fired | -0.060 |
Token | more |
Token ID | 517 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.026 |
uren | +0.023 |
lf | +0.022 |
moons | +0.022 |
Neg logit contributions | |
aback | -0.037 |
fired | -0.032 |
closer | -0.031 |
revenge | -0.030 |
away | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.023 |
omo | +0.020 |
ae | +0.020 |
Neg logit contributions | |
aback | -0.020 |
closer | -0.019 |
fired | -0.018 |
away | -0.017 |
home | -0.017 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
kin | +0.015 |
pron | +0.013 |
lf | +0.012 |
uren | +0.011 |
omo | +0.011 |
Neg logit contributions | |
aback | -0.021 |
fired | -0.019 |
closer | -0.018 |
revenge | -0.017 |
nearer | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
kin | +0.068 |
pron | +0.064 |
uren | +0.059 |
omo | +0.053 |
lf | +0.052 |
Neg logit contributions | |
aback | -0.056 |
closer | -0.050 |
fired | -0.050 |
away | -0.047 |
home | -0.047 |
Token | different |
Token ID | 1180 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
kin | +0.044 |
pron | +0.041 |
uren | +0.038 |
lf | +0.035 |
omo | +0.035 |
Neg logit contributions | |
aback | -0.036 |
fired | -0.032 |
closer | -0.032 |
revenge | -0.029 |
away | -0.029 |
Token | colors |
Token ID | 7577 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
kin | +0.048 |
pron | +0.043 |
uren | +0.039 |
omo | +0.033 |
lf | +0.033 |
Neg logit contributions | |
aback | -0.077 |
closer | -0.072 |
fired | -0.071 |
away | -0.067 |
revenge | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
uren | +0.166 |
pron | +0.166 |
kin | +0.166 |
ae | +0.145 |
Adam | +0.144 |
Neg logit contributions | |
aback | -0.081 |
closer | -0.080 |
away | -0.077 |
back | -0.075 |
home | -0.074 |
Token | sizes |
Token ID | 10620 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.019 |
uren | +0.017 |
ae | +0.014 |
addy | +0.014 |
Neg logit contributions | |
aback | -0.036 |
closer | -0.034 |
away | -0.032 |
fired | -0.032 |
revenge | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
pron | +0.211 |
uren | +0.209 |
kin | +0.207 |
ae | +0.183 |
Adam | +0.183 |
Neg logit contributions | |
aback | -0.079 |
away | -0.077 |
closer | -0.075 |
home | -0.073 |
back | -0.070 |
Token | They |
Token ID | 1119 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
home | +0.005 |
fired | +0.004 |
away | +0.004 |
Neg logit contributions | |
kin | -0.006 |
pron | -0.005 |
uren | -0.005 |
lf | -0.005 |
bridge | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
kin | +0.094 |
pron | +0.089 |
uren | +0.085 |
ae | +0.082 |
addy | +0.078 |
Neg logit contributions | |
closer | -0.050 |
away | -0.048 |
aback | -0.046 |
back | -0.043 |
home | -0.040 |
Token | roads |
Token ID | 9725 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
kin | +0.096 |
pron | +0.089 |
uren | +0.082 |
ae | +0.075 |
omo | +0.075 |
Neg logit contributions | |
closer | -0.060 |
aback | -0.060 |
away | -0.055 |
home | -0.053 |
back | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
kin | +0.111 |
pron | +0.110 |
uren | +0.104 |
omo | +0.092 |
ae | +0.090 |
Neg logit contributions | |
aback | -0.082 |
closer | -0.080 |
away | -0.076 |
back | -0.072 |
home | -0.071 |
Token | time |
Token ID | 640 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
closer | +0.025 |
aback | +0.025 |
home | +0.024 |
away | +0.024 |
back | +0.023 |
Neg logit contributions | |
kin | -0.018 |
uren | -0.016 |
pron | -0.015 |
majesty | -0.013 |
scalp | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
aback | +0.033 |
closer | +0.026 |
fired | +0.025 |
away | +0.022 |
revenge | +0.021 |
Neg logit contributions | |
kin | -0.103 |
pron | -0.098 |
uren | -0.093 |
omo | -0.087 |
lf | -0.087 |
Token | Lily |
Token ID | 20037 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
aback | +0.025 |
closer | +0.022 |
fired | +0.022 |
away | +0.021 |
home | +0.021 |
Neg logit contributions | |
kin | -0.024 |
pron | -0.022 |
uren | -0.020 |
omo | -0.018 |
lf | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.011 |
fired | +0.010 |
revenge | +0.009 |
away | +0.009 |
Neg logit contributions | |
kin | -0.029 |
pron | -0.027 |
uren | -0.026 |
omo | -0.024 |
lf | -0.024 |
Token | go |
Token ID | 467 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
pron | +0.025 |
kin | +0.025 |
uren | +0.023 |
moons | +0.022 |
utes | +0.021 |
Neg logit contributions | |
away | -0.013 |
home | -0.012 |
closer | -0.012 |
aback | -0.012 |
back | -0.011 |
Token | back |
Token ID | 736 |
Feature activation | +4.90e+00 |
Pos logit contributions | |
aback | +0.044 |
beh | +0.031 |
fired | +0.029 |
revenge | +0.027 |
closer | +0.026 |
Neg logit contributions | |
kin | -0.131 |
pron | -0.126 |
uren | -0.121 |
addy | -0.115 |
stand | -0.115 |
Token | inside |
Token ID | 2641 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
aback | +0.072 |
beh | +0.064 |
revenge | +0.055 |
oc | +0.054 |
smart | +0.053 |
Neg logit contributions | |
kin | -0.125 |
pron | -0.114 |
uren | -0.113 |
Ben | -0.111 |
Adam | -0.110 |
Token | , |
Token ID | 11 |
Feature activation | -9.73e-01 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
home | +0.005 |
fired | +0.004 |
away | +0.004 |
Neg logit contributions | |
kin | -0.009 |
pron | -0.009 |
uren | -0.008 |
bridge | -0.008 |
omo | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.023 |
uren | +0.022 |
ae | +0.021 |
inner | +0.021 |
Neg logit contributions | |
closer | -0.018 |
home | -0.017 |
aback | -0.017 |
away | -0.016 |
back | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
kin | +0.001 |
pron | +0.001 |
uren | +0.001 |
omo | +0.001 |
lf | +0.001 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
fired | -0.001 |
away | -0.001 |
home | -0.001 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
aback | +0.025 |
closer | +0.024 |
fired | +0.023 |
away | +0.022 |
home | +0.022 |
Neg logit contributions | |
kin | -0.026 |
pron | -0.024 |
uren | -0.023 |
omo | -0.020 |
lf | -0.020 |
Token | followed |
Token ID | 3940 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.004 |
fired | +0.004 |
away | +0.004 |
revenge | +0.004 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.005 |
uren | -0.004 |
Adam | -0.004 |
lf | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
aback | +0.016 |
fired | +0.015 |
closer | +0.013 |
beh | +0.013 |
medical | +0.013 |
Neg logit contributions | |
kin | -0.016 |
pron | -0.014 |
uren | -0.013 |
lf | -0.012 |
ae | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
aback | +0.028 |
fired | +0.024 |
beh | +0.023 |
closer | +0.023 |
smart | +0.023 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.014 |
uren | -0.013 |
scalp | -0.012 |
omo | -0.012 |
Token | When |
Token ID | 1649 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
aback | +0.003 |
closer | +0.003 |
fired | +0.002 |
home | +0.002 |
away | +0.002 |
Neg logit contributions | |
kin | -0.004 |
pron | -0.004 |
uren | -0.003 |
lf | -0.003 |
moons | -0.003 |
Token | they |
Token ID | 484 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
aback | +0.025 |
closer | +0.023 |
fired | +0.023 |
home | +0.022 |
away | +0.022 |
Neg logit contributions | |
kin | -0.022 |
pron | -0.021 |
uren | -0.019 |
omo | -0.017 |
lf | -0.016 |
Token | got |
Token ID | 1392 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
kin | +0.034 |
pron | +0.030 |
uren | +0.029 |
lf | +0.025 |
omo | +0.025 |
Neg logit contributions | |
aback | -0.032 |
fired | -0.029 |
closer | -0.028 |
revenge | -0.027 |
beh | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
oc | +0.100 |
aback | +0.085 |
smart | +0.080 |
vered | +0.077 |
beh | +0.075 |
Neg logit contributions | |
kin | -0.093 |
Ben | -0.088 |
pron | -0.084 |
not | -0.079 |
omo | -0.075 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
aback | +0.006 |
closer | +0.005 |
fired | +0.005 |
away | +0.005 |
revenge | +0.005 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.006 |
uren | -0.006 |
omo | -0.005 |
lf | -0.005 |
Token | stable |
Token ID | 8245 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
aback | +0.004 |
fired | +0.003 |
closer | +0.003 |
revenge | +0.003 |
away | +0.003 |
Neg logit contributions | |
kin | -0.004 |
pron | -0.003 |
uren | -0.003 |
omo | -0.003 |
lf | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
aback | +0.015 |
closer | +0.013 |
fired | +0.013 |
home | +0.012 |
away | +0.012 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.022 |
uren | -0.021 |
omo | -0.019 |
lf | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
aback | +0.003 |
closer | +0.003 |
fired | +0.002 |
home | +0.002 |
away | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
omo | -0.002 |
lf | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
aback | +0.036 |
fired | +0.032 |
closer | +0.032 |
revenge | +0.030 |
home | +0.029 |
Neg logit contributions | |
kin | -0.039 |
pron | -0.035 |
uren | -0.032 |
omo | -0.029 |
lf | -0.029 |
Token | Tom |
Token ID | 4186 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
aback | +0.004 |
closer | +0.004 |
fired | +0.004 |
revenge | +0.003 |
home | +0.003 |
Neg logit contributions | |
kin | -0.006 |
pron | -0.006 |
uren | -0.005 |
lf | -0.005 |
bee | -0.005 |
Token | screamed |
Token ID | 25421 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
aback | +0.016 |
closer | +0.015 |
away | +0.014 |
fired | +0.014 |
back | +0.013 |
Neg logit contributions | |
kin | -0.025 |
pron | -0.024 |
uren | -0.022 |
omo | -0.021 |
Adam | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.008 |
fired | +0.007 |
away | +0.007 |
home | +0.007 |
Neg logit contributions | |
kin | -0.009 |
pron | -0.008 |
uren | -0.008 |
omo | -0.007 |
lf | -0.007 |
Token | pulled |
Token ID | 5954 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
aback | +0.011 |
closer | +0.011 |
away | +0.010 |
fired | +0.010 |
revenge | +0.009 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.016 |
uren | -0.015 |
ae | -0.013 |
Adam | -0.013 |
Token | back |
Token ID | 736 |
Feature activation | +5.22e+00 |
Pos logit contributions | |
aback | +0.022 |
fired | +0.021 |
beh | +0.020 |
medical | +0.019 |
revenge | +0.019 |
Neg logit contributions | |
kin | -0.021 |
Ben | -0.017 |
pron | -0.017 |
uren | -0.016 |
ia | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
aback | +0.137 |
beh | +0.125 |
medical | +0.123 |
fired | +0.120 |
unst | +0.120 |
Neg logit contributions | |
Ben | -0.068 |
kin | -0.068 |
ia | -0.058 |
Anna | -0.054 |
Tom | -0.053 |
Token | hand |
Token ID | 1021 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
aback | +0.022 |
closer | +0.021 |
fired | +0.020 |
away | +0.019 |
revenge | +0.019 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
uren | -0.020 |
lf | -0.017 |
omo | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
aback | +0.090 |
fired | +0.084 |
revenge | +0.079 |
beh | +0.076 |
medical | +0.076 |
Neg logit contributions | |
kin | -0.065 |
pron | -0.054 |
uren | -0.045 |
scalp | -0.045 |
stand | -0.045 |
Token | It |
Token ID | 632 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aback | +0.009 |
fired | +0.008 |
closer | +0.008 |
revenge | +0.007 |
home | +0.007 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.012 |
moons | -0.011 |
lf | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
aback | +0.026 |
fired | +0.023 |
closer | +0.022 |
home | +0.021 |
revenge | +0.021 |
Neg logit contributions | |
kin | -0.029 |
pron | -0.026 |
uren | -0.023 |
omo | -0.022 |
lf | -0.021 |
Token | when |
Token ID | 618 |
Feature activation | +8.79e-01 |
Pos logit contributions | |
kin | +0.023 |
pron | +0.022 |
uren | +0.020 |
lf | +0.018 |
omo | +0.017 |
Neg logit contributions | |
aback | -0.023 |
fired | -0.021 |
closer | -0.021 |
revenge | -0.019 |
away | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
aback | +0.022 |
fired | +0.020 |
closer | +0.019 |
revenge | +0.018 |
away | +0.018 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.016 |
uren | -0.015 |
lf | -0.013 |
omo | -0.012 |
Token | princess |
Token ID | 21752 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
kin | +0.009 |
pron | +0.008 |
uren | +0.007 |
lf | +0.007 |
omo | +0.006 |
Neg logit contributions | |
aback | -0.009 |
fired | -0.008 |
closer | -0.008 |
away | -0.008 |
revenge | -0.008 |
Token | got |
Token ID | 1392 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.005 |
uren | +0.004 |
lf | +0.004 |
omo | +0.004 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
fired | -0.004 |
revenge | -0.004 |
away | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
oc | +0.076 |
aback | +0.074 |
fired | +0.065 |
beh | +0.063 |
smart | +0.061 |
Neg logit contributions | |
pron | -0.092 |
kin | -0.087 |
Avery | -0.074 |
uren | -0.067 |
ae | -0.066 |
Token | magnet |
Token ID | 19972 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
aback | +0.005 |
fired | +0.005 |
beh | +0.005 |
closer | +0.004 |
arling | +0.004 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.005 |
uren | -0.004 |
ceiling | -0.003 |
lf | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
aback | +0.092 |
fired | +0.080 |
closer | +0.079 |
revenge | +0.076 |
beh | +0.074 |
Neg logit contributions | |
kin | -0.099 |
pron | -0.092 |
uren | -0.082 |
lf | -0.077 |
moons | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
aback | +0.056 |
closer | +0.049 |
fired | +0.049 |
revenge | +0.047 |
beh | +0.046 |
Neg logit contributions | |
kin | -0.051 |
pron | -0.047 |
uren | -0.041 |
lf | -0.038 |
moons | -0.036 |
Token | fake |
Token ID | 8390 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.004 |
uren | +0.004 |
omo | +0.004 |
lf | +0.004 |
Neg logit contributions | |
aback | -0.003 |
closer | -0.003 |
fired | -0.003 |
away | -0.003 |
home | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
kin | +0.003 |
pron | +0.003 |
uren | +0.003 |
omo | +0.003 |
lf | +0.003 |
Neg logit contributions | |
aback | -0.003 |
closer | -0.002 |
fired | -0.002 |
away | -0.002 |
revenge | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
aback | +0.011 |
closer | +0.009 |
fired | +0.009 |
home | +0.009 |
away | +0.008 |
Neg logit contributions | |
kin | -0.015 |
pron | -0.014 |
uren | -0.012 |
lf | -0.012 |
omo | -0.011 |
Token | not |
Token ID | 407 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
kin | +0.043 |
pron | +0.040 |
uren | +0.035 |
omo | +0.031 |
lf | +0.028 |
Neg logit contributions | |
aback | -0.073 |
closer | -0.072 |
away | -0.068 |
fired | -0.068 |
home | -0.066 |
Token | know |
Token ID | 760 |
Feature activation | +7.35e-02 |
Pos logit contributions | |
aback | +0.012 |
closer | +0.011 |
fired | +0.011 |
away | +0.010 |
revenge | +0.010 |
Neg logit contributions | |
kin | -0.020 |
pron | -0.019 |
uren | -0.018 |
omo | -0.016 |
lf | -0.016 |
Token | how |
Token ID | 703 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
fired | +0.001 |
away | +0.001 |
home | +0.001 |
Neg logit contributions | |
kin | -0.002 |
pron | -0.002 |
uren | -0.002 |
omo | -0.001 |
Adam | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
aback | +0.033 |
closer | +0.026 |
fired | +0.026 |
revenge | +0.024 |
away | +0.024 |
Neg logit contributions | |
kin | -0.059 |
pron | -0.055 |
uren | -0.052 |
lf | -0.048 |
omo | -0.048 |
Token | go |
Token ID | 467 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
aback | +0.008 |
fired | +0.007 |
closer | +0.007 |
revenge | +0.006 |
unst | +0.006 |
Neg logit contributions | |
kin | -0.009 |
pron | -0.008 |
uren | -0.007 |
lf | -0.007 |
omo | -0.006 |
Token | back |
Token ID | 736 |
Feature activation | +5.11e+00 |
Pos logit contributions | |
aback | +0.082 |
beh | +0.069 |
vered | +0.066 |
revenge | +0.065 |
medical | +0.065 |
Neg logit contributions | |
kin | -0.078 |
line | -0.068 |
Ben | -0.062 |
pron | -0.061 |
stand | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
aback | +0.083 |
beh | +0.074 |
medical | +0.067 |
unst | +0.067 |
revenge | +0.063 |
Neg logit contributions | |
kin | -0.119 |
Ben | -0.109 |
uren | -0.106 |
ia | -0.104 |
Eric | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
aback | +0.000 |
closer | +0.000 |
fired | +0.000 |
away | +0.000 |
revenge | +0.000 |
Neg logit contributions | |
kin | -0.000 |
pron | -0.000 |
uren | -0.000 |
Adam | -0.000 |
omo | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
kin | +0.008 |
pron | +0.007 |
uren | +0.007 |
omo | +0.006 |
lf | +0.006 |
Neg logit contributions | |
aback | -0.008 |
closer | -0.007 |
fired | -0.007 |
away | -0.007 |
revenge | -0.007 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
aback | +0.017 |
closer | +0.016 |
fired | +0.016 |
away | +0.015 |
revenge | +0.015 |
Neg logit contributions | |
kin | -0.013 |
pron | -0.012 |
uren | -0.011 |
omo | -0.010 |
lf | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
aback | +0.040 |
fired | +0.035 |
closer | +0.034 |
revenge | +0.033 |
beh | +0.033 |
Neg logit contributions | |
kin | -0.043 |
pron | -0.037 |
uren | -0.037 |
lf | -0.032 |
ia | -0.032 |
Token | laugh |
Token ID | 6487 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.014 |
away | +0.013 |
home | +0.012 |
back | +0.012 |
Neg logit contributions | |
kin | -0.025 |
pron | -0.025 |
uren | -0.022 |
omo | -0.022 |
lf | -0.021 |
Token | or |
Token ID | 393 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
pron | +0.103 |
kin | +0.101 |
uren | +0.095 |
omo | +0.086 |
ae | +0.085 |
Neg logit contributions | |
aback | -0.054 |
closer | -0.054 |
away | -0.052 |
back | -0.049 |
home | -0.046 |
Token | scream |
Token ID | 8196 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
kin | +0.002 |
pron | +0.002 |
uren | +0.002 |
omo | +0.002 |
ae | +0.002 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
away | -0.001 |
fired | -0.001 |
revenge | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +8.19e-02 |
Pos logit contributions | |
kin | +0.037 |
pron | +0.035 |
uren | +0.032 |
omo | +0.029 |
lf | +0.029 |
Neg logit contributions | |
aback | -0.026 |
closer | -0.024 |
fired | -0.023 |
away | -0.022 |
home | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.001 |
fired | +0.001 |
home | +0.001 |
revenge | +0.001 |
Neg logit contributions | |
kin | -0.002 |
pron | -0.002 |
uren | -0.002 |
lf | -0.002 |
ae | -0.002 |
Token | looks |
Token ID | 3073 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
kin | +0.007 |
pron | +0.007 |
uren | +0.006 |
lf | +0.006 |
ae | +0.005 |
Neg logit contributions | |
aback | -0.005 |
closer | -0.005 |
away | -0.005 |
fired | -0.004 |
revenge | -0.004 |
Token | bored |
Token ID | 17533 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
aback | +0.010 |
fired | +0.009 |
closer | +0.009 |
revenge | +0.008 |
home | +0.008 |
Neg logit contributions | |
kin | -0.013 |
pron | -0.013 |
uren | -0.012 |
omo | -0.011 |
lf | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
kin | +0.071 |
pron | +0.067 |
uren | +0.063 |
omo | +0.056 |
ae | +0.056 |
Neg logit contributions | |
aback | -0.056 |
closer | -0.052 |
away | -0.050 |
fired | -0.048 |
home | -0.047 |
Token | mean |
Token ID | 1612 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.014 |
away | +0.012 |
fired | +0.012 |
revenge | +0.011 |
Neg logit contributions | |
kin | -0.026 |
pron | -0.024 |
uren | -0.023 |
lf | -0.021 |
ae | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
away | +0.001 |
fired | +0.001 |
home | +0.001 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.001 |
omo | -0.001 |
lf | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
aback | +0.004 |
closer | +0.003 |
fired | +0.003 |
revenge | +0.003 |
away | +0.003 |
Neg logit contributions | |
kin | -0.004 |
pron | -0.004 |
uren | -0.003 |
lf | -0.003 |
omo | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
kin | +0.016 |
pron | +0.015 |
uren | +0.014 |
lf | +0.012 |
omo | +0.012 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.016 |
away | -0.015 |
home | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
kin | +0.015 |
pron | +0.014 |
uren | +0.013 |
lf | +0.011 |
omo | +0.011 |
Neg logit contributions | |
aback | -0.012 |
closer | -0.011 |
fired | -0.011 |
away | -0.010 |
home | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
aback | +0.011 |
closer | +0.010 |
fired | +0.010 |
away | +0.010 |
home | +0.009 |
Neg logit contributions | |
kin | -0.013 |
pron | -0.012 |
uren | -0.011 |
lf | -0.010 |
moons | -0.010 |
Token | What |
Token ID | 2061 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
aback | +0.048 |
closer | +0.044 |
fired | +0.040 |
away | +0.039 |
revenge | +0.039 |
Neg logit contributions | |
kin | -0.059 |
pron | -0.055 |
uren | -0.052 |
omo | -0.048 |
lf | -0.048 |
Token | is |
Token ID | 318 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
aback | +0.022 |
closer | +0.021 |
fired | +0.020 |
revenge | +0.019 |
home | +0.018 |
Neg logit contributions | |
kin | -0.024 |
pron | -0.023 |
uren | -0.022 |
omo | -0.019 |
lf | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
kin | +0.025 |
pron | +0.023 |
uren | +0.021 |
lf | +0.019 |
Adam | +0.018 |
Neg logit contributions | |
aback | -0.025 |
fired | -0.022 |
closer | -0.021 |
away | -0.019 |
revenge | -0.019 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
aback | +0.031 |
closer | +0.028 |
fired | +0.027 |
away | +0.026 |
revenge | +0.026 |
Neg logit contributions | |
kin | -0.027 |
pron | -0.025 |
uren | -0.022 |
omo | -0.020 |
lf | -0.020 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
kin | +0.056 |
pron | +0.053 |
uren | +0.045 |
lf | +0.043 |
reflecting | +0.042 |
Neg logit contributions | |
aback | -0.052 |
closer | -0.050 |
home | -0.045 |
fired | -0.044 |
away | -0.044 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
kin | +0.041 |
pron | +0.038 |
uren | +0.035 |
omo | +0.033 |
ae | +0.033 |
Neg logit contributions | |
aback | -0.023 |
closer | -0.020 |
fired | -0.019 |
away | -0.018 |
home | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
kin | +0.000 |
pron | +0.000 |
uren | +0.000 |
ia | +0.000 |
Ben | +0.000 |
Neg logit contributions | |
aback | -0.000 |
fired | -0.000 |
closer | -0.000 |
revenge | -0.000 |
beh | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
kin | +0.027 |
pron | +0.025 |
uren | +0.023 |
lf | +0.022 |
omo | +0.021 |
Neg logit contributions | |
aback | -0.021 |
closer | -0.019 |
fired | -0.018 |
away | -0.016 |
home | -0.016 |
Token | angry |
Token ID | 7954 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
kin | +0.037 |
pron | +0.034 |
uren | +0.032 |
lf | +0.028 |
omo | +0.028 |
Neg logit contributions | |
aback | -0.032 |
closer | -0.029 |
fired | -0.028 |
away | -0.027 |
home | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
kin | +0.030 |
pron | +0.028 |
uren | +0.026 |
lf | +0.023 |
omo | +0.023 |
Neg logit contributions | |
aback | -0.024 |
closer | -0.021 |
fired | -0.021 |
away | -0.019 |
home | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
aback | +0.008 |
closer | +0.007 |
fired | +0.006 |
away | +0.006 |
home | +0.006 |
Neg logit contributions | |
kin | -0.011 |
pron | -0.010 |
uren | -0.009 |
lf | -0.008 |
ae | -0.008 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
aback | +0.009 |
closer | +0.008 |
fired | +0.008 |
away | +0.008 |
revenge | +0.008 |
Neg logit contributions | |
kin | -0.011 |
pron | -0.010 |
uren | -0.009 |
ae | -0.008 |
lf | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
aback | +0.029 |
fired | +0.025 |
beh | +0.024 |
oc | +0.023 |
arling | +0.023 |
Neg logit contributions | |
Ben | -0.035 |
kin | -0.034 |
pron | -0.033 |
ia | -0.031 |
uren | -0.031 |
Token | scare |
Token ID | 19437 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
aback | +0.017 |
fired | +0.015 |
closer | +0.014 |
arling | +0.014 |
nearer | +0.013 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.015 |
uren | -0.014 |
omo | -0.014 |
ia | -0.013 |
Token | them |
Token ID | 606 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
aback | +0.017 |
fired | +0.016 |
closer | +0.015 |
medical | +0.015 |
beh | +0.014 |
Neg logit contributions | |
kin | -0.009 |
uren | -0.008 |
Ben | -0.008 |
pron | -0.007 |
ia | -0.007 |
Token | again |
Token ID | 757 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
aback | +0.016 |
fired | +0.014 |
revenge | +0.013 |
closer | +0.013 |
medical | +0.013 |
Neg logit contributions | |
kin | -0.015 |
pron | -0.012 |
uren | -0.011 |
omo | -0.011 |
lf | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
aback | +0.073 |
fired | +0.063 |
closer | +0.061 |
revenge | +0.060 |
beh | +0.059 |
Neg logit contributions | |
kin | -0.055 |
pron | -0.045 |
uren | -0.041 |
omo | -0.039 |
ia | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
fired | +0.002 |
away | +0.002 |
home | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
lf | -0.003 |
ae | -0.002 |
Token | ran |
Token ID | 4966 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
kin | +0.002 |
pron | +0.001 |
uren | +0.001 |
lf | +0.001 |
Adam | +0.001 |
Neg logit contributions | |
aback | -0.001 |
closer | -0.001 |
fired | -0.001 |
away | -0.001 |
revenge | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
away | +0.002 |
home | +0.001 |
revenge | +0.001 |
Neg logit contributions | |
kin | -0.004 |
pron | -0.004 |
uren | -0.004 |
omo | -0.003 |
ae | -0.003 |
Token | boots |
Token ID | 14412 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
aback | +0.041 |
fired | +0.037 |
closer | +0.037 |
beh | +0.036 |
revenge | +0.036 |
Neg logit contributions | |
kin | -0.024 |
pron | -0.024 |
uren | -0.020 |
lf | -0.018 |
omo | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
kin | +0.092 |
pron | +0.085 |
uren | +0.082 |
omo | +0.076 |
majesty | +0.074 |
Neg logit contributions | |
aback | -0.056 |
closer | -0.050 |
away | -0.050 |
home | -0.049 |
fired | -0.046 |
Token | One |
Token ID | 1881 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
fired | +0.002 |
home | +0.002 |
revenge | +0.002 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
ae | -0.003 |
scalp | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
kin | +0.011 |
pron | +0.010 |
uren | +0.009 |
omo | +0.008 |
lf | +0.008 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.009 |
fired | -0.009 |
away | -0.009 |
revenge | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
aback | +0.046 |
fired | +0.040 |
closer | +0.040 |
beh | +0.038 |
revenge | +0.038 |
Neg logit contributions | |
kin | -0.042 |
pron | -0.037 |
uren | -0.034 |
omo | -0.032 |
lf | -0.032 |
Token | Tim |
Token ID | 5045 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.012 |
fired | +0.012 |
away | +0.011 |
revenge | +0.011 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.016 |
uren | -0.015 |
omo | -0.013 |
lf | -0.013 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
kin | +0.016 |
pron | +0.015 |
uren | +0.014 |
ae | +0.013 |
unison | +0.013 |
Neg logit contributions | |
aback | -0.008 |
fired | -0.008 |
closer | -0.007 |
home | -0.007 |
away | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
aback | +0.034 |
arling | +0.027 |
fired | +0.027 |
beh | +0.027 |
oc | +0.027 |
Neg logit contributions | |
pron | -0.039 |
kin | -0.036 |
Ben | -0.034 |
stand | -0.033 |
lf | -0.032 |
Token | be |
Token ID | 307 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
fired | +0.001 |
away | +0.001 |
home | +0.001 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.001 |
omo | -0.001 |
lf | -0.001 |
Token | just |
Token ID | 655 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
kin | +0.001 |
pron | +0.001 |
uren | +0.001 |
omo | +0.001 |
lf | +0.001 |
Neg logit contributions | |
aback | -0.001 |
fired | -0.001 |
closer | -0.001 |
revenge | -0.000 |
away | -0.000 |
Token | again |
Token ID | 757 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
kin | +0.018 |
pron | +0.018 |
uren | +0.016 |
omo | +0.015 |
Adam | +0.015 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.010 |
fired | -0.010 |
away | -0.010 |
home | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
aback | +0.042 |
closer | +0.038 |
fired | +0.037 |
revenge | +0.035 |
away | +0.034 |
Neg logit contributions | |
kin | -0.046 |
pron | -0.043 |
uren | -0.040 |
lf | -0.036 |
omo | -0.035 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
aback | +0.022 |
fired | +0.020 |
closer | +0.019 |
home | +0.019 |
revenge | +0.018 |
Neg logit contributions | |
kin | -0.028 |
pron | -0.026 |
uren | -0.022 |
lf | -0.021 |
bridge | -0.020 |
Token | Once |
Token ID | 7454 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
kin | +0.036 |
pron | +0.034 |
uren | +0.031 |
omo | +0.028 |
lf | +0.028 |
Neg logit contributions | |
aback | -0.029 |
closer | -0.026 |
fired | -0.025 |
home | -0.024 |
away | -0.024 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
kin | +0.016 |
pron | +0.015 |
uren | +0.014 |
scalp | +0.012 |
bridge | +0.012 |
Neg logit contributions | |
aback | -0.019 |
closer | -0.018 |
home | -0.018 |
fired | -0.017 |
away | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
kin | +0.093 |
pron | +0.089 |
uren | +0.088 |
omo | +0.080 |
majesty | +0.080 |
Neg logit contributions | |
closer | -0.033 |
aback | -0.032 |
away | -0.026 |
home | -0.026 |
back | -0.025 |
Token | time |
Token ID | 640 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
aback | +0.010 |
closer | +0.010 |
home | +0.009 |
away | +0.009 |
fired | +0.009 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.007 |
uren | -0.006 |
bridge | -0.006 |
moons | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
fired | +0.005 |
away | +0.004 |
revenge | +0.004 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.007 |
uren | -0.006 |
omo | -0.006 |
lf | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
kin | +0.018 |
pron | +0.016 |
uren | +0.015 |
omo | +0.013 |
lf | +0.013 |
Neg logit contributions | |
aback | -0.016 |
fired | -0.014 |
closer | -0.014 |
revenge | -0.013 |
away | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
kin | +0.063 |
pron | +0.059 |
uren | +0.056 |
omo | +0.050 |
lf | +0.050 |
Neg logit contributions | |
aback | -0.043 |
closer | -0.038 |
fired | -0.037 |
away | -0.034 |
home | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
aback | +0.009 |
closer | +0.008 |
fired | +0.008 |
home | +0.008 |
away | +0.007 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.016 |
uren | -0.015 |
lf | -0.013 |
omo | -0.013 |
Token | named |
Token ID | 3706 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
aback | +0.029 |
closer | +0.025 |
fired | +0.025 |
revenge | +0.024 |
nearer | +0.024 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
uren | -0.018 |
lf | -0.018 |
omo | -0.017 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
aback | +0.000 |
closer | +0.000 |
fired | +0.000 |
away | +0.000 |
home | +0.000 |
Neg logit contributions | |
kin | -0.000 |
pron | -0.000 |
uren | -0.000 |
lf | -0.000 |
omo | -0.000 |
Token | my |
Token ID | 1820 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
kin | +0.045 |
pron | +0.042 |
uren | +0.041 |
lf | +0.037 |
sheets | +0.037 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.015 |
away | -0.014 |
home | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
kin | +0.013 |
pron | +0.012 |
uren | +0.012 |
omo | +0.010 |
lf | +0.010 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.010 |
fired | -0.010 |
away | -0.009 |
revenge | -0.009 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
aback | +0.009 |
closer | +0.008 |
fired | +0.008 |
home | +0.007 |
away | +0.007 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.012 |
ae | -0.011 |
lf | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
kin | +0.032 |
pron | +0.030 |
uren | +0.029 |
ae | +0.026 |
lf | +0.026 |
Neg logit contributions | |
aback | -0.013 |
fired | -0.011 |
closer | -0.011 |
away | -0.010 |
home | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
kin | +0.007 |
pron | +0.007 |
uren | +0.007 |
unison | +0.006 |
ae | +0.006 |
Neg logit contributions | |
aback | -0.006 |
fired | -0.005 |
home | -0.005 |
away | -0.005 |
closer | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
kin | +0.036 |
pron | +0.034 |
uren | +0.031 |
omo | +0.029 |
lf | +0.029 |
Neg logit contributions | |
aback | -0.022 |
fired | -0.019 |
closer | -0.019 |
away | -0.017 |
revenge | -0.017 |
Token | poor |
Token ID | 3595 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
aback | +0.031 |
closer | +0.027 |
fired | +0.027 |
away | +0.025 |
revenge | +0.025 |
Neg logit contributions | |
kin | -0.039 |
pron | -0.036 |
uren | -0.034 |
omo | -0.031 |
lf | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
kin | +0.036 |
pron | +0.034 |
uren | +0.033 |
Adam | +0.029 |
bridge | +0.028 |
Neg logit contributions | |
aback | -0.025 |
home | -0.024 |
closer | -0.023 |
fired | -0.023 |
away | -0.022 |
Token | he |
Token ID | 339 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
fired | +0.001 |
away | +0.001 |
home | +0.001 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.001 |
unison | -0.001 |
utes | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
aback | +0.032 |
fired | +0.028 |
closer | +0.028 |
revenge | +0.026 |
away | +0.025 |
Neg logit contributions | |
kin | -0.041 |
pron | -0.039 |
uren | -0.036 |
lf | -0.033 |
omo | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
aback | +0.018 |
fired | +0.015 |
closer | +0.013 |
away | +0.013 |
revenge | +0.013 |
Neg logit contributions | |
kin | -0.038 |
pron | -0.037 |
uren | -0.034 |
lf | -0.032 |
ae | -0.032 |
Token | spread |
Token ID | 4104 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
aback | +0.017 |
closer | +0.014 |
fired | +0.014 |
away | +0.013 |
revenge | +0.013 |
Neg logit contributions | |
kin | -0.032 |
pron | -0.030 |
uren | -0.029 |
omo | -0.026 |
lf | -0.026 |
Token | some |
Token ID | 617 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
aback | +0.001 |
fired | +0.001 |
closer | +0.000 |
beh | +0.000 |
revenge | +0.000 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.001 |
addy | -0.001 |
moons | -0.001 |
Token | peanut |
Token ID | 26636 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
aback | +0.027 |
fired | +0.026 |
beh | +0.023 |
closer | +0.023 |
revenge | +0.022 |
Neg logit contributions | |
kin | -0.020 |
pron | -0.019 |
uren | -0.014 |
moons | -0.014 |
dots | -0.013 |
Token | butter |
Token ID | 9215 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
aback | +0.000 |
fired | +0.000 |
closer | +0.000 |
revenge | +0.000 |
beh | +0.000 |
Neg logit contributions | |
kin | -0.000 |
pron | -0.000 |
uren | -0.000 |
lf | -0.000 |
moons | -0.000 |
Token | on |
Token ID | 319 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.026 |
uren | +0.024 |
omo | +0.022 |
lf | +0.022 |
Neg logit contributions | |
aback | -0.016 |
closer | -0.014 |
fired | -0.013 |
away | -0.012 |
revenge | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.019 |
uren | +0.018 |
omo | +0.017 |
lf | +0.017 |
Neg logit contributions | |
aback | -0.013 |
closer | -0.012 |
away | -0.011 |
fired | -0.011 |
home | -0.011 |
Token | piece |
Token ID | 3704 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.020 |
uren | +0.016 |
lf | +0.014 |
ae | +0.013 |
Neg logit contributions | |
aback | -0.035 |
fired | -0.032 |
closer | -0.031 |
revenge | -0.030 |
beh | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
kin | +0.018 |
pron | +0.017 |
uren | +0.017 |
omo | +0.015 |
Adam | +0.015 |
Neg logit contributions | |
aback | -0.012 |
closer | -0.011 |
fired | -0.011 |
away | -0.011 |
home | -0.010 |
Token | bread |
Token ID | 8509 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
kin | +0.043 |
pron | +0.039 |
uren | +0.036 |
omo | +0.032 |
lf | +0.032 |
Neg logit contributions | |
aback | -0.045 |
closer | -0.041 |
fired | -0.040 |
away | -0.038 |
revenge | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
kin | +0.011 |
pron | +0.010 |
uren | +0.010 |
omo | +0.009 |
lf | +0.008 |
Neg logit contributions | |
aback | -0.007 |
closer | -0.007 |
fired | -0.006 |
away | -0.006 |
home | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | -7.49e-02 |
Pos logit contributions | |
aback | +0.006 |
closer | +0.005 |
fired | +0.005 |
home | +0.005 |
revenge | +0.005 |
Neg logit contributions | |
kin | -0.009 |
pron | -0.009 |
uren | -0.008 |
lf | -0.008 |
ae | -0.007 |
Token | feels |
Token ID | 5300 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
kin | +0.002 |
pron | +0.002 |
uren | +0.002 |
lf | +0.001 |
omo | +0.001 |
Neg logit contributions | |
aback | -0.002 |
closer | -0.001 |
fired | -0.001 |
away | -0.001 |
revenge | -0.001 |
Token | sorry |
Token ID | 7926 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
kin | +0.010 |
pron | +0.009 |
uren | +0.008 |
Adam | +0.007 |
moons | +0.007 |
Neg logit contributions | |
aback | -0.008 |
fired | -0.008 |
closer | -0.007 |
home | -0.007 |
revenge | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
kin | +0.004 |
pron | +0.004 |
uren | +0.003 |
omo | +0.003 |
lf | +0.003 |
Neg logit contributions | |
aback | -0.002 |
closer | -0.002 |
fired | -0.002 |
revenge | -0.002 |
away | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
aback | +0.007 |
closer | +0.006 |
fired | +0.006 |
home | +0.005 |
away | +0.005 |
Neg logit contributions | |
kin | -0.010 |
pron | -0.009 |
uren | -0.008 |
lf | -0.008 |
ae | -0.007 |
Token | says |
Token ID | 1139 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
fired | +0.004 |
away | +0.004 |
revenge | +0.004 |
Neg logit contributions | |
kin | -0.006 |
pron | -0.006 |
uren | -0.005 |
lf | -0.005 |
ae | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
aback | +0.018 |
fired | +0.016 |
closer | +0.015 |
revenge | +0.014 |
away | +0.014 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.017 |
uren | -0.015 |
ma | -0.014 |
lf | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
aback | +0.006 |
closer | +0.006 |
fired | +0.005 |
back | +0.005 |
away | +0.005 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.004 |
uren | -0.004 |
omo | -0.004 |
ae | -0.004 |
Token | I |
Token ID | 40 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
aback | +0.045 |
closer | +0.041 |
fired | +0.040 |
away | +0.038 |
revenge | +0.038 |
Neg logit contributions | |
kin | -0.044 |
pron | -0.041 |
uren | -0.038 |
lf | -0.033 |
omo | -0.033 |
Token | am |
Token ID | 716 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
aback | +0.030 |
closer | +0.026 |
fired | +0.026 |
away | +0.024 |
home | +0.024 |
Neg logit contributions | |
kin | -0.041 |
pron | -0.037 |
uren | -0.034 |
omo | -0.033 |
Adam | -0.031 |
Token | big |
Token ID | 1263 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
aback | +0.016 |
closer | +0.014 |
fired | +0.014 |
away | +0.013 |
revenge | +0.013 |
Neg logit contributions | |
kin | -0.018 |
pron | -0.016 |
uren | -0.015 |
omo | -0.013 |
lf | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
kin | +0.019 |
pron | +0.017 |
uren | +0.016 |
omo | +0.015 |
Adam | +0.014 |
Neg logit contributions | |
aback | -0.015 |
closer | -0.013 |
away | -0.012 |
fired | -0.012 |
home | -0.012 |
Token | red |
Token ID | 2266 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
kin | +0.015 |
pron | +0.014 |
uren | +0.012 |
omo | +0.011 |
lf | +0.011 |
Neg logit contributions | |
aback | -0.015 |
fired | -0.014 |
revenge | -0.013 |
closer | -0.013 |
home | -0.013 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
kin | +0.078 |
pron | +0.075 |
uren | +0.070 |
Adam | +0.063 |
lf | +0.062 |
Neg logit contributions | |
aback | -0.058 |
closer | -0.054 |
fired | -0.050 |
away | -0.050 |
home | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
kin | +0.096 |
pron | +0.090 |
lf | +0.082 |
uren | +0.081 |
bridge | +0.080 |
Neg logit contributions | |
aback | -0.046 |
closer | -0.044 |
fired | -0.039 |
home | -0.038 |
back | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
kin | +0.027 |
pron | +0.025 |
uren | +0.023 |
lf | +0.021 |
moons | +0.021 |
Neg logit contributions | |
aback | -0.021 |
closer | -0.020 |
fired | -0.019 |
home | -0.018 |
away | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
aback | +0.003 |
closer | +0.003 |
fired | +0.003 |
away | +0.003 |
home | +0.003 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.005 |
moons | -0.004 |
uren | -0.004 |
bridge | -0.004 |
Token | It |
Token ID | 1026 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
aback | +0.041 |
closer | +0.041 |
nearer | +0.034 |
away | +0.034 |
fired | +0.034 |
Neg logit contributions | |
kin | -0.056 |
pron | -0.052 |
uren | -0.049 |
lf | -0.048 |
omo | -0.046 |
Token | is |
Token ID | 318 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
aback | +0.040 |
fired | +0.037 |
closer | +0.035 |
home | +0.035 |
revenge | +0.035 |
Neg logit contributions | |
kin | -0.037 |
pron | -0.034 |
uren | -0.031 |
omo | -0.028 |
moons | -0.028 |
Token | funny |
Token ID | 8258 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
kin | +0.041 |
pron | +0.039 |
uren | +0.037 |
lf | +0.033 |
Adam | +0.033 |
Neg logit contributions | |
aback | -0.028 |
closer | -0.025 |
fired | -0.023 |
away | -0.023 |
home | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
kin | +0.049 |
pron | +0.046 |
uren | +0.042 |
Adam | +0.038 |
omo | +0.038 |
Neg logit contributions | |
aback | -0.035 |
closer | -0.032 |
fired | -0.030 |
home | -0.029 |
away | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
kin | +0.011 |
pron | +0.010 |
uren | +0.009 |
lf | +0.008 |
omo | +0.008 |
Neg logit contributions | |
aback | -0.009 |
fired | -0.008 |
closer | -0.008 |
revenge | -0.007 |
away | -0.007 |
Token | The |
Token ID | 383 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
aback | +0.012 |
closer | +0.011 |
fired | +0.011 |
away | +0.010 |
home | +0.010 |
Neg logit contributions | |
kin | -0.013 |
pron | -0.012 |
uren | -0.011 |
lf | -0.010 |
omo | -0.010 |
Token | end |
Token ID | 886 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
kin | +0.013 |
pron | +0.013 |
uren | +0.012 |
addy | +0.011 |
ae | +0.011 |
Neg logit contributions | |
closer | -0.009 |
home | -0.008 |
back | -0.008 |
aback | -0.008 |
away | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
aback | +0.050 |
fired | +0.044 |
closer | +0.043 |
revenge | +0.041 |
away | +0.040 |
Neg logit contributions | |
kin | -0.045 |
pron | -0.042 |
uren | -0.037 |
omo | -0.035 |
lf | -0.034 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
aback | +0.021 |
closer | +0.019 |
fired | +0.019 |
away | +0.017 |
revenge | +0.017 |
Neg logit contributions | |
kin | -0.021 |
pron | -0.019 |
uren | -0.018 |
lf | -0.016 |
omo | -0.016 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
kin | +0.031 |
pron | +0.029 |
uren | +0.027 |
omo | +0.024 |
lf | +0.024 |
Neg logit contributions | |
aback | -0.025 |
closer | -0.023 |
fired | -0.022 |
home | -0.021 |
away | -0.021 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
kin | +0.003 |
pron | +0.003 |
uren | +0.003 |
scalp | +0.002 |
bridge | +0.002 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
home | -0.004 |
fired | -0.004 |
away | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
kin | +0.086 |
uren | +0.082 |
pron | +0.082 |
omo | +0.074 |
majesty | +0.074 |
Neg logit contributions | |
closer | -0.029 |
aback | -0.028 |
home | -0.023 |
away | -0.023 |
back | -0.022 |
Token | time |
Token ID | 640 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.013 |
home | +0.012 |
away | +0.012 |
fired | +0.012 |
Neg logit contributions | |
kin | -0.011 |
pron | -0.009 |
uren | -0.009 |
bridge | -0.008 |
moons | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
aback | +0.020 |
closer | +0.017 |
fired | +0.017 |
away | +0.016 |
revenge | +0.016 |
Neg logit contributions | |
kin | -0.026 |
pron | -0.024 |
uren | -0.023 |
omo | -0.020 |
lf | -0.020 |
Token | there |
Token ID | 612 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
kin | +0.006 |
pron | +0.005 |
uren | +0.005 |
omo | +0.004 |
lf | +0.004 |
Neg logit contributions | |
aback | -0.005 |
closer | -0.005 |
fired | -0.005 |
revenge | -0.004 |
away | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | +1.59e-01 |
Pos logit contributions | |
aback | +0.027 |
fired | +0.024 |
beh | +0.023 |
closer | +0.022 |
revenge | +0.022 |
Neg logit contributions | |
kin | -0.021 |
pron | -0.019 |
uren | -0.018 |
Adam | -0.016 |
lf | -0.016 |
Token | beds |
Token ID | 20237 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
aback | +0.005 |
fired | +0.004 |
closer | +0.004 |
beh | +0.004 |
smart | +0.004 |
Neg logit contributions | |
kin | -0.002 |
pron | -0.002 |
lf | -0.002 |
omo | -0.002 |
uren | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
kin | +0.053 |
pron | +0.050 |
uren | +0.048 |
omo | +0.043 |
lf | +0.042 |
Neg logit contributions | |
aback | -0.038 |
closer | -0.035 |
fired | -0.034 |
away | -0.033 |
home | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
aback | +0.005 |
closer | +0.005 |
home | +0.005 |
away | +0.005 |
back | +0.004 |
Neg logit contributions | |
kin | -0.007 |
pron | -0.007 |
lf | -0.006 |
uren | -0.006 |
bridge | -0.006 |
Token | c |
Token ID | 269 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
kin | +0.067 |
pron | +0.066 |
uren | +0.062 |
omo | +0.058 |
lf | +0.056 |
Neg logit contributions | |
closer | -0.042 |
aback | -0.039 |
away | -0.039 |
back | -0.036 |
home | -0.036 |
Token | uddle |
Token ID | 24500 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
kin | +0.019 |
pron | +0.017 |
uren | +0.016 |
lf | +0.014 |
omo | +0.013 |
Neg logit contributions | |
aback | -0.021 |
closer | -0.019 |
fired | -0.019 |
away | -0.018 |
home | -0.018 |
Token | with |
Token ID | 351 |
Feature activation | +9.69e-01 |
Pos logit contributions | |
kin | +0.088 |
pron | +0.081 |
uren | +0.075 |
omo | +0.068 |
lf | +0.068 |
Neg logit contributions | |
aback | -0.075 |
closer | -0.066 |
fired | -0.066 |
revenge | -0.061 |
away | -0.061 |
Token | their |
Token ID | 511 |
Feature activation | -8.18e-01 |
Pos logit contributions | |
aback | +0.019 |
closer | +0.017 |
fired | +0.016 |
away | +0.016 |
home | +0.016 |
Neg logit contributions | |
kin | -0.024 |
pron | -0.023 |
uren | -0.021 |
lf | -0.019 |
omo | -0.019 |
Token | blankets |
Token ID | 34794 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
kin | +0.017 |
pron | +0.016 |
uren | +0.014 |
omo | +0.013 |
lf | +0.013 |
Neg logit contributions | |
aback | -0.020 |
fired | -0.017 |
closer | -0.017 |
away | -0.016 |
revenge | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
kin | +0.036 |
pron | +0.036 |
uren | +0.035 |
Adam | +0.031 |
omo | +0.031 |
Neg logit contributions | |
aback | -0.025 |
closer | -0.024 |
away | -0.024 |
home | -0.023 |
back | -0.022 |
Token | pill |
Token ID | 9582 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
kin | +0.002 |
pron | +0.002 |
uren | +0.002 |
omo | +0.001 |
lf | +0.001 |
Neg logit contributions | |
aback | -0.002 |
closer | -0.002 |
fired | -0.001 |
away | -0.001 |
home | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
aback | +0.005 |
fired | +0.004 |
closer | +0.004 |
away | +0.004 |
revenge | +0.004 |
Neg logit contributions | |
kin | -0.005 |
pron | -0.005 |
uren | -0.005 |
lf | -0.004 |
omo | -0.004 |
Token | desk |
Token ID | 6915 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
aback | +0.043 |
closer | +0.038 |
fired | +0.038 |
revenge | +0.035 |
away | +0.035 |
Neg logit contributions | |
kin | -0.043 |
pron | -0.040 |
uren | -0.036 |
lf | -0.033 |
omo | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
kin | +0.023 |
pron | +0.022 |
uren | +0.021 |
omo | +0.019 |
scalp | +0.019 |
Neg logit contributions | |
aback | -0.013 |
closer | -0.012 |
away | -0.012 |
fired | -0.012 |
home | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
kin | +0.109 |
pron | +0.103 |
uren | +0.097 |
omo | +0.091 |
ae | +0.088 |
Neg logit contributions | |
aback | -0.055 |
closer | -0.052 |
fired | -0.045 |
away | -0.044 |
revenge | -0.042 |
Token | phone |
Token ID | 3072 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
kin | +0.037 |
pron | +0.034 |
uren | +0.032 |
omo | +0.029 |
lf | +0.028 |
Neg logit contributions | |
aback | -0.035 |
closer | -0.033 |
fired | -0.032 |
away | -0.030 |
home | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
aback | +0.002 |
closer | +0.002 |
away | +0.002 |
fired | +0.002 |
home | +0.001 |
Neg logit contributions | |
kin | -0.003 |
pron | -0.003 |
uren | -0.003 |
ae | -0.003 |
omo | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
kin | +0.121 |
pron | +0.113 |
uren | +0.107 |
omo | +0.100 |
ae | +0.098 |
Neg logit contributions | |
aback | -0.064 |
closer | -0.060 |
away | -0.053 |
fired | -0.053 |
home | -0.050 |
Token | computer |
Token ID | 3644 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
kin | +0.055 |
pron | +0.049 |
uren | +0.047 |
omo | +0.043 |
Adam | +0.042 |
Neg logit contributions | |
aback | -0.047 |
closer | -0.045 |
fired | -0.043 |
away | -0.041 |
home | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
kin | +0.019 |
pron | +0.018 |
uren | +0.017 |
omo | +0.016 |
ae | +0.016 |
Neg logit contributions | |
aback | -0.008 |
away | -0.008 |
closer | -0.008 |
back | -0.007 |
home | -0.007 |
Token | some |
Token ID | 617 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.026 |
uren | +0.024 |
omo | +0.022 |
lf | +0.022 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.016 |
fired | -0.016 |
away | -0.015 |
revenge | -0.015 |
Token | papers |
Token ID | 9473 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
kin | +0.026 |
pron | +0.024 |
uren | +0.022 |
lf | +0.020 |
omo | +0.020 |
Neg logit contributions | |
aback | -0.027 |
closer | -0.024 |
fired | -0.024 |
away | -0.023 |
revenge | -0.022 |
Token | nightmare |
Token ID | 17123 |
Feature activation | +7.03e-01 |
Pos logit contributions | |
kin | +0.031 |
pron | +0.029 |
uren | +0.028 |
Adam | +0.024 |
ae | +0.024 |
Neg logit contributions | |
aback | -0.023 |
closer | -0.021 |
home | -0.020 |
away | -0.020 |
fired | -0.019 |
Token | couldn |
Token ID | 3521 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
aback | +0.014 |
closer | +0.013 |
fired | +0.012 |
away | +0.012 |
revenge | +0.012 |
Neg logit contributions | |
kin | -0.017 |
pron | -0.016 |
uren | -0.015 |
omo | -0.014 |
Adam | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
kin | +0.012 |
pron | +0.010 |
uren | +0.009 |
lf | +0.008 |
omo | +0.008 |
Neg logit contributions | |
aback | -0.019 |
fired | -0.018 |
closer | -0.018 |
revenge | -0.017 |
away | -0.016 |
Token | hurt |
Token ID | 5938 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
kin | +0.008 |
pron | +0.008 |
uren | +0.007 |
omo | +0.006 |
Adam | +0.006 |
Neg logit contributions | |
aback | -0.006 |
closer | -0.006 |
fired | -0.005 |
away | -0.005 |
home | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
kin | +0.040 |
pron | +0.035 |
uren | +0.034 |
lf | +0.031 |
ia | +0.030 |
Neg logit contributions | |
aback | -0.033 |
fired | -0.028 |
closer | -0.028 |
revenge | -0.026 |
nearer | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
kin | +0.035 |
pron | +0.033 |
uren | +0.032 |
omo | +0.028 |
Adam | +0.028 |
Neg logit contributions | |
aback | -0.028 |
closer | -0.026 |
fired | -0.025 |
away | -0.025 |
home | -0.025 |
Token | so |
Token ID | 523 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
kin | +0.095 |
pron | +0.087 |
uren | +0.082 |
omo | +0.074 |
ae | +0.073 |
Neg logit contributions | |
aback | -0.089 |
closer | -0.084 |
fired | -0.078 |
away | -0.078 |
home | -0.077 |
Token | she |
Token ID | 673 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
aback | +0.013 |
closer | +0.012 |
fired | +0.011 |
away | +0.011 |
home | +0.011 |
Neg logit contributions | |
kin | -0.014 |
pron | -0.013 |
uren | -0.012 |
omo | -0.010 |
Adam | -0.010 |
Token | lay |
Token ID | 3830 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
kin | +0.005 |
pron | +0.005 |
uren | +0.005 |
Adam | +0.004 |
omo | +0.004 |
Neg logit contributions | |
aback | -0.004 |
closer | -0.004 |
away | -0.004 |
fired | -0.004 |
home | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
kin | +0.058 |
pron | +0.055 |
uren | +0.052 |
omo | +0.049 |
lf | +0.049 |
Neg logit contributions | |
aback | -0.019 |
closer | -0.016 |
fired | -0.015 |
away | -0.014 |
home | -0.013 |
Token | bed |
Token ID | 3996 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
aback | +0.016 |
closer | +0.015 |
fired | +0.014 |
away | +0.014 |
home | +0.014 |
Neg logit contributions | |
kin | -0.020 |
pron | -0.018 |
uren | -0.017 |
omo | -0.015 |
lf | -0.015 |
Token | You |
Token ID | 921 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
fired | +0.001 |
revenge | +0.001 |
away | +0.001 |
Neg logit contributions | |
kin | -0.001 |
pron | -0.001 |
uren | -0.001 |
lf | -0.001 |
omo | -0.001 |
Token | are |
Token ID | 389 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
kin | +0.028 |
pron | +0.026 |
uren | +0.024 |
omo | +0.022 |
lf | +0.022 |
Neg logit contributions | |
aback | -0.021 |
closer | -0.019 |
fired | -0.018 |
away | -0.018 |
revenge | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
kin | +0.052 |
pron | +0.049 |
uren | +0.046 |
omo | +0.042 |
lf | +0.041 |
Neg logit contributions | |
aback | -0.037 |
closer | -0.033 |
fired | -0.032 |
away | -0.030 |
revenge | -0.030 |
Token | good |
Token ID | 922 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
kin | +0.010 |
pron | +0.010 |
uren | +0.008 |
omo | +0.008 |
lf | +0.007 |
Neg logit contributions | |
aback | -0.009 |
fired | -0.008 |
closer | -0.008 |
revenge | -0.007 |
nearer | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
aback | +0.019 |
closer | +0.017 |
fired | +0.017 |
away | +0.016 |
home | +0.016 |
Neg logit contributions | |
kin | -0.027 |
pron | -0.025 |
uren | -0.024 |
lf | -0.021 |
omo | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
aback | +0.021 |
closer | +0.019 |
fired | +0.018 |
away | +0.018 |
home | +0.017 |
Neg logit contributions | |
kin | -0.023 |
pron | -0.021 |
uren | -0.020 |
omo | -0.018 |
lf | -0.017 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
kin | +0.100 |
pron | +0.089 |
uren | +0.086 |
lf | +0.077 |
bridge | +0.077 |
Neg logit contributions | |
aback | -0.079 |
closer | -0.077 |
home | -0.072 |
back | -0.070 |
away | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
kin | +0.033 |
pron | +0.031 |
uren | +0.030 |
omo | +0.027 |
ae | +0.027 |
Neg logit contributions | |
aback | -0.021 |
away | -0.019 |
home | -0.019 |
fired | -0.019 |
closer | -0.018 |
Token | You |
Token ID | 921 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
aback | +0.013 |
fired | +0.011 |
closer | +0.011 |
revenge | +0.010 |
home | +0.010 |
Neg logit contributions | |
kin | -0.016 |
pron | -0.015 |
uren | -0.013 |
lf | -0.012 |
ae | -0.012 |
Token | can |
Token ID | 460 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
kin | +0.024 |
pron | +0.022 |
uren | +0.021 |
omo | +0.019 |
lf | +0.019 |
Neg logit contributions | |
aback | -0.019 |
closer | -0.016 |
fired | -0.016 |
away | -0.016 |
revenge | -0.015 |
Token | help |
Token ID | 1037 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
kin | +0.012 |
pron | +0.011 |
uren | +0.010 |
lf | +0.009 |
omo | +0.009 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.010 |
fired | -0.010 |
away | -0.010 |
revenge | -0.010 |
Token | tr |
Token ID | 491 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
kin | +0.008 |
pron | +0.008 |
uren | +0.007 |
Adam | +0.007 |
ae | +0.007 |
Neg logit contributions | |
aback | -0.007 |
closer | -0.007 |
fired | -0.006 |
home | -0.006 |
away | -0.006 |
Token | amp |
Token ID | 696 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
aback | +0.001 |
closer | +0.001 |
fired | +0.001 |
away | +0.000 |
revenge | +0.000 |
Neg logit contributions | |
kin | -0.000 |
pron | -0.000 |
uren | -0.000 |
omo | -0.000 |
lf | -0.000 |
Token | oline |
Token ID | 14453 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
kin | +0.054 |
pron | +0.053 |
uren | +0.048 |
omo | +0.042 |
majesty | +0.042 |
Neg logit contributions | |
aback | -0.074 |
away | -0.069 |
closer | -0.068 |
fired | -0.067 |
home | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
kin | +0.051 |
pron | +0.050 |
uren | +0.047 |
omo | +0.043 |
Adam | +0.042 |
Neg logit contributions | |
aback | -0.031 |
closer | -0.029 |
fired | -0.028 |
away | -0.027 |
home | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
kin | +0.014 |
pron | +0.013 |
uren | +0.012 |
omo | +0.011 |
Adam | +0.011 |
Neg logit contributions | |
aback | -0.011 |
closer | -0.010 |
fired | -0.009 |
away | -0.009 |
home | -0.009 |
Token | sandbox |
Token ID | 35204 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
kin | +0.021 |
pron | +0.019 |
uren | +0.018 |
Adam | +0.017 |
ae | +0.017 |
Neg logit contributions | |
aback | -0.018 |
closer | -0.018 |
fired | -0.016 |
home | -0.016 |
away | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
pron | +0.133 |
uren | +0.133 |
kin | +0.130 |
Adam | +0.116 |
Avery | +0.113 |
Neg logit contributions | |
aback | -0.064 |
closer | -0.063 |
away | -0.062 |
home | -0.061 |
fired | -0.059 |
Token | He |
Token ID | 679 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
aback | +0.011 |
closer | +0.008 |
home | +0.008 |
back | +0.008 |
down | +0.008 |
Neg logit contributions | |
kin | -0.016 |
pron | -0.014 |
lf | -0.012 |
uren | -0.012 |
utes | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
kin | +0.020 |
pron | +0.019 |
uren | +0.018 |
Adam | +0.016 |
scalp | +0.016 |
Neg logit contributions | |
aback | -0.014 |
closer | -0.014 |
fired | -0.013 |
away | -0.012 |
home | -0.012 |
Token | having |
Token ID | 1719 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
kin | +0.046 |
pron | +0.043 |
uren | +0.041 |
lf | +0.038 |
omo | +0.037 |
Neg logit contributions | |
aback | -0.021 |
closer | -0.021 |
home | -0.019 |
away | -0.017 |
back | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
kin | +0.010 |
pron | +0.009 |
uren | +0.009 |
lf | +0.008 |
omo | +0.008 |
Neg logit contributions | |
aback | -0.006 |
closer | -0.005 |
home | -0.004 |
fired | -0.004 |
away | -0.004 |