Token | the |
Token ID | 262 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
iring | +0.007 |
ind | +0.007 |
handed | +0.006 |
cheaper | +0.006 |
glers | +0.006 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.004 |
ids | -0.003 |
nod | -0.003 |
imagination | -0.003 |
Token | pigeon |
Token ID | 46387 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
idea | +0.009 |
gard | +0.008 |
imagination | +0.008 |
tul | +0.008 |
nod | +0.007 |
Neg logit contributions | |
iring | -0.012 |
shadow | -0.012 |
ding | -0.011 |
ind | -0.011 |
awed | -0.011 |
Token | all |
Token ID | 477 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.005 |
cheaper | +0.005 |
glers | +0.004 |
homeless | +0.004 |
Neg logit contributions | |
isel | -0.004 |
alk | -0.003 |
pan | -0.003 |
ids | -0.003 |
kin | -0.003 |
Token | those |
Token ID | 883 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
isel | +0.002 |
pan | +0.001 |
alk | +0.001 |
kin | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.002 |
handed | -0.001 |
cheaper | -0.001 |
barking | -0.001 |
Token | weeks |
Token ID | 2745 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
ind | +0.013 |
iring | +0.012 |
barking | +0.012 |
handed | +0.012 |
shadow | +0.012 |
Neg logit contributions | |
lived | -0.010 |
isel | -0.010 |
aces | -0.009 |
imagination | -0.009 |
kin | -0.009 |
Token | ago |
Token ID | 2084 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
isel | +0.054 |
pan | +0.051 |
ids | +0.050 |
kin | +0.049 |
alk | +0.048 |
Neg logit contributions | |
ind | -0.089 |
iring | -0.087 |
barking | -0.077 |
cheaper | -0.076 |
nicer | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
isel | +0.189 |
pan | +0.161 |
kin | +0.157 |
alk | +0.155 |
ids | +0.151 |
Neg logit contributions | |
ind | -0.218 |
iring | -0.215 |
handed | -0.189 |
cheaper | -0.189 |
barking | -0.185 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
isel | +0.025 |
kin | +0.021 |
pan | +0.021 |
alk | +0.019 |
brush | +0.019 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.022 |
handed | -0.019 |
barking | -0.019 |
elderly | -0.018 |
Token | Mike |
Token ID | 16073 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
ind | +0.057 |
iring | +0.056 |
cheaper | +0.050 |
handed | +0.050 |
homeless | +0.049 |
Neg logit contributions | |
isel | -0.045 |
pan | -0.037 |
alk | -0.037 |
kin | -0.037 |
ids | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
isel | +0.002 |
pan | +0.002 |
alk | +0.002 |
kin | +0.002 |
ids | +0.002 |
Neg logit contributions | |
iring | -0.002 |
ind | -0.002 |
cheaper | -0.002 |
handed | -0.002 |
faster | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
ind | +0.022 |
iring | +0.022 |
handed | +0.019 |
barking | +0.019 |
cheaper | +0.019 |
Neg logit contributions | |
isel | -0.030 |
pan | -0.026 |
kin | -0.025 |
alk | -0.025 |
ids | -0.025 |
Token | by |
Token ID | 416 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
isel | +0.010 |
alk | +0.009 |
imagination | +0.009 |
ids | +0.009 |
pan | +0.009 |
Neg logit contributions | |
ind | -0.013 |
iring | -0.013 |
handed | -0.012 |
ich | -0.012 |
concession | -0.012 |
Token | people |
Token ID | 661 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
isel | +0.059 |
alk | +0.049 |
imagination | +0.048 |
kin | +0.044 |
pan | +0.042 |
Neg logit contributions | |
iring | -0.099 |
ind | -0.099 |
concession | -0.093 |
glers | -0.093 |
handed | -0.091 |
Token | a |
Token ID | 257 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
isel | +0.023 |
ids | +0.023 |
can | +0.021 |
pan | +0.021 |
pter | +0.021 |
Neg logit contributions | |
iring | -0.039 |
ind | -0.038 |
sidelines | -0.034 |
handed | -0.034 |
concession | -0.034 |
Token | long |
Token ID | 890 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
isel | +0.040 |
imagination | +0.034 |
alk | +0.033 |
pan | +0.032 |
cuc | +0.032 |
Neg logit contributions | |
iring | -0.043 |
ind | -0.039 |
glers | -0.036 |
handed | -0.035 |
concession | -0.033 |
Token | time |
Token ID | 640 |
Feature activation | +7.33e-02 |
Pos logit contributions | |
isel | +0.050 |
pan | +0.043 |
kin | +0.041 |
ids | +0.040 |
alk | +0.038 |
Neg logit contributions | |
ind | -0.057 |
barking | -0.052 |
iring | -0.051 |
faster | -0.050 |
cheaper | -0.049 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
isel | +0.002 |
alk | +0.002 |
ids | +0.002 |
pan | +0.002 |
kin | +0.002 |
Neg logit contributions | |
ind | -0.004 |
iring | -0.004 |
handed | -0.003 |
homeless | -0.003 |
concession | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
isel | +0.188 |
pan | +0.160 |
kin | +0.158 |
alk | +0.155 |
ids | +0.151 |
Neg logit contributions | |
ind | -0.206 |
iring | -0.203 |
handed | -0.178 |
cheaper | -0.177 |
barking | -0.174 |
Token | Tim |
Token ID | 5045 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
isel | +0.020 |
pan | +0.015 |
alk | +0.015 |
ids | +0.014 |
kin | +0.014 |
Neg logit contributions | |
ind | -0.030 |
iring | -0.029 |
handed | -0.026 |
cheaper | -0.026 |
faster | -0.026 |
Token | my |
Token ID | 1820 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
isel | +0.025 |
alk | +0.021 |
kin | +0.021 |
pan | +0.021 |
aces | +0.020 |
Neg logit contributions | |
iring | -0.017 |
ind | -0.016 |
cheaper | -0.015 |
handed | -0.014 |
homeless | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
kin | +0.004 |
alk | +0.004 |
ids | +0.004 |
Neg logit contributions | |
ind | -0.006 |
iring | -0.006 |
handed | -0.006 |
cheaper | -0.006 |
barking | -0.006 |
Token | very |
Token ID | 845 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.011 |
kin | +0.011 |
ids | +0.010 |
alk | +0.010 |
Neg logit contributions | |
ind | -0.011 |
iring | -0.011 |
handed | -0.009 |
cheaper | -0.009 |
glers | -0.009 |
Token | coins |
Token ID | 10796 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
ind | +0.030 |
iring | +0.030 |
handed | +0.026 |
ich | +0.025 |
cheaper | +0.025 |
Neg logit contributions | |
isel | -0.025 |
pan | -0.021 |
kin | -0.020 |
alk | -0.020 |
ids | -0.020 |
Token | that |
Token ID | 326 |
Feature activation | +6.07e-02 |
Pos logit contributions | |
isel | +0.018 |
pan | +0.016 |
kin | +0.016 |
ids | +0.016 |
aces | +0.015 |
Neg logit contributions | |
ind | -0.035 |
iring | -0.033 |
handed | -0.032 |
concession | -0.031 |
homeless | -0.030 |
Token | people |
Token ID | 661 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
isel | +0.002 |
kin | +0.002 |
pan | +0.002 |
lived | +0.002 |
ids | +0.002 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.003 |
handed | -0.003 |
shadow | -0.002 |
cheaper | -0.002 |
Token | used |
Token ID | 973 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
ind | +0.010 |
iring | +0.009 |
handed | +0.009 |
ich | +0.008 |
destination | +0.008 |
Neg logit contributions | |
isel | -0.004 |
lived | -0.003 |
pan | -0.003 |
kin | -0.003 |
are | -0.003 |
Token | long |
Token ID | 890 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
iring | +0.002 |
ind | +0.002 |
handed | +0.002 |
ich | +0.002 |
itating | +0.002 |
Neg logit contributions | |
isel | -0.002 |
alk | -0.001 |
pan | -0.001 |
ids | -0.001 |
imagination | -0.001 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
isel | +0.043 |
pan | +0.035 |
kin | +0.034 |
alk | +0.034 |
ids | +0.032 |
Neg logit contributions | |
ind | -0.055 |
iring | -0.055 |
handed | -0.049 |
cheaper | -0.049 |
barking | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
isel | +0.194 |
pan | +0.163 |
kin | +0.160 |
alk | +0.159 |
ids | +0.154 |
Neg logit contributions | |
ind | -0.198 |
iring | -0.196 |
handed | -0.172 |
cheaper | -0.170 |
barking | -0.168 |
Token | They |
Token ID | 1119 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
kin | +0.004 |
alk | +0.004 |
ids | +0.004 |
Neg logit contributions | |
iring | -0.006 |
ind | -0.006 |
cheaper | -0.005 |
handed | -0.005 |
barking | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.011 |
kin | +0.011 |
alk | +0.011 |
ids | +0.010 |
Neg logit contributions | |
ind | -0.019 |
iring | -0.019 |
cheaper | -0.017 |
barking | -0.017 |
faster | -0.017 |
Token | paintings |
Token ID | 21641 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
isel | +0.001 |
imagination | +0.001 |
cuc | +0.001 |
lived | +0.001 |
pan | +0.001 |
Neg logit contributions | |
ind | -0.001 |
iring | -0.001 |
shadow | -0.001 |
itating | -0.001 |
handed | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
brush | +0.016 |
isel | +0.015 |
pan | +0.014 |
aces | +0.014 |
ids | +0.014 |
Neg logit contributions | |
ind | -0.049 |
handed | -0.046 |
iring | -0.045 |
shadow | -0.044 |
homeless | -0.042 |
Token | flyer |
Token ID | 42464 |
Feature activation | -8.86e-02 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
idea | +0.004 |
kin | +0.004 |
imagination | +0.004 |
Neg logit contributions | |
iring | -0.006 |
ind | -0.006 |
handed | -0.006 |
ll | -0.005 |
glers | -0.005 |
Token | posted |
Token ID | 4481 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ind | +0.004 |
iring | +0.004 |
handed | +0.003 |
glers | +0.003 |
ich | +0.003 |
Neg logit contributions | |
isel | -0.003 |
pan | -0.003 |
kin | -0.003 |
alk | -0.003 |
idea | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
ind | +0.008 |
iring | +0.007 |
ll | +0.007 |
handed | +0.007 |
ich | +0.007 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.004 |
brush | -0.004 |
aces | -0.004 |
It | -0.004 |
Token | few |
Token ID | 1178 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
isel | +0.022 |
pan | +0.019 |
brush | +0.019 |
imagination | +0.019 |
kin | +0.019 |
Neg logit contributions | |
iring | -0.029 |
ind | -0.027 |
handed | -0.024 |
glers | -0.024 |
ll | -0.024 |
Token | days |
Token ID | 1528 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
isel | +0.029 |
pan | +0.023 |
kin | +0.023 |
alk | +0.023 |
imagination | +0.022 |
Neg logit contributions | |
iring | -0.033 |
ind | -0.033 |
handed | -0.029 |
barking | -0.029 |
ich | -0.028 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
isel | +0.048 |
pan | +0.042 |
ids | +0.041 |
alk | +0.040 |
aces | +0.039 |
Neg logit contributions | |
ind | -0.080 |
iring | -0.075 |
cheaper | -0.068 |
nicer | -0.067 |
handed | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
isel | +0.197 |
pan | +0.164 |
alk | +0.159 |
kin | +0.159 |
ids | +0.154 |
Neg logit contributions | |
ind | -0.193 |
iring | -0.192 |
handed | -0.170 |
cheaper | -0.167 |
barking | -0.167 |
Token | looking |
Token ID | 2045 |
Feature activation | +7.03e-02 |
Pos logit contributions | |
isel | +0.028 |
imagination | +0.024 |
It | +0.024 |
pan | +0.024 |
ids | +0.023 |
Neg logit contributions | |
ind | -0.050 |
iring | -0.045 |
glers | -0.042 |
handed | -0.041 |
ll | -0.041 |
Token | for |
Token ID | 329 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
isel | +0.003 |
pan | +0.002 |
idea | +0.002 |
ids | +0.002 |
aces | +0.002 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.003 |
handed | -0.003 |
ll | -0.003 |
ich | -0.003 |
Token | help |
Token ID | 1037 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
ind | +0.008 |
itating | +0.008 |
iring | +0.008 |
ll | +0.007 |
glers | +0.007 |
Neg logit contributions | |
isel | -0.005 |
imagination | -0.004 |
lived | -0.004 |
ids | -0.004 |
idea | -0.004 |
Token | around |
Token ID | 1088 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
isel | +0.001 |
pan | +0.001 |
alk | +0.001 |
idea | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.002 |
Nice | -0.002 |
ich | -0.002 |
handed | -0.002 |
Token | how |
Token ID | 703 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
imagination | +0.004 |
kin | +0.004 |
lived | +0.004 |
Neg logit contributions | |
ind | -0.006 |
iring | -0.006 |
handed | -0.005 |
ich | -0.005 |
itating | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
isel | +0.018 |
pan | +0.016 |
kin | +0.015 |
alk | +0.015 |
ids | +0.015 |
Neg logit contributions | |
iring | -0.012 |
ind | -0.011 |
cheaper | -0.010 |
elderly | -0.010 |
new | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
cheaper | +0.006 |
handed | +0.006 |
faster | +0.006 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.004 |
kin | -0.004 |
alk | -0.004 |
ids | -0.003 |
Token | used |
Token ID | 973 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
ind | +0.001 |
iring | +0.001 |
handed | +0.001 |
eddy | +0.001 |
sidelines | +0.001 |
Neg logit contributions | |
isel | -0.001 |
aces | -0.001 |
lived | -0.001 |
idea | -0.001 |
ids | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
isel | +0.004 |
pan | +0.003 |
alk | +0.003 |
ids | +0.003 |
imagination | +0.003 |
Neg logit contributions | |
ind | -0.004 |
iring | -0.004 |
handed | -0.004 |
ich | -0.003 |
homeless | -0.003 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
isel | +0.053 |
kin | +0.044 |
pan | +0.044 |
alk | +0.041 |
ids | +0.041 |
Neg logit contributions | |
ind | -0.051 |
iring | -0.049 |
cheaper | -0.045 |
faster | -0.045 |
barking | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
isel | +0.184 |
pan | +0.157 |
kin | +0.155 |
alk | +0.152 |
ids | +0.148 |
Neg logit contributions | |
ind | -0.204 |
iring | -0.202 |
handed | -0.177 |
cheaper | -0.175 |
barking | -0.173 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
isel | +0.025 |
pan | +0.021 |
kin | +0.020 |
alk | +0.020 |
ids | +0.019 |
Neg logit contributions | |
ind | -0.032 |
iring | -0.031 |
handed | -0.028 |
cheaper | -0.028 |
barking | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
isel | +0.019 |
pan | +0.017 |
alk | +0.016 |
kin | +0.016 |
ids | +0.015 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.017 |
faster | -0.016 |
elderly | -0.016 |
cheaper | -0.015 |
Token | fascinated |
Token ID | 30103 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
isel | +0.020 |
pan | +0.017 |
kin | +0.017 |
ids | +0.016 |
aces | +0.016 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.021 |
handed | -0.019 |
glers | -0.018 |
cheaper | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
idea | +0.015 |
isel | +0.015 |
It | +0.014 |
ily | +0.014 |
can | +0.013 |
Neg logit contributions | |
shadow | -0.026 |
sidelines | -0.025 |
concession | -0.025 |
handed | -0.025 |
ind | -0.024 |
Token | someone |
Token ID | 2130 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
isel | +0.049 |
alk | +0.044 |
kin | +0.042 |
pan | +0.042 |
imagination | +0.040 |
Neg logit contributions | |
ind | -0.070 |
iring | -0.069 |
cheaper | -0.062 |
concession | -0.062 |
handed | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
iring | +0.039 |
ind | +0.038 |
sidelines | +0.034 |
Nice | +0.033 |
handed | +0.033 |
Neg logit contributions | |
can | -0.021 |
lived | -0.020 |
isel | -0.019 |
ids | -0.019 |
are | -0.019 |
Token | very |
Token ID | 845 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
isel | +0.025 |
imagination | +0.022 |
kin | +0.022 |
cuc | +0.022 |
pan | +0.022 |
Neg logit contributions | |
iring | -0.038 |
ind | -0.034 |
glers | -0.030 |
handed | -0.030 |
itating | -0.030 |
Token | long |
Token ID | 890 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
iring | +0.026 |
ning | +0.025 |
ind | +0.024 |
glers | +0.023 |
handed | +0.023 |
Neg logit contributions | |
isel | -0.029 |
idea | -0.026 |
imagination | -0.025 |
kin | -0.025 |
alk | -0.024 |
Token | time |
Token ID | 640 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.028 |
kin | +0.027 |
alk | +0.027 |
ids | +0.027 |
Neg logit contributions | |
ind | -0.048 |
iring | -0.046 |
barking | -0.043 |
cheaper | -0.043 |
handed | -0.043 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.79e+00 |
Pos logit contributions | |
ind | +0.006 |
iring | +0.006 |
handed | +0.006 |
glers | +0.006 |
homeless | +0.006 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.002 |
ids | -0.001 |
alk | -0.001 |
imagination | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
isel | +0.190 |
pan | +0.157 |
alk | +0.152 |
kin | +0.152 |
ids | +0.148 |
Neg logit contributions | |
ind | -0.195 |
iring | -0.193 |
handed | -0.172 |
cheaper | -0.170 |
barking | -0.168 |
Token | The |
Token ID | 383 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
isel | +0.017 |
pan | +0.014 |
kin | +0.013 |
alk | +0.013 |
ids | +0.013 |
Neg logit contributions | |
ind | -0.026 |
iring | -0.025 |
handed | -0.023 |
cheaper | -0.023 |
barking | -0.022 |
Token | little |
Token ID | 1310 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
isel | +0.025 |
kin | +0.021 |
pan | +0.021 |
alk | +0.021 |
ids | +0.020 |
Neg logit contributions | |
ind | -0.027 |
iring | -0.027 |
handed | -0.024 |
barking | -0.023 |
cheaper | -0.023 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.005 |
ids | +0.005 |
alk | +0.005 |
kin | +0.004 |
Neg logit contributions | |
iring | -0.004 |
ind | -0.003 |
elderly | -0.003 |
cheaper | -0.003 |
faster | -0.003 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
ind | +0.014 |
iring | +0.014 |
cheaper | +0.012 |
handed | +0.012 |
barking | +0.012 |
Neg logit contributions | |
isel | -0.012 |
pan | -0.010 |
alk | -0.010 |
kin | -0.010 |
ids | -0.010 |
Token | important |
Token ID | 1593 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
isel | +0.009 |
alk | +0.008 |
kin | +0.008 |
pan | +0.008 |
imagination | +0.008 |
Neg logit contributions | |
iring | -0.005 |
ind | -0.005 |
handed | -0.004 |
barking | -0.004 |
cheaper | -0.004 |
Token | person |
Token ID | 1048 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
isel | +0.024 |
pan | +0.020 |
kin | +0.020 |
alk | +0.020 |
ids | +0.019 |
Neg logit contributions | |
ind | -0.019 |
iring | -0.019 |
handed | -0.016 |
cheaper | -0.016 |
barking | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
iring | +0.041 |
ind | +0.041 |
sidelines | +0.036 |
handed | +0.035 |
homeless | +0.034 |
Neg logit contributions | |
ids | -0.020 |
lived | -0.020 |
isel | -0.020 |
can | -0.020 |
pan | -0.020 |
Token | long |
Token ID | 890 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
isel | +0.030 |
imagination | +0.028 |
cuc | +0.026 |
gard | +0.026 |
idea | +0.026 |
Neg logit contributions | |
iring | -0.039 |
ind | -0.036 |
glers | -0.033 |
ning | -0.031 |
ized | -0.031 |
Token | time |
Token ID | 640 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.029 |
kin | +0.027 |
alk | +0.027 |
ids | +0.026 |
Neg logit contributions | |
ind | -0.045 |
iring | -0.044 |
barking | -0.040 |
handed | -0.040 |
cheaper | -0.040 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
ind | +0.011 |
iring | +0.011 |
handed | +0.010 |
cheaper | +0.010 |
homeless | +0.010 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.003 |
alk | -0.003 |
imagination | -0.003 |
ids | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
isel | +0.194 |
pan | +0.163 |
kin | +0.159 |
alk | +0.158 |
ids | +0.154 |
Neg logit contributions | |
ind | -0.191 |
iring | -0.189 |
handed | -0.166 |
cheaper | -0.165 |
barking | -0.163 |
Token | She |
Token ID | 1375 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
isel | +0.009 |
It | +0.007 |
alk | +0.006 |
pan | +0.006 |
ids | +0.006 |
Neg logit contributions | |
ind | -0.021 |
iring | -0.020 |
ich | -0.018 |
cheaper | -0.018 |
faster | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
isel | +0.032 |
pan | +0.027 |
kin | +0.026 |
alk | +0.026 |
ids | +0.025 |
Neg logit contributions | |
ind | -0.034 |
iring | -0.034 |
handed | -0.030 |
cheaper | -0.029 |
barking | -0.029 |
Token | excited |
Token ID | 6568 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
isel | +0.016 |
pan | +0.014 |
kin | +0.013 |
idea | +0.013 |
ids | +0.013 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.018 |
handed | -0.016 |
glers | -0.016 |
ll | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
idea | +0.006 |
isel | +0.006 |
imagination | +0.005 |
It | +0.005 |
nod | +0.005 |
Neg logit contributions | |
ind | -0.013 |
iring | -0.012 |
handed | -0.011 |
ich | -0.011 |
fastest | -0.011 |
Token | be |
Token ID | 307 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
isel | +0.022 |
alk | +0.017 |
imagination | +0.016 |
kin | +0.016 |
pan | +0.016 |
Neg logit contributions | |
iring | -0.041 |
ind | -0.041 |
handed | -0.036 |
ich | -0.036 |
cheaper | -0.036 |
Token | alive |
Token ID | 6776 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
isel | +0.028 |
kin | +0.024 |
pan | +0.023 |
ids | +0.023 |
imagination | +0.023 |
Neg logit contributions | |
iring | -0.028 |
ind | -0.027 |
handed | -0.024 |
glers | -0.023 |
barking | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.012 |
kin | +0.011 |
alk | +0.011 |
ids | +0.011 |
Neg logit contributions | |
iring | -0.016 |
ind | -0.016 |
handed | -0.015 |
cheaper | -0.014 |
barking | -0.014 |
Token | long |
Token ID | 890 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
isel | +0.021 |
imagination | +0.018 |
cuc | +0.018 |
kin | +0.017 |
gard | +0.017 |
Neg logit contributions | |
iring | -0.027 |
ind | -0.025 |
glers | -0.023 |
handed | -0.022 |
ning | -0.022 |
Token | time |
Token ID | 640 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.030 |
ids | +0.028 |
kin | +0.027 |
alk | +0.027 |
Neg logit contributions | |
ind | -0.042 |
iring | -0.038 |
barking | -0.037 |
faster | -0.036 |
cheaper | -0.036 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
handed | +0.006 |
cheaper | +0.006 |
homeless | +0.006 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.004 |
alk | -0.004 |
kin | -0.004 |
ids | -0.004 |
Token | ". |
Token ID | 1911 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
isel | +0.194 |
pan | +0.163 |
kin | +0.159 |
alk | +0.158 |
ids | +0.154 |
Neg logit contributions | |
ind | -0.191 |
iring | -0.188 |
handed | -0.166 |
cheaper | -0.164 |
barking | -0.162 |
Token | |
Token ID | 220 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
isel | +0.021 |
It | +0.019 |
nod | +0.015 |
ids | +0.015 |
alk | +0.015 |
Neg logit contributions | |
ind | -0.049 |
iring | -0.045 |
faster | -0.041 |
glers | -0.041 |
nicer | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
ind | +0.022 |
iring | +0.021 |
cheaper | +0.019 |
handed | +0.019 |
faster | +0.019 |
Neg logit contributions | |
isel | -0.015 |
pan | -0.012 |
alk | -0.012 |
kin | -0.012 |
ids | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
isel | +0.007 |
It | +0.006 |
lived | +0.005 |
kin | +0.005 |
ily | +0.005 |
Neg logit contributions | |
ind | -0.024 |
iring | -0.022 |
fastest | -0.021 |
faster | -0.021 |
nicer | -0.021 |
Token | M |
Token ID | 44 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
isel | +0.000 |
kin | +0.000 |
brush | +0.000 |
lived | +0.000 |
ily | +0.000 |
Neg logit contributions | |
iring | -0.001 |
ind | -0.001 |
barking | -0.001 |
faster | -0.001 |
fastest | -0.001 |
Token | vere |
Token ID | 4119 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
ind | +0.038 |
iring | +0.038 |
handed | +0.033 |
cheaper | +0.032 |
faster | +0.032 |
Neg logit contributions | |
isel | -0.049 |
pan | -0.042 |
kin | -0.041 |
alk | -0.041 |
ids | -0.040 |
Token | r |
Token ID | 81 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
ind | +0.025 |
iring | +0.024 |
handed | +0.022 |
barking | +0.022 |
faster | +0.022 |
Neg logit contributions | |
isel | -0.012 |
pan | -0.010 |
kin | -0.009 |
ids | -0.008 |
brush | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
isel | +0.157 |
pan | +0.143 |
alk | +0.141 |
kin | +0.139 |
ids | +0.131 |
Neg logit contributions | |
iring | -0.184 |
ind | -0.184 |
cheaper | -0.169 |
handed | -0.162 |
homeless | -0.161 |
Token | cle |
Token ID | 1190 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.029 |
kin | +0.028 |
lived | +0.028 |
idea | +0.028 |
Neg logit contributions | |
ind | -0.036 |
iring | -0.033 |
handed | -0.029 |
oma | -0.029 |
ich | -0.028 |
Token | vere |
Token ID | 4119 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
ind | +0.019 |
iring | +0.019 |
handed | +0.016 |
cheaper | +0.016 |
faster | +0.016 |
Neg logit contributions | |
isel | -0.028 |
pan | -0.025 |
kin | -0.024 |
alk | -0.024 |
ids | -0.023 |
Token | r |
Token ID | 81 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
ind | +0.022 |
iring | +0.022 |
handed | +0.020 |
barking | +0.020 |
faster | +0.019 |
Neg logit contributions | |
isel | -0.010 |
pan | -0.008 |
kin | -0.008 |
ids | -0.007 |
brush | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
isel | +0.175 |
pan | +0.156 |
alk | +0.154 |
kin | +0.153 |
ids | +0.145 |
Neg logit contributions | |
ind | -0.197 |
iring | -0.197 |
cheaper | -0.180 |
handed | -0.176 |
homeless | -0.174 |
Token | Eventually |
Token ID | 16178 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
isel | +0.006 |
alk | +0.005 |
pan | +0.004 |
ids | +0.004 |
It | +0.004 |
Neg logit contributions | |
ind | -0.012 |
iring | -0.012 |
cheaper | -0.011 |
handed | -0.010 |
homeless | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
isel | +0.026 |
pan | +0.020 |
kin | +0.020 |
alk | +0.019 |
ids | +0.019 |
Neg logit contributions | |
ind | -0.041 |
iring | -0.041 |
handed | -0.037 |
cheaper | -0.037 |
barking | -0.037 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -2.19e-01 |
Pos logit contributions | |
isel | +0.031 |
pan | +0.025 |
alk | +0.025 |
ids | +0.024 |
kin | +0.024 |
Neg logit contributions | |
ind | -0.038 |
iring | -0.038 |
cheaper | -0.034 |
barking | -0.034 |
elderly | -0.033 |
Token | figured |
Token ID | 11638 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
ind | +0.012 |
iring | +0.011 |
cheaper | +0.010 |
handed | +0.010 |
homeless | +0.010 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.005 |
alk | -0.005 |
lived | -0.005 |
kin | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
ind | +0.001 |
iring | +0.001 |
cheaper | +0.001 |
barking | +0.001 |
handed | +0.001 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.002 |
kin | -0.002 |
alk | -0.002 |
ids | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
isel | +0.002 |
pan | +0.001 |
kin | +0.001 |
alk | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.003 |
handed | -0.003 |
cheaper | -0.003 |
barking | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
ily | +0.008 |
idea | +0.008 |
It | +0.008 |
isel | +0.008 |
understand | +0.007 |
Neg logit contributions | |
ind | -0.030 |
iring | -0.027 |
ich | -0.026 |
glers | -0.026 |
handed | -0.025 |
Token | long |
Token ID | 890 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
isel | +0.030 |
idea | +0.027 |
imagination | +0.026 |
alk | +0.026 |
pan | +0.026 |
Neg logit contributions | |
iring | -0.019 |
ind | -0.019 |
handed | -0.016 |
glers | -0.015 |
ized | -0.014 |
Token | time |
Token ID | 640 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
isel | +0.038 |
ids | +0.031 |
pan | +0.030 |
aces | +0.030 |
adders | +0.029 |
Neg logit contributions | |
barking | -0.029 |
ind | -0.028 |
faster | -0.026 |
new | -0.026 |
cheaper | -0.026 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
ind | +0.008 |
iring | +0.008 |
handed | +0.007 |
homeless | +0.006 |
cheaper | +0.006 |
Neg logit contributions | |
isel | -0.008 |
pan | -0.007 |
ids | -0.007 |
kin | -0.007 |
imagination | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
isel | +0.201 |
pan | +0.162 |
alk | +0.160 |
kin | +0.155 |
ids | +0.153 |
Neg logit contributions | |
iring | -0.180 |
ind | -0.179 |
handed | -0.161 |
barking | -0.161 |
cheaper | -0.158 |
Token | Rose |
Token ID | 8049 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
isel | +0.007 |
pan | +0.005 |
alk | +0.005 |
kin | +0.005 |
ids | +0.005 |
Neg logit contributions | |
ind | -0.010 |
iring | -0.010 |
handed | -0.009 |
cheaper | -0.009 |
homeless | -0.009 |
Token | had |
Token ID | 550 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
isel | +0.037 |
pan | +0.030 |
alk | +0.029 |
kin | +0.029 |
ids | +0.028 |
Neg logit contributions | |
ind | -0.039 |
iring | -0.038 |
cheaper | -0.035 |
faster | -0.035 |
handed | -0.035 |
Token | promised |
Token ID | 8072 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
isel | +0.023 |
imagination | +0.019 |
alk | +0.019 |
pan | +0.018 |
aces | +0.018 |
Neg logit contributions | |
ind | -0.034 |
iring | -0.034 |
handed | -0.029 |
ich | -0.029 |
glers | -0.028 |
Token | always |
Token ID | 1464 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
ily | +0.017 |
isel | +0.016 |
imagination | +0.016 |
ids | +0.015 |
It | +0.015 |
Neg logit contributions | |
ind | -0.035 |
glers | -0.032 |
iring | -0.032 |
concession | -0.031 |
handed | -0.030 |
Token | big |
Token ID | 1263 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
isel | +0.027 |
imagination | +0.026 |
idea | +0.025 |
gard | +0.024 |
can | +0.024 |
Neg logit contributions | |
iring | -0.037 |
ind | -0.035 |
glers | -0.031 |
ning | -0.031 |
awed | -0.031 |
Token | farm |
Token ID | 5318 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
isel | +0.035 |
imagination | +0.029 |
pan | +0.029 |
alk | +0.028 |
kin | +0.028 |
Neg logit contributions | |
iring | -0.043 |
ind | -0.042 |
handed | -0.037 |
itating | -0.035 |
glers | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
isel | +0.030 |
kin | +0.030 |
pan | +0.029 |
brush | +0.029 |
ids | +0.027 |
Neg logit contributions | |
ind | -0.055 |
iring | -0.054 |
itating | -0.046 |
Nice | -0.046 |
shadow | -0.045 |
Token | long |
Token ID | 890 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
isel | +0.021 |
imagination | +0.020 |
gard | +0.020 |
cuc | +0.019 |
idea | +0.019 |
Neg logit contributions | |
iring | -0.027 |
ind | -0.024 |
handed | -0.022 |
awed | -0.021 |
ning | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
isel | +0.029 |
pan | +0.023 |
kin | +0.022 |
alk | +0.022 |
ids | +0.022 |
Neg logit contributions | |
ind | -0.037 |
iring | -0.037 |
handed | -0.033 |
cheaper | -0.033 |
barking | -0.033 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
ind | +0.012 |
iring | +0.012 |
handed | +0.011 |
homeless | +0.010 |
cheaper | +0.010 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.004 |
alk | -0.004 |
ids | -0.004 |
imagination | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
isel | +0.186 |
pan | +0.154 |
alk | +0.149 |
kin | +0.149 |
ids | +0.145 |
Neg logit contributions | |
ind | -0.194 |
iring | -0.193 |
handed | -0.171 |
cheaper | -0.169 |
barking | -0.168 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
isel | +0.015 |
pan | +0.012 |
alk | +0.012 |
It | +0.012 |
kin | +0.012 |
Neg logit contributions | |
ind | -0.023 |
iring | -0.022 |
ich | -0.020 |
handed | -0.019 |
barking | -0.019 |
Token | listened |
Token ID | 16399 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
isel | +0.011 |
pan | +0.009 |
kin | +0.009 |
alk | +0.009 |
ids | +0.009 |
Neg logit contributions | |
ind | -0.014 |
iring | -0.014 |
handed | -0.013 |
cheaper | -0.013 |
barking | -0.012 |
Token | as |
Token ID | 355 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
isel | +0.009 |
pan | +0.008 |
alk | +0.008 |
It | +0.008 |
imagination | +0.007 |
Neg logit contributions | |
ind | -0.015 |
iring | -0.015 |
handed | -0.014 |
glers | -0.014 |
ich | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
isel | +0.012 |
kin | +0.011 |
pan | +0.010 |
alk | +0.010 |
ids | +0.010 |
Neg logit contributions | |
ind | -0.015 |
iring | -0.014 |
handed | -0.013 |
cheaper | -0.013 |
barking | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
iring | +0.010 |
ind | +0.009 |
barking | +0.009 |
cheaper | +0.009 |
new | +0.008 |
Neg logit contributions | |
isel | -0.011 |
pan | -0.009 |
kin | -0.009 |
alk | -0.009 |
ids | -0.008 |
Token | gives |
Token ID | 3607 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
isel | +0.002 |
pan | +0.002 |
alk | +0.002 |
kin | +0.002 |
anish | +0.002 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.002 |
cheaper | -0.002 |
faster | -0.001 |
elderly | -0.001 |
Token | some |
Token ID | 617 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
isel | +0.010 |
pan | +0.008 |
ids | +0.008 |
imagination | +0.008 |
kin | +0.008 |
Neg logit contributions | |
iring | -0.014 |
ind | -0.013 |
handed | -0.012 |
homeless | -0.012 |
barking | -0.012 |
Token | neck |
Token ID | 7393 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
isel | +0.048 |
pan | +0.039 |
kin | +0.039 |
alk | +0.038 |
ids | +0.037 |
Neg logit contributions | |
ind | -0.062 |
iring | -0.061 |
handed | -0.055 |
cheaper | -0.054 |
barking | -0.054 |
Token | l |
Token ID | 75 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
isel | +0.133 |
pan | +0.113 |
kin | +0.111 |
alk | +0.110 |
ids | +0.107 |
Neg logit contributions | |
ind | -0.104 |
iring | -0.102 |
cheaper | -0.088 |
handed | -0.088 |
barking | -0.086 |
Token | aces |
Token ID | 2114 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
isel | +0.041 |
pan | +0.029 |
kin | +0.025 |
alk | +0.025 |
ids | +0.023 |
Neg logit contributions | |
iring | -0.093 |
ind | -0.093 |
faster | -0.084 |
barking | -0.084 |
cheaper | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
isel | +0.163 |
pan | +0.140 |
alk | +0.136 |
kin | +0.135 |
ids | +0.133 |
Neg logit contributions | |
ind | -0.217 |
iring | -0.209 |
handed | -0.191 |
barking | -0.185 |
homeless | -0.185 |
Token | her |
Token ID | 607 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
isel | +0.010 |
ids | +0.009 |
kin | +0.008 |
pan | +0.008 |
alk | +0.008 |
Neg logit contributions | |
iring | -0.017 |
ind | -0.017 |
handed | -0.016 |
ich | -0.015 |
homeless | -0.015 |
Token | friends |
Token ID | 2460 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
iring | +0.001 |
ind | +0.001 |
handed | +0.001 |
homeless | +0.001 |
itating | +0.001 |
Neg logit contributions | |
isel | -0.001 |
kin | -0.001 |
imagination | -0.001 |
ids | -0.001 |
alk | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
ind | +0.014 |
iring | +0.014 |
handed | +0.012 |
cheaper | +0.012 |
homeless | +0.012 |
Neg logit contributions | |
isel | -0.012 |
pan | -0.010 |
kin | -0.010 |
alk | -0.010 |
ids | -0.009 |
Token | family |
Token ID | 1641 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
ind | +0.018 |
iring | +0.018 |
cheaper | +0.016 |
barking | +0.016 |
faster | +0.016 |
Neg logit contributions | |
isel | -0.018 |
pan | -0.015 |
kin | -0.015 |
alk | -0.015 |
ids | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
iring | +0.037 |
ind | +0.035 |
handed | +0.033 |
sidelines | +0.033 |
late | +0.031 |
Neg logit contributions | |
lived | -0.014 |
kin | -0.012 |
can | -0.012 |
ids | -0.011 |
isel | -0.011 |
Token | bought |
Token ID | 5839 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
isel | +0.030 |
pan | +0.027 |
kin | +0.026 |
ids | +0.026 |
lived | +0.026 |
Neg logit contributions | |
iring | -0.040 |
ind | -0.040 |
itating | -0.035 |
handed | -0.034 |
concession | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
iring | +0.036 |
ind | +0.035 |
itating | +0.033 |
ich | +0.032 |
shadow | +0.032 |
Neg logit contributions | |
isel | -0.021 |
pan | -0.020 |
kin | -0.020 |
ids | -0.019 |
lived | -0.019 |
Token | long |
Token ID | 890 |
Feature activation | +8.48e-01 |
Pos logit contributions | |
isel | +0.017 |
imagination | +0.017 |
idea | +0.015 |
pan | +0.015 |
tul | +0.015 |
Neg logit contributions | |
iring | -0.026 |
ind | -0.024 |
handed | -0.023 |
ups | -0.021 |
trained | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
isel | +0.031 |
pan | +0.025 |
ids | +0.024 |
alk | +0.024 |
kin | +0.023 |
Neg logit contributions | |
ind | -0.036 |
barking | -0.033 |
iring | -0.033 |
cheaper | -0.032 |
faster | -0.032 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ind | +0.011 |
iring | +0.011 |
handed | +0.010 |
homeless | +0.009 |
cheaper | +0.009 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.005 |
ids | -0.005 |
alk | -0.005 |
kin | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-02 |
Pos logit contributions | |
isel | +0.189 |
pan | +0.158 |
kin | +0.154 |
alk | +0.153 |
ids | +0.149 |
Neg logit contributions | |
ind | -0.191 |
iring | -0.190 |
handed | -0.167 |
cheaper | -0.166 |
barking | -0.164 |
Token | They |
Token ID | 1119 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
isel | +0.001 |
It | +0.001 |
ids | +0.001 |
alk | +0.001 |
pan | +0.001 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.003 |
handed | -0.003 |
cheaper | -0.003 |
faster | -0.003 |
Token | did |
Token ID | 750 |
Feature activation | -9.01e-02 |
Pos logit contributions | |
isel | +0.016 |
pan | +0.013 |
alk | +0.013 |
kin | +0.013 |
ids | +0.012 |
Neg logit contributions | |
ind | -0.019 |
iring | -0.019 |
cheaper | -0.017 |
faster | -0.017 |
homeless | -0.017 |
Token | not |
Token ID | 407 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ind | +0.004 |
iring | +0.004 |
handed | +0.003 |
homeless | +0.003 |
glers | +0.003 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.003 |
alk | -0.003 |
ids | -0.003 |
kin | -0.003 |
Token | know |
Token ID | 760 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ind | +0.037 |
iring | +0.035 |
cheaper | +0.034 |
faster | +0.034 |
barking | +0.034 |
Neg logit contributions | |
isel | -0.017 |
pan | -0.014 |
kin | -0.013 |
alk | -0.012 |
ids | -0.012 |
Token | furry |
Token ID | 40857 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
isel | +0.021 |
kin | +0.020 |
brush | +0.019 |
ids | +0.019 |
aces | +0.019 |
Neg logit contributions | |
handed | -0.034 |
ind | -0.032 |
iring | -0.031 |
concession | -0.028 |
itating | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
isel | +0.021 |
pan | +0.017 |
kin | +0.016 |
alk | +0.016 |
ids | +0.016 |
Neg logit contributions | |
ind | -0.038 |
iring | -0.037 |
handed | -0.035 |
homeless | -0.034 |
cheaper | -0.033 |
Token | some |
Token ID | 617 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
isel | +0.004 |
pan | +0.003 |
brush | +0.003 |
kin | +0.003 |
aces | +0.003 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.006 |
handed | -0.006 |
ich | -0.006 |
ll | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
isel | +0.010 |
kin | +0.008 |
pan | +0.008 |
brush | +0.007 |
imagination | +0.007 |
Neg logit contributions | |
ind | -0.030 |
iring | -0.030 |
handed | -0.028 |
ich | -0.027 |
shadow | -0.027 |
Token | l |
Token ID | 300 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
isel | +0.034 |
aces | +0.031 |
pan | +0.030 |
brush | +0.029 |
ids | +0.029 |
Neg logit contributions | |
iring | -0.060 |
ind | -0.059 |
handed | -0.056 |
itating | -0.054 |
shadow | -0.053 |
Token | aces |
Token ID | 2114 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
iring | +0.020 |
ind | +0.020 |
cheaper | +0.018 |
faster | +0.018 |
handed | +0.018 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.004 |
alk | -0.004 |
kin | -0.004 |
imagination | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
isel | +0.149 |
pan | +0.125 |
alk | +0.121 |
ids | +0.121 |
kin | +0.120 |
Neg logit contributions | |
ind | -0.234 |
iring | -0.223 |
handed | -0.206 |
homeless | -0.201 |
cheaper | -0.199 |
Token | some |
Token ID | 617 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
ind | +0.034 |
iring | +0.034 |
handed | +0.030 |
cheaper | +0.029 |
homeless | +0.029 |
Neg logit contributions | |
isel | -0.029 |
pan | -0.024 |
kin | -0.024 |
alk | -0.023 |
ids | -0.023 |
Token | had |
Token ID | 550 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
isel | +0.001 |
aces | +0.001 |
kin | +0.001 |
pan | +0.001 |
brush | +0.001 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.001 |
handed | -0.001 |
ich | -0.001 |
shadow | -0.001 |
Token | buttons |
Token ID | 12163 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
isel | +0.029 |
aces | +0.027 |
pan | +0.025 |
brush | +0.025 |
ids | +0.025 |
Neg logit contributions | |
iring | -0.048 |
ind | -0.046 |
handed | -0.043 |
itating | -0.042 |
shadow | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
isel | +0.034 |
pan | +0.031 |
ids | +0.031 |
aces | +0.030 |
brush | +0.029 |
Neg logit contributions | |
ind | -0.056 |
iring | -0.054 |
handed | -0.053 |
homeless | -0.051 |
elderly | -0.049 |
Token | famous |
Token ID | 5863 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
isel | +0.003 |
idea | +0.003 |
cuc | +0.003 |
imagination | +0.003 |
thank | +0.003 |
Neg logit contributions | |
iring | -0.004 |
handed | -0.004 |
ind | -0.004 |
ll | -0.004 |
glers | -0.004 |
Token | artist |
Token ID | 6802 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
iring | +0.005 |
ind | +0.005 |
handed | +0.005 |
itating | +0.005 |
glers | +0.005 |
Neg logit contributions | |
isel | -0.004 |
idea | -0.003 |
imagination | -0.003 |
kin | -0.003 |
gard | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.012 |
kin | +0.012 |
alk | +0.012 |
ids | +0.011 |
Neg logit contributions | |
ind | -0.014 |
iring | -0.014 |
handed | -0.012 |
cheaper | -0.012 |
barking | -0.012 |
Token | long |
Token ID | 890 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
isel | +0.009 |
imagination | +0.008 |
cuc | +0.008 |
idea | +0.008 |
kin | +0.008 |
Neg logit contributions | |
iring | -0.011 |
ind | -0.010 |
handed | -0.009 |
glers | -0.009 |
ll | -0.009 |
Token | time |
Token ID | 640 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
isel | +0.025 |
pan | +0.021 |
ids | +0.020 |
kin | +0.020 |
alk | +0.019 |
Neg logit contributions | |
ind | -0.028 |
iring | -0.026 |
barking | -0.025 |
cheaper | -0.024 |
faster | -0.024 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
ind | +0.015 |
iring | +0.015 |
handed | +0.013 |
cheaper | +0.013 |
homeless | +0.013 |
Neg logit contributions | |
isel | -0.011 |
pan | -0.009 |
alk | -0.009 |
ids | -0.009 |
kin | -0.009 |
Token | ." |
Token ID | 526 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
isel | +0.206 |
pan | +0.170 |
alk | +0.166 |
kin | +0.165 |
ids | +0.161 |
Neg logit contributions | |
ind | -0.174 |
iring | -0.172 |
handed | -0.151 |
barking | -0.149 |
cheaper | -0.149 |
Token | |
Token ID | 220 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
isel | +0.053 |
kin | +0.044 |
pan | +0.043 |
alk | +0.038 |
ids | +0.038 |
Neg logit contributions | |
iring | -0.047 |
handed | -0.046 |
ind | -0.045 |
barking | -0.045 |
new | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
iring | +0.020 |
ind | +0.020 |
handed | +0.017 |
cheaper | +0.017 |
barking | +0.017 |
Neg logit contributions | |
isel | -0.017 |
pan | -0.015 |
kin | -0.014 |
alk | -0.014 |
ids | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.010 |
kin | +0.010 |
alk | +0.009 |
ids | +0.009 |
Neg logit contributions | |
ind | -0.012 |
iring | -0.012 |
handed | -0.011 |
barking | -0.011 |
cheaper | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | +7.49e-02 |
Pos logit contributions | |
ind | +0.004 |
iring | +0.004 |
handed | +0.004 |
cheaper | +0.004 |
barking | +0.004 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.005 |
kin | -0.005 |
alk | -0.005 |
ids | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
iring | +0.069 |
ind | +0.068 |
handed | +0.061 |
homeless | +0.060 |
barking | +0.060 |
Neg logit contributions | |
isel | -0.048 |
pan | -0.040 |
kin | -0.038 |
alk | -0.038 |
ids | -0.037 |
Token | away |
Token ID | 1497 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
pan | +0.004 |
isel | +0.004 |
kin | +0.004 |
alk | +0.003 |
brush | +0.003 |
Neg logit contributions | |
ind | -0.005 |
iring | -0.005 |
ica | -0.004 |
homeless | -0.004 |
ich | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ind | +0.015 |
iring | +0.015 |
barking | +0.014 |
handed | +0.014 |
homeless | +0.014 |
Neg logit contributions | |
isel | -0.009 |
kin | -0.009 |
pan | -0.009 |
alk | -0.008 |
aces | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
isel | +0.010 |
kin | +0.009 |
pan | +0.009 |
imagination | +0.008 |
cuc | +0.008 |
Neg logit contributions | |
iring | -0.016 |
ind | -0.014 |
handed | -0.013 |
ning | -0.013 |
glers | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
isel | +0.026 |
adders | +0.022 |
aces | +0.021 |
ids | +0.021 |
pan | +0.020 |
Neg logit contributions | |
ind | -0.023 |
barking | -0.023 |
faster | -0.022 |
cheaper | -0.021 |
homeless | -0.020 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.68e+00 |
Pos logit contributions | |
ind | +0.011 |
iring | +0.011 |
handed | +0.010 |
homeless | +0.010 |
cheaper | +0.010 |
Neg logit contributions | |
isel | -0.007 |
pan | -0.006 |
kin | -0.006 |
alk | -0.006 |
ids | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.97e-02 |
Pos logit contributions | |
isel | +0.195 |
pan | +0.161 |
alk | +0.157 |
kin | +0.157 |
ids | +0.153 |
Neg logit contributions | |
ind | -0.183 |
iring | -0.181 |
handed | -0.160 |
cheaper | -0.158 |
barking | -0.157 |
Token | It |
Token ID | 632 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
iring | +0.003 |
ind | +0.003 |
barking | +0.002 |
handed | +0.002 |
cheaper | +0.002 |
Neg logit contributions | |
isel | -0.003 |
pan | -0.002 |
alk | -0.002 |
kin | -0.002 |
ids | -0.002 |
Token | is |
Token ID | 318 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
isel | +0.039 |
pan | +0.033 |
kin | +0.031 |
alk | +0.031 |
ids | +0.030 |
Neg logit contributions | |
ind | -0.057 |
iring | -0.056 |
handed | -0.051 |
cheaper | -0.049 |
homeless | -0.049 |
Token | not |
Token ID | 407 |
Feature activation | -4.51e-02 |
Pos logit contributions | |
iring | +0.002 |
ind | +0.002 |
handed | +0.002 |
itating | +0.002 |
glers | +0.002 |
Neg logit contributions | |
isel | -0.002 |
kin | -0.002 |
pan | -0.002 |
imagination | -0.002 |
idea | -0.002 |
Token | good |
Token ID | 922 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ind | +0.002 |
iring | +0.002 |
handed | +0.002 |
itating | +0.002 |
concession | +0.002 |
Neg logit contributions | |
isel | -0.002 |
kin | -0.002 |
pan | -0.002 |
imagination | -0.002 |
idea | -0.002 |
Token | do |
Token ID | 466 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
isel | +0.002 |
pan | +0.002 |
brush | +0.002 |
ids | +0.002 |
kin | +0.002 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.003 |
cheaper | -0.002 |
handed | -0.002 |
glers | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
ind | +0.024 |
iring | +0.024 |
cheaper | +0.020 |
handed | +0.020 |
homeless | +0.020 |
Neg logit contributions | |
isel | -0.022 |
kin | -0.019 |
pan | -0.019 |
alk | -0.018 |
ids | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
isel | +0.010 |
pan | +0.009 |
It | +0.009 |
brush | +0.009 |
lived | +0.008 |
Neg logit contributions | |
ind | -0.016 |
iring | -0.015 |
handed | -0.013 |
glers | -0.013 |
ll | -0.013 |
Token | few |
Token ID | 1178 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
isel | +0.004 |
pan | +0.003 |
kin | +0.003 |
idea | +0.003 |
imagination | +0.003 |
Neg logit contributions | |
iring | -0.004 |
ind | -0.004 |
handed | -0.003 |
glers | -0.003 |
itating | -0.003 |
Token | days |
Token ID | 1528 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
isel | +0.017 |
pan | +0.013 |
kin | +0.013 |
alk | +0.013 |
imagination | +0.013 |
Neg logit contributions | |
ind | -0.017 |
iring | -0.017 |
handed | -0.015 |
itating | -0.015 |
cheaper | -0.015 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
isel | +0.058 |
pan | +0.051 |
ids | +0.048 |
kin | +0.048 |
alk | +0.048 |
Neg logit contributions | |
ind | -0.066 |
iring | -0.062 |
cheaper | -0.055 |
handed | -0.054 |
nicer | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
isel | +0.178 |
pan | +0.144 |
alk | +0.141 |
kin | +0.138 |
ids | +0.135 |
Neg logit contributions | |
iring | -0.193 |
ind | -0.192 |
handed | -0.174 |
barking | -0.173 |
faster | -0.170 |
Token | He |
Token ID | 679 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
isel | +0.012 |
alk | +0.009 |
pan | +0.009 |
ids | +0.009 |
It | +0.009 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.021 |
cheaper | -0.019 |
glers | -0.019 |
faster | -0.019 |
Token | started |
Token ID | 2067 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.011 |
kin | +0.011 |
alk | +0.010 |
lived | +0.010 |
Neg logit contributions | |
iring | -0.022 |
ind | -0.022 |
handed | -0.020 |
cheaper | -0.019 |
barking | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +8.01e-02 |
Pos logit contributions | |
iring | +0.001 |
ind | +0.001 |
handed | +0.001 |
cheaper | +0.001 |
homeless | +0.001 |
Neg logit contributions | |
isel | -0.001 |
pan | -0.001 |
alk | -0.001 |
imagination | -0.001 |
ids | -0.001 |
Token | applaud |
Token ID | 22517 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
isel | +0.003 |
pan | +0.002 |
kin | +0.002 |
alk | +0.002 |
ids | +0.002 |
Neg logit contributions | |
ind | -0.004 |
iring | -0.004 |
handed | -0.003 |
cheaper | -0.003 |
barking | -0.003 |
Token | help |
Token ID | 1037 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
isel | +0.033 |
pan | +0.026 |
kin | +0.025 |
alk | +0.025 |
ids | +0.024 |
Neg logit contributions | |
ind | -0.057 |
iring | -0.056 |
handed | -0.051 |
cheaper | -0.050 |
barking | -0.050 |
Token | me |
Token ID | 502 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
iring | +0.016 |
ind | +0.014 |
handed | +0.014 |
barking | +0.013 |
Nice | +0.013 |
Neg logit contributions | |
isel | -0.021 |
pan | -0.019 |
brush | -0.018 |
alk | -0.018 |
kin | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
isel | +0.039 |
pan | +0.033 |
alk | +0.031 |
brush | +0.031 |
kin | +0.031 |
Neg logit contributions | |
ind | -0.054 |
iring | -0.052 |
handed | -0.046 |
barking | -0.046 |
cheaper | -0.045 |
Token | these |
Token ID | 777 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
isel | +0.030 |
pan | +0.027 |
imagination | +0.025 |
ids | +0.025 |
kin | +0.025 |
Neg logit contributions | |
iring | -0.027 |
ind | -0.024 |
handed | -0.022 |
itating | -0.022 |
glers | -0.021 |
Token | l |
Token ID | 300 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.010 |
kin | +0.010 |
alk | +0.010 |
brush | +0.010 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.017 |
barking | -0.016 |
handed | -0.016 |
faster | -0.015 |
Token | aces |
Token ID | 2114 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
iring | +0.014 |
ind | +0.014 |
handed | +0.013 |
cheaper | +0.013 |
elderly | +0.013 |
Neg logit contributions | |
isel | -0.008 |
pan | -0.006 |
alk | -0.005 |
nod | -0.005 |
lived | -0.005 |
Token | ?" |
Token ID | 1701 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
isel | +0.147 |
pan | +0.127 |
alk | +0.122 |
kin | +0.122 |
brush | +0.117 |
Neg logit contributions | |
ind | -0.226 |
iring | -0.218 |
handed | -0.200 |
barking | -0.199 |
cheaper | -0.192 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
isel | +0.030 |
pan | +0.025 |
It | +0.024 |
imagination | +0.024 |
alk | +0.023 |
Neg logit contributions | |
ind | -0.040 |
iring | -0.038 |
handed | -0.033 |
ich | -0.033 |
cheaper | -0.033 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ind | +0.030 |
iring | +0.030 |
handed | +0.026 |
cheaper | +0.026 |
barking | +0.025 |
Neg logit contributions | |
isel | -0.034 |
pan | -0.029 |
kin | -0.029 |
alk | -0.028 |
ids | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
isel | +0.044 |
pan | +0.037 |
kin | +0.036 |
ids | +0.035 |
alk | +0.035 |
Neg logit contributions | |
ind | -0.057 |
iring | -0.055 |
handed | -0.049 |
cheaper | -0.048 |
homeless | -0.048 |
Token |
|
Token ID | 198 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.012 |
kin | +0.012 |
alk | +0.011 |
ids | +0.011 |
Neg logit contributions | |
iring | -0.015 |
ind | -0.015 |
handed | -0.013 |
barking | -0.013 |
cheaper | -0.013 |
Token | colorful |
Token ID | 20239 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
isel | +0.009 |
cuc | +0.008 |
idea | +0.008 |
kin | +0.008 |
brush | +0.008 |
Neg logit contributions | |
ind | -0.011 |
ich | -0.010 |
iring | -0.010 |
itating | -0.010 |
ica | -0.010 |
Token | sk |
Token ID | 1341 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
isel | +0.030 |
pan | +0.027 |
cuc | +0.026 |
kin | +0.026 |
brush | +0.025 |
Neg logit contributions | |
ind | -0.026 |
iring | -0.026 |
handed | -0.023 |
itating | -0.022 |
ich | -0.022 |
Token | ates |
Token ID | 689 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
isel | +0.029 |
pan | +0.024 |
alk | +0.024 |
kin | +0.023 |
imagination | +0.023 |
Neg logit contributions | |
ind | -0.023 |
iring | -0.022 |
handed | -0.020 |
cheaper | -0.018 |
barking | -0.018 |
Token | with |
Token ID | 351 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
isel | +0.020 |
pan | +0.019 |
kin | +0.019 |
ids | +0.017 |
aces | +0.017 |
Neg logit contributions | |
ind | -0.033 |
iring | -0.031 |
handed | -0.029 |
barking | -0.028 |
homeless | -0.027 |
Token | l |
Token ID | 300 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
isel | +0.020 |
cuc | +0.017 |
pan | +0.017 |
imagination | +0.016 |
It | +0.016 |
Neg logit contributions | |
iring | -0.031 |
ind | -0.030 |
ich | -0.028 |
handed | -0.028 |
itating | -0.027 |
Token | aces |
Token ID | 2114 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
ind | +0.016 |
iring | +0.016 |
cheaper | +0.014 |
handed | +0.014 |
faster | +0.014 |
Neg logit contributions | |
isel | -0.008 |
pan | -0.006 |
alk | -0.006 |
kin | -0.006 |
imagination | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
isel | +0.139 |
pan | +0.129 |
aces | +0.122 |
ids | +0.121 |
kin | +0.119 |
Neg logit contributions | |
ind | -0.230 |
iring | -0.216 |
handed | -0.194 |
barking | -0.194 |
concession | -0.193 |
Token |
|
Token ID | 198 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
alk | +0.004 |
kin | +0.004 |
ids | +0.004 |
Neg logit contributions | |
ind | -0.006 |
iring | -0.005 |
handed | -0.005 |
cheaper | -0.005 |
faster | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
ind | +0.019 |
iring | +0.018 |
cheaper | +0.016 |
homeless | +0.016 |
handed | +0.016 |
Neg logit contributions | |
isel | -0.010 |
alk | -0.008 |
pan | -0.008 |
kin | -0.007 |
ids | -0.007 |
Token | On |
Token ID | 2202 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
ind | +0.026 |
iring | +0.025 |
handed | +0.022 |
cheaper | +0.022 |
barking | +0.021 |
Neg logit contributions | |
isel | -0.031 |
pan | -0.027 |
kin | -0.026 |
alk | -0.026 |
ids | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ind | +0.034 |
iring | +0.033 |
handed | +0.029 |
ich | +0.028 |
barking | +0.028 |
Neg logit contributions | |
isel | -0.023 |
pan | -0.020 |
kin | -0.020 |
alk | -0.018 |
ids | -0.017 |
Token | velvet |
Token ID | 47750 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
iring | +0.000 |
ind | +0.000 |
glers | +0.000 |
barking | +0.000 |
shadow | +0.000 |
Neg logit contributions | |
isel | -0.000 |
imagination | -0.000 |
idea | -0.000 |
kin | -0.000 |
pan | -0.000 |
Token | box |
Token ID | 3091 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
isel | +0.043 |
pan | +0.040 |
kin | +0.039 |
alk | +0.037 |
brush | +0.036 |
Neg logit contributions | |
iring | -0.060 |
ind | -0.060 |
handed | -0.053 |
cheaper | -0.053 |
barking | -0.052 |
Token | all |
Token ID | 477 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
pan | +0.004 |
kin | +0.004 |
isel | +0.004 |
brush | +0.004 |
lived | +0.004 |
Neg logit contributions | |
ind | -0.010 |
iring | -0.009 |
handed | -0.008 |
Nice | -0.008 |
homeless | -0.008 |
Token | those |
Token ID | 883 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ind | +0.016 |
iring | +0.016 |
ich | +0.015 |
ograph | +0.014 |
homeless | +0.014 |
Neg logit contributions | |
isel | -0.009 |
lived | -0.009 |
alk | -0.008 |
pan | -0.008 |
idea | -0.008 |
Token | years |
Token ID | 812 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
ind | +0.021 |
barking | +0.021 |
iring | +0.020 |
ich | +0.020 |
handed | +0.020 |
Neg logit contributions | |
lived | -0.017 |
isel | -0.016 |
aces | -0.016 |
imagination | -0.016 |
kin | -0.015 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
isel | +0.036 |
kin | +0.031 |
alk | +0.031 |
pan | +0.031 |
ids | +0.030 |
Neg logit contributions | |
iring | -0.052 |
ind | -0.050 |
handed | -0.049 |
barking | -0.048 |
itating | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
isel | +0.189 |
pan | +0.159 |
kin | +0.155 |
alk | +0.154 |
ids | +0.150 |
Neg logit contributions | |
ind | -0.185 |
iring | -0.183 |
handed | -0.161 |
cheaper | -0.160 |
barking | -0.157 |
Token | They |
Token ID | 1119 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.010 |
alk | +0.010 |
kin | +0.009 |
ids | +0.009 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.021 |
handed | -0.019 |
cheaper | -0.019 |
barking | -0.019 |
Token | were |
Token ID | 547 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
isel | +0.025 |
pan | +0.020 |
kin | +0.020 |
alk | +0.020 |
ids | +0.019 |
Neg logit contributions | |
ind | -0.034 |
iring | -0.034 |
handed | -0.030 |
cheaper | -0.030 |
barking | -0.030 |
Token | glad |
Token ID | 9675 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
isel | +0.009 |
lived | +0.008 |
pan | +0.008 |
kin | +0.008 |
imagination | +0.008 |
Neg logit contributions | |
ind | -0.010 |
iring | -0.010 |
handed | -0.009 |
cheaper | -0.009 |
glers | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ind | +0.016 |
handed | +0.015 |
iring | +0.014 |
fastest | +0.014 |
icycle | +0.014 |
Neg logit contributions | |
isel | -0.008 |
imagination | -0.008 |
It | -0.007 |
lived | -0.007 |
can | -0.007 |
Token | who |
Token ID | 508 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
alk | +0.004 |
ids | +0.004 |
lived | +0.004 |
Neg logit contributions | |
ind | -0.012 |
iring | -0.012 |
handed | -0.011 |
cheaper | -0.011 |
barking | -0.011 |
Token | own |
Token ID | 898 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
iring | +0.054 |
ind | +0.053 |
cheaper | +0.049 |
faster | +0.048 |
barking | +0.048 |
Neg logit contributions | |
isel | -0.026 |
alk | -0.018 |
pan | -0.018 |
lived | -0.018 |
imagination | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
iring | +0.061 |
ind | +0.059 |
handed | +0.053 |
cheaper | +0.053 |
faster | +0.053 |
Neg logit contributions | |
isel | -0.048 |
pan | -0.041 |
lived | -0.041 |
imagination | -0.040 |
alk | -0.039 |
Token | don |
Token ID | 836 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ind | +0.004 |
iring | +0.004 |
handed | +0.004 |
homeless | +0.004 |
cheaper | +0.003 |
Neg logit contributions | |
lived | -0.002 |
isel | -0.002 |
can | -0.002 |
are | -0.002 |
imagination | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
isel | +0.075 |
pan | +0.065 |
kin | +0.064 |
alk | +0.064 |
ids | +0.062 |
Neg logit contributions | |
ind | -0.051 |
iring | -0.050 |
handed | -0.043 |
cheaper | -0.042 |
barking | -0.042 |
Token | actually |
Token ID | 1682 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
iring | +0.035 |
ind | +0.034 |
ning | +0.031 |
handed | +0.031 |
concession | +0.031 |
Neg logit contributions | |
isel | -0.012 |
alk | -0.009 |
understand | -0.008 |
kin | -0.008 |
idea | -0.008 |
Token | live |
Token ID | 2107 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
iring | +0.227 |
ind | +0.223 |
handed | +0.195 |
ich | +0.194 |
itating | +0.193 |
Neg logit contributions | |
isel | -0.099 |
imagination | -0.077 |
alk | -0.077 |
lived | -0.073 |
kin | -0.072 |
Token | there |
Token ID | 612 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
iring | +0.033 |
ind | +0.032 |
sidelines | +0.031 |
handed | +0.031 |
barking | +0.030 |
Neg logit contributions | |
isel | -0.025 |
pan | -0.024 |
kin | -0.024 |
alk | -0.023 |
ids | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
pan | +0.017 |
isel | +0.017 |
alk | +0.017 |
imagination | +0.016 |
kin | +0.016 |
Neg logit contributions | |
ind | -0.041 |
iring | -0.041 |
handed | -0.037 |
ich | -0.036 |
homeless | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
handed | +0.006 |
cheaper | +0.006 |
barking | +0.006 |
Neg logit contributions | |
isel | -0.003 |
pan | -0.003 |
kin | -0.003 |
alk | -0.003 |
ids | -0.002 |
Token | hate |
Token ID | 5465 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
isel | +0.009 |
pan | +0.007 |
alk | +0.006 |
kin | +0.006 |
ids | +0.006 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.022 |
handed | -0.020 |
barking | -0.019 |
cheaper | -0.019 |
Token | couldn |
Token ID | 3521 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
ind | +0.010 |
iring | +0.010 |
handed | +0.009 |
cheaper | +0.009 |
barking | +0.009 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.004 |
kin | -0.004 |
alk | -0.004 |
ids | -0.004 |
Token | â |
Token ID | 22940 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
isel | +0.029 |
pan | +0.025 |
alk | +0.024 |
kin | +0.023 |
ids | +0.023 |
Neg logit contributions | |
ind | -0.036 |
iring | -0.036 |
cheaper | -0.031 |
handed | -0.031 |
barking | -0.031 |
Token | € |
Token ID | 26391 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ind | +0.046 |
iring | +0.045 |
handed | +0.043 |
cheaper | +0.041 |
faster | +0.040 |
Neg logit contributions | |
isel | -0.041 |
pan | -0.035 |
kin | -0.033 |
ids | -0.032 |
cuc | -0.032 |
Token | ™ |
Token ID | 8151 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.005 |
cheaper | +0.004 |
faster | +0.004 |
nicer | +0.004 |
Neg logit contributions | |
isel | -0.004 |
ids | -0.003 |
pan | -0.003 |
alk | -0.003 |
kin | -0.003 |
Token | t |
Token ID | 83 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
isel | +0.013 |
ids | +0.013 |
pan | +0.012 |
brush | +0.012 |
kin | +0.012 |
Neg logit contributions | |
ind | -0.025 |
iring | -0.023 |
nicer | -0.022 |
cheaper | -0.021 |
elderly | -0.021 |
Token | actually |
Token ID | 1682 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
ind | +0.032 |
iring | +0.032 |
handed | +0.029 |
cheaper | +0.029 |
barking | +0.028 |
Neg logit contributions | |
isel | -0.021 |
pan | -0.017 |
kin | -0.016 |
alk | -0.016 |
ids | -0.016 |
Token | hide |
Token ID | 7808 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ind | +0.188 |
iring | +0.187 |
handed | +0.169 |
cheaper | +0.168 |
barking | +0.166 |
Neg logit contributions | |
isel | -0.116 |
pan | -0.093 |
kin | -0.089 |
alk | -0.088 |
ids | -0.085 |
Token | in |
Token ID | 287 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
iring | +0.006 |
ind | +0.006 |
handed | +0.005 |
glers | +0.005 |
barking | +0.005 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.005 |
kin | -0.005 |
ids | -0.004 |
alk | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
isel | +0.025 |
pan | +0.023 |
imagination | +0.022 |
alk | +0.022 |
kin | +0.021 |
Neg logit contributions | |
iring | -0.033 |
ind | -0.031 |
ich | -0.029 |
ll | -0.029 |
glers | -0.029 |
Token | like |
Token ID | 588 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
ich | +0.006 |
homeless | +0.006 |
barking | +0.006 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.004 |
alk | -0.004 |
kin | -0.003 |
aces | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
isel | +0.011 |
imagination | +0.010 |
pan | +0.010 |
lived | +0.010 |
kin | +0.010 |
Neg logit contributions | |
iring | -0.013 |
ind | -0.012 |
itating | -0.011 |
handed | -0.011 |
glers | -0.011 |
Token | see |
Token ID | 766 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
iring | +0.037 |
elderly | +0.036 |
faster | +0.035 |
new | +0.035 |
ind | +0.034 |
Neg logit contributions | |
isel | -0.040 |
kin | -0.037 |
pan | -0.037 |
ids | -0.036 |
pter | -0.034 |
Token | what |
Token ID | 644 |
Feature activation | -6.63e-01 |
Pos logit contributions | |
ind | +0.037 |
iring | +0.036 |
handed | +0.034 |
glers | +0.032 |
homeless | +0.032 |
Neg logit contributions | |
isel | -0.028 |
pan | -0.022 |
imagination | -0.020 |
lived | -0.020 |
alk | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
ind | +0.031 |
iring | +0.031 |
handed | +0.028 |
homeless | +0.027 |
cheaper | +0.027 |
Neg logit contributions | |
isel | -0.022 |
pan | -0.018 |
kin | -0.018 |
lived | -0.017 |
alk | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.005 |
handed | +0.005 |
homeless | +0.004 |
cheaper | +0.004 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.004 |
alk | -0.004 |
kin | -0.004 |
ids | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
ind | +0.025 |
iring | +0.024 |
handed | +0.021 |
cheaper | +0.021 |
barking | +0.021 |
Neg logit contributions | |
isel | -0.026 |
pan | -0.022 |
kin | -0.021 |
alk | -0.021 |
ids | -0.021 |
Token | other |
Token ID | 584 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
ind | +0.050 |
iring | +0.048 |
handed | +0.045 |
cheaper | +0.043 |
barking | +0.042 |
Neg logit contributions | |
isel | -0.047 |
pan | -0.040 |
alk | -0.039 |
kin | -0.038 |
idea | -0.037 |
Token | side |
Token ID | 1735 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
iring | +0.112 |
ind | +0.111 |
faster | +0.094 |
barking | +0.093 |
handed | +0.093 |
Neg logit contributions | |
isel | -0.174 |
pan | -0.152 |
kin | -0.149 |
alk | -0.146 |
ids | -0.144 |
Token | . |
Token ID | 13 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
ind | +0.069 |
iring | +0.060 |
homeless | +0.060 |
handed | +0.058 |
ograph | +0.056 |
Neg logit contributions | |
isel | -0.029 |
alk | -0.023 |
kin | -0.023 |
pan | -0.022 |
aces | -0.022 |
Token | So |
Token ID | 1406 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.006 |
handed | +0.006 |
cheaper | +0.006 |
barking | +0.006 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.005 |
kin | -0.004 |
alk | -0.004 |
ids | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
iring | +0.047 |
ind | +0.047 |
barking | +0.043 |
faster | +0.042 |
cheaper | +0.042 |
Neg logit contributions | |
isel | -0.030 |
pan | -0.024 |
alk | -0.023 |
kin | -0.022 |
ids | -0.022 |
Token | Spot |
Token ID | 15899 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
isel | +0.002 |
kin | +0.002 |
lived | +0.002 |
pan | +0.002 |
It | +0.002 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.002 |
handed | -0.002 |
cheaper | -0.002 |
homeless | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ind | +0.048 |
iring | +0.045 |
handed | +0.044 |
king | +0.040 |
destination | +0.040 |
Neg logit contributions | |
isel | -0.058 |
imagination | -0.052 |
cuc | -0.051 |
lived | -0.051 |
ily | -0.050 |
Token | not |
Token ID | 407 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
isel | +0.039 |
pan | +0.038 |
alk | +0.035 |
imagination | +0.035 |
kin | +0.034 |
Neg logit contributions | |
iring | -0.037 |
ind | -0.037 |
handed | -0.035 |
ups | -0.034 |
cheaper | -0.034 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.012 |
handed | +0.011 |
concession | +0.010 |
glers | +0.010 |
Neg logit contributions | |
isel | -0.016 |
alk | -0.014 |
pan | -0.013 |
kin | -0.013 |
imagination | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
ind | +0.010 |
iring | +0.010 |
handed | +0.009 |
cheaper | +0.009 |
homeless | +0.009 |
Neg logit contributions | |
isel | -0.013 |
kin | -0.011 |
pan | -0.011 |
alk | -0.011 |
ids | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
iring | +0.039 |
ind | +0.037 |
king | +0.034 |
ll | +0.033 |
itating | +0.033 |
Neg logit contributions | |
isel | -0.022 |
alk | -0.021 |
pan | -0.020 |
imagination | -0.019 |
lived | -0.018 |
Token | other |
Token ID | 584 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
iring | +0.068 |
ind | +0.065 |
handed | +0.061 |
homeless | +0.059 |
cheaper | +0.058 |
Neg logit contributions | |
isel | -0.046 |
alk | -0.042 |
imagination | -0.041 |
lived | -0.041 |
kin | -0.041 |
Token | side |
Token ID | 1735 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
iring | +0.138 |
ind | +0.137 |
handed | +0.124 |
homeless | +0.123 |
cheaper | +0.123 |
Neg logit contributions | |
isel | -0.131 |
alk | -0.114 |
kin | -0.111 |
pan | -0.108 |
imagination | -0.108 |
Token | of |
Token ID | 286 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ind | +0.062 |
iring | +0.060 |
homeless | +0.056 |
handed | +0.055 |
security | +0.054 |
Neg logit contributions | |
isel | -0.031 |
alk | -0.030 |
kin | -0.027 |
pan | -0.027 |
brush | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
iring | +0.081 |
ind | +0.079 |
ll | +0.072 |
king | +0.071 |
cheaper | +0.070 |
Neg logit contributions | |
isel | -0.043 |
alk | -0.040 |
pan | -0.037 |
imagination | -0.036 |
kin | -0.032 |
Token | tunnel |
Token ID | 13275 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
iring | +0.024 |
ind | +0.022 |
handed | +0.021 |
homeless | +0.021 |
king | +0.021 |
Neg logit contributions | |
isel | -0.013 |
alk | -0.012 |
imagination | -0.011 |
lived | -0.010 |
idea | -0.010 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ind | +0.028 |
iring | +0.027 |
Mrs | +0.024 |
homeless | +0.024 |
Nice | +0.024 |
Neg logit contributions | |
pan | -0.014 |
isel | -0.013 |
alk | -0.013 |
can | -0.012 |
kin | -0.011 |
Token | grandmother |
Token ID | 18410 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ind | +0.009 |
iring | +0.009 |
shadow | +0.009 |
Nice | +0.008 |
sidelines | +0.008 |
Neg logit contributions | |
idea | -0.007 |
imagination | -0.006 |
kin | -0.005 |
alk | -0.005 |
aces | -0.005 |
Token | who |
Token ID | 508 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
ind | +0.035 |
iring | +0.034 |
ich | +0.029 |
Nice | +0.029 |
handed | +0.028 |
Neg logit contributions | |
idea | -0.017 |
isel | -0.016 |
pan | -0.016 |
ids | -0.016 |
are | -0.016 |
Token | lived |
Token ID | 5615 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
ind | +0.048 |
iring | +0.047 |
handed | +0.042 |
king | +0.042 |
faster | +0.041 |
Neg logit contributions | |
lived | -0.017 |
isel | -0.015 |
kin | -0.012 |
can | -0.012 |
are | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
kin | +0.024 |
isel | +0.022 |
ily | +0.021 |
pan | +0.020 |
alk | +0.020 |
Neg logit contributions | |
iring | -0.038 |
ind | -0.037 |
sidelines | -0.036 |
handed | -0.035 |
cheaper | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
iring | +0.024 |
ll | +0.022 |
ind | +0.022 |
itating | +0.021 |
shadow | +0.021 |
Neg logit contributions | |
alk | -0.008 |
imagination | -0.008 |
isel | -0.008 |
pan | -0.008 |
lived | -0.007 |
Token | other |
Token ID | 584 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
iring | +0.047 |
ind | +0.045 |
shadow | +0.040 |
cheaper | +0.040 |
barking | +0.039 |
Neg logit contributions | |
isel | -0.036 |
alk | -0.033 |
pan | -0.032 |
kin | -0.031 |
imagination | -0.031 |
Token | side |
Token ID | 1735 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ind | +0.128 |
iring | +0.126 |
handed | +0.110 |
cheaper | +0.108 |
barking | +0.107 |
Neg logit contributions | |
isel | -0.152 |
pan | -0.129 |
kin | -0.126 |
alk | -0.125 |
ids | -0.122 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ind | +0.061 |
iring | +0.058 |
homeless | +0.054 |
cheaper | +0.052 |
shadow | +0.052 |
Neg logit contributions | |
isel | -0.022 |
kin | -0.022 |
alk | -0.022 |
ily | -0.021 |
ids | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
iring | +0.075 |
ind | +0.071 |
ll | +0.065 |
itating | +0.065 |
cheaper | +0.064 |
Neg logit contributions | |
isel | -0.041 |
alk | -0.037 |
pan | -0.037 |
imagination | -0.034 |
kin | -0.033 |
Token | wall |
Token ID | 3355 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.011 |
cheaper | +0.010 |
shadow | +0.010 |
handed | +0.010 |
Neg logit contributions | |
isel | -0.010 |
alk | -0.009 |
imagination | -0.009 |
pan | -0.009 |
kin | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
isel | +0.027 |
pan | +0.026 |
alk | +0.025 |
kin | +0.024 |
aces | +0.024 |
Neg logit contributions | |
ind | -0.059 |
iring | -0.057 |
homeless | -0.051 |
ich | -0.050 |
cheaper | -0.049 |
Token | even |
Token ID | 772 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
isel | +0.025 |
imagination | +0.022 |
It | +0.021 |
brush | +0.021 |
pan | +0.020 |
Neg logit contributions | |
ind | -0.040 |
iring | -0.038 |
handed | -0.035 |
glers | -0.034 |
itating | -0.032 |
Token | though |
Token ID | 996 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
isel | +0.006 |
cuc | +0.005 |
kin | +0.004 |
pan | +0.004 |
imagination | +0.004 |
Neg logit contributions | |
ind | -0.012 |
iring | -0.011 |
handed | -0.011 |
ich | -0.011 |
destination | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
isel | +0.058 |
lived | +0.052 |
kin | +0.052 |
imagination | +0.050 |
alk | +0.047 |
Neg logit contributions | |
ind | -0.099 |
iring | -0.094 |
handed | -0.090 |
cheaper | -0.084 |
itating | -0.084 |
Token | did |
Token ID | 750 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
iring | +0.059 |
ind | +0.057 |
cheaper | +0.052 |
handed | +0.051 |
ours | +0.051 |
Neg logit contributions | |
isel | -0.025 |
lived | -0.022 |
kin | -0.020 |
imagination | -0.018 |
can | -0.018 |
Token | not |
Token ID | 407 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.011 |
imagination | +0.011 |
alk | +0.011 |
brush | +0.010 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.018 |
handed | -0.016 |
ich | -0.016 |
glers | -0.015 |
Token | actually |
Token ID | 1682 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ind | +0.026 |
iring | +0.025 |
handed | +0.023 |
cheaper | +0.023 |
barking | +0.022 |
Neg logit contributions | |
isel | -0.014 |
pan | -0.011 |
alk | -0.011 |
kin | -0.011 |
ids | -0.010 |
Token | win |
Token ID | 1592 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
ind | +0.178 |
iring | +0.177 |
handed | +0.152 |
ich | +0.150 |
cheaper | +0.149 |
Neg logit contributions | |
isel | -0.108 |
alk | -0.081 |
kin | -0.081 |
imagination | -0.079 |
pan | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
ind | +0.078 |
iring | +0.075 |
ich | +0.068 |
concession | +0.067 |
handed | +0.067 |
Neg logit contributions | |
isel | -0.047 |
aces | -0.041 |
alk | -0.041 |
kin | -0.041 |
lived | -0.038 |
Token | competition |
Token ID | 5449 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
iring | +0.018 |
ind | +0.018 |
handed | +0.015 |
barking | +0.015 |
glers | +0.015 |
Neg logit contributions | |
isel | -0.013 |
kin | -0.011 |
imagination | -0.011 |
idea | -0.011 |
alk | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
ind | +0.040 |
iring | +0.037 |
homeless | +0.032 |
ich | +0.032 |
handed | +0.032 |
Neg logit contributions | |
isel | -0.019 |
pan | -0.017 |
idea | -0.017 |
lived | -0.017 |
aces | -0.017 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
isel | +0.014 |
alk | +0.011 |
pan | +0.010 |
kin | +0.010 |
ids | +0.010 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.021 |
cheaper | -0.019 |
faster | -0.019 |
handed | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ind | +0.001 |
iring | +0.001 |
barking | +0.001 |
faster | +0.001 |
handed | +0.001 |
Neg logit contributions | |
isel | -0.001 |
pan | -0.001 |
alk | -0.001 |
kin | -0.001 |
ids | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ind | +0.009 |
iring | +0.009 |
handed | +0.008 |
cheaper | +0.008 |
barking | +0.008 |
Neg logit contributions | |
isel | -0.008 |
pan | -0.007 |
kin | -0.007 |
alk | -0.007 |
ids | -0.007 |
Token | cat |
Token ID | 3797 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
iring | +0.010 |
ind | +0.009 |
handed | +0.009 |
ups | +0.008 |
shadow | +0.008 |
Neg logit contributions | |
isel | -0.008 |
kin | -0.008 |
gard | -0.007 |
idea | -0.007 |
pan | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
isel | +0.016 |
pan | +0.014 |
kin | +0.014 |
alk | +0.014 |
ids | +0.013 |
Neg logit contributions | |
iring | -0.018 |
ind | -0.018 |
cheaper | -0.016 |
handed | -0.015 |
homeless | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
iring | +0.015 |
ind | +0.015 |
handed | +0.013 |
cheaper | +0.013 |
homeless | +0.013 |
Neg logit contributions | |
isel | -0.012 |
pan | -0.010 |
alk | -0.010 |
kin | -0.010 |
ids | -0.009 |
Token | other |
Token ID | 584 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
iring | +0.066 |
ind | +0.063 |
shadow | +0.059 |
cheaper | +0.058 |
handed | +0.057 |
Neg logit contributions | |
pan | -0.035 |
isel | -0.034 |
alk | -0.034 |
gard | -0.033 |
brush | -0.032 |
Token | side |
Token ID | 1735 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ind | +0.124 |
iring | +0.123 |
handed | +0.106 |
cheaper | +0.105 |
barking | +0.103 |
Neg logit contributions | |
isel | -0.152 |
pan | -0.131 |
kin | -0.128 |
alk | -0.128 |
ids | -0.125 |
Token | of |
Token ID | 286 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ind | +0.055 |
iring | +0.052 |
homeless | +0.049 |
cheaper | +0.049 |
handed | +0.047 |
Neg logit contributions | |
isel | -0.033 |
alk | -0.029 |
kin | -0.028 |
pan | -0.026 |
ids | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
iring | +0.093 |
ind | +0.092 |
ll | +0.087 |
itating | +0.085 |
cheaper | +0.082 |
Neg logit contributions | |
isel | -0.045 |
pan | -0.040 |
alk | -0.038 |
It | -0.036 |
soil | -0.036 |
Token | wire |
Token ID | 6503 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
iring | +0.003 |
ind | +0.002 |
handed | +0.002 |
shadow | +0.002 |
glers | +0.002 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.001 |
brush | -0.001 |
alk | -0.001 |
kin | -0.001 |
Token | fence |
Token ID | 13990 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
handed | +0.006 |
cheaper | +0.006 |
homeless | +0.006 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.004 |
kin | -0.004 |
alk | -0.004 |
lived | -0.004 |
Token | know |
Token ID | 760 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ind | +0.037 |
iring | +0.036 |
handed | +0.034 |
elderly | +0.033 |
barking | +0.033 |
Neg logit contributions | |
isel | -0.033 |
pan | -0.028 |
kin | -0.027 |
ids | -0.026 |
alk | -0.025 |
Token | what |
Token ID | 644 |
Feature activation | -7.44e-01 |
Pos logit contributions | |
isel | +0.009 |
pan | +0.008 |
lived | +0.008 |
imagination | +0.007 |
brush | +0.007 |
Neg logit contributions | |
ind | -0.015 |
handed | -0.014 |
iring | -0.014 |
barking | -0.013 |
ich | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
ind | +0.029 |
iring | +0.029 |
handed | +0.025 |
cheaper | +0.025 |
barking | +0.024 |
Neg logit contributions | |
isel | -0.031 |
pan | -0.027 |
kin | -0.026 |
alk | -0.026 |
ids | -0.025 |
Token | on |
Token ID | 319 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
iring | +0.003 |
ind | +0.003 |
handed | +0.003 |
concession | +0.003 |
sidelines | +0.003 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.002 |
aces | -0.002 |
ids | -0.002 |
ily | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
iring | +0.021 |
ind | +0.021 |
handed | +0.019 |
barking | +0.018 |
ll | +0.018 |
Neg logit contributions | |
isel | -0.017 |
pan | -0.015 |
alk | -0.015 |
kin | -0.014 |
imagination | -0.014 |
Token | other |
Token ID | 584 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
shadow | +0.053 |
awed | +0.049 |
iring | +0.048 |
ounce | +0.046 |
arrested | +0.046 |
Neg logit contributions | |
gard | -0.033 |
idea | -0.031 |
soil | -0.030 |
cuc | -0.030 |
tul | -0.029 |
Token | side |
Token ID | 1735 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
iring | +0.150 |
ind | +0.147 |
cheaper | +0.134 |
shadow | +0.132 |
handed | +0.132 |
Neg logit contributions | |
isel | -0.111 |
imagination | -0.099 |
kin | -0.099 |
alk | -0.098 |
ids | -0.097 |
Token | of |
Token ID | 286 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
ind | +0.062 |
iring | +0.056 |
homeless | +0.054 |
handed | +0.053 |
concession | +0.052 |
Neg logit contributions | |
isel | -0.024 |
brush | -0.023 |
ids | -0.023 |
alk | -0.023 |
kin | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
iring | +0.071 |
ind | +0.070 |
handed | +0.061 |
ll | +0.060 |
cheaper | +0.060 |
Neg logit contributions | |
isel | -0.047 |
pan | -0.041 |
alk | -0.040 |
kin | -0.038 |
imagination | -0.038 |
Token | big |
Token ID | 1263 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
shadow | +0.021 |
iring | +0.020 |
king | +0.020 |
awed | +0.019 |
arrested | +0.019 |
Neg logit contributions | |
imagination | -0.012 |
isel | -0.012 |
soil | -0.011 |
alk | -0.011 |
idea | -0.011 |
Token | door |
Token ID | 3420 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ind | +0.003 |
iring | +0.003 |
handed | +0.003 |
cheaper | +0.003 |
homeless | +0.003 |
Neg logit contributions | |
isel | -0.003 |
pan | -0.003 |
alk | -0.003 |
kin | -0.003 |
ids | -0.003 |
Token | who |
Token ID | 508 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
isel | +0.008 |
kin | +0.007 |
lived | +0.007 |
pan | +0.007 |
alk | +0.007 |
Neg logit contributions | |
iring | -0.013 |
ind | -0.013 |
handed | -0.011 |
cheaper | -0.011 |
homeless | -0.011 |
Token | never |
Token ID | 1239 |
Feature activation | -4.55e-01 |
Pos logit contributions | |
iring | +0.064 |
ind | +0.063 |
cheaper | +0.058 |
handed | +0.056 |
homeless | +0.056 |
Neg logit contributions | |
isel | -0.032 |
lived | -0.025 |
imagination | -0.025 |
alk | -0.024 |
ids | -0.023 |
Token | explores |
Token ID | 25409 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ind | +0.024 |
iring | +0.024 |
handed | +0.021 |
cheaper | +0.021 |
ich | +0.020 |
Neg logit contributions | |
isel | -0.013 |
alk | -0.010 |
pan | -0.010 |
imagination | -0.010 |
kin | -0.010 |
Token | will |
Token ID | 481 |
Feature activation | -7.97e-01 |
Pos logit contributions | |
iring | +0.049 |
ind | +0.049 |
handed | +0.045 |
homeless | +0.043 |
cheaper | +0.043 |
Neg logit contributions | |
isel | -0.036 |
alk | -0.035 |
pan | -0.031 |
lived | -0.031 |
imagination | -0.031 |
Token | never |
Token ID | 1239 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ind | +0.039 |
iring | +0.039 |
cheaper | +0.034 |
handed | +0.034 |
homeless | +0.033 |
Neg logit contributions | |
isel | -0.024 |
alk | -0.022 |
pan | -0.021 |
kin | -0.020 |
ids | -0.019 |
Token | truly |
Token ID | 4988 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ind | +0.006 |
iring | +0.006 |
handed | +0.006 |
concession | +0.005 |
cheaper | +0.005 |
Neg logit contributions | |
isel | -0.003 |
alk | -0.003 |
understand | -0.003 |
nod | -0.003 |
idea | -0.003 |
Token | know |
Token ID | 760 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
ind | +0.169 |
iring | +0.167 |
cheaper | +0.149 |
handed | +0.149 |
barking | +0.147 |
Neg logit contributions | |
isel | -0.108 |
pan | -0.085 |
alk | -0.084 |
kin | -0.083 |
ids | -0.079 |
Token | what |
Token ID | 644 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
isel | +0.007 |
pan | +0.006 |
imagination | +0.006 |
lived | +0.006 |
aces | +0.006 |
Neg logit contributions | |
ind | -0.009 |
iring | -0.009 |
handed | -0.008 |
glers | -0.008 |
barking | -0.008 |
Token | is |
Token ID | 318 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
ind | +0.019 |
iring | +0.018 |
handed | +0.016 |
cheaper | +0.016 |
homeless | +0.016 |
Neg logit contributions | |
isel | -0.018 |
alk | -0.015 |
pan | -0.015 |
imagination | -0.015 |
kin | -0.015 |
Token | around |
Token ID | 1088 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
ind | +0.004 |
iring | +0.004 |
handed | +0.004 |
glers | +0.004 |
concession | +0.004 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.003 |
imagination | -0.003 |
alk | -0.003 |
kin | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
isel | +0.026 |
alk | +0.024 |
lived | +0.023 |
pan | +0.023 |
imagination | +0.023 |
Neg logit contributions | |
iring | -0.018 |
ind | -0.017 |
cheaper | -0.017 |
handed | -0.015 |
homeless | -0.015 |
Token | big |
Token ID | 1263 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
iring | +0.004 |
ind | +0.004 |
handed | +0.003 |
ups | +0.003 |
shadow | +0.003 |
Neg logit contributions | |
isel | -0.003 |
kin | -0.003 |
cuc | -0.003 |
gard | -0.003 |
idea | -0.003 |
Token | banana |
Token ID | 25996 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
isel | +0.015 |
pan | +0.012 |
kin | +0.012 |
alk | +0.012 |
imagination | +0.011 |
Neg logit contributions | |
iring | -0.019 |
ind | -0.019 |
handed | -0.017 |
cheaper | -0.016 |
faster | -0.016 |
Token | tree |
Token ID | 5509 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
isel | +0.001 |
pan | +0.001 |
kin | +0.001 |
alk | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.001 |
iring | -0.001 |
handed | -0.001 |
cheaper | -0.001 |
homeless | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
isel | +0.019 |
alk | +0.017 |
pan | +0.017 |
kin | +0.017 |
lived | +0.016 |
Neg logit contributions | |
ind | -0.023 |
iring | -0.022 |
cheaper | -0.021 |
handed | -0.021 |
concession | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
cheaper | +0.006 |
handed | +0.006 |
homeless | +0.006 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.005 |
alk | -0.004 |
kin | -0.004 |
ids | -0.004 |
Token | other |
Token ID | 584 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
iring | +0.064 |
ind | +0.062 |
cheaper | +0.057 |
barking | +0.056 |
shadow | +0.056 |
Neg logit contributions | |
isel | -0.036 |
pan | -0.032 |
alk | -0.032 |
cuc | -0.030 |
kin | -0.030 |
Token | side |
Token ID | 1735 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ind | +0.121 |
iring | +0.120 |
handed | +0.104 |
cheaper | +0.101 |
barking | +0.101 |
Neg logit contributions | |
isel | -0.156 |
pan | -0.134 |
kin | -0.131 |
alk | -0.129 |
ids | -0.127 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
ind | +0.057 |
iring | +0.052 |
homeless | +0.051 |
cheaper | +0.050 |
nicer | +0.049 |
Neg logit contributions | |
isel | -0.029 |
alk | -0.027 |
kin | -0.025 |
ily | -0.023 |
pan | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
ind | +0.081 |
iring | +0.080 |
ll | +0.071 |
itating | +0.071 |
cheaper | +0.071 |
Neg logit contributions | |
isel | -0.047 |
pan | -0.038 |
alk | -0.038 |
cuc | -0.036 |
kin | -0.034 |
Token | island |
Token ID | 7022 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
iring | +0.025 |
shadow | +0.022 |
king | +0.022 |
itating | +0.022 |
ind | +0.022 |
Neg logit contributions | |
isel | -0.014 |
alk | -0.014 |
lived | -0.013 |
soil | -0.013 |
cuc | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
ind | +0.013 |
iring | +0.012 |
ica | +0.011 |
ograph | +0.011 |
cheaper | +0.011 |
Neg logit contributions | |
lived | -0.004 |
isel | -0.004 |
alk | -0.004 |
kin | -0.004 |
pan | -0.004 |
Token | flashlight |
Token ID | 38371 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
isel | +0.006 |
kin | +0.005 |
pan | +0.005 |
brush | +0.005 |
imagination | +0.005 |
Neg logit contributions | |
iring | -0.008 |
ind | -0.008 |
handed | -0.007 |
itating | -0.006 |
ning | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +9.51e-02 |
Pos logit contributions | |
ind | +0.012 |
iring | +0.012 |
handed | +0.011 |
homeless | +0.011 |
cheaper | +0.010 |
Neg logit contributions | |
pan | -0.009 |
isel | -0.008 |
brush | -0.008 |
kin | -0.007 |
alk | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
isel | +0.003 |
pan | +0.002 |
brush | +0.002 |
ids | +0.002 |
aces | +0.002 |
Neg logit contributions | |
ind | -0.005 |
iring | -0.005 |
handed | -0.004 |
itating | -0.004 |
glers | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
ind | +0.018 |
iring | +0.017 |
handed | +0.015 |
itating | +0.015 |
ich | +0.015 |
Neg logit contributions | |
isel | -0.011 |
pan | -0.010 |
kin | -0.009 |
imagination | -0.009 |
brush | -0.009 |
Token | magn |
Token ID | 7842 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
iring | +0.011 |
ind | +0.010 |
handed | +0.009 |
itating | +0.009 |
shadow | +0.008 |
Neg logit contributions | |
isel | -0.008 |
pan | -0.007 |
kin | -0.007 |
imagination | -0.007 |
brush | -0.007 |
Token | ifying |
Token ID | 4035 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
ind | +0.023 |
iring | +0.022 |
handed | +0.020 |
cheaper | +0.019 |
homeless | +0.019 |
Neg logit contributions | |
isel | -0.036 |
pan | -0.032 |
ids | -0.031 |
alk | -0.030 |
kin | -0.030 |
Token | glass |
Token ID | 5405 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
ind | +0.150 |
iring | +0.148 |
handed | +0.133 |
cheaper | +0.132 |
barking | +0.130 |
Neg logit contributions | |
isel | -0.123 |
pan | -0.101 |
kin | -0.098 |
alk | -0.097 |
ids | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
isel | +0.007 |
pan | +0.007 |
kin | +0.006 |
brush | +0.006 |
alk | +0.006 |
Neg logit contributions | |
ind | -0.010 |
iring | -0.010 |
handed | -0.008 |
homeless | -0.008 |
barking | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
isel | +0.000 |
pan | +0.000 |
kin | +0.000 |
alk | +0.000 |
ids | +0.000 |
Neg logit contributions | |
ind | -0.001 |
iring | -0.001 |
handed | -0.000 |
cheaper | -0.000 |
barking | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
ind | +0.006 |
iring | +0.006 |
handed | +0.005 |
cheaper | +0.005 |
barking | +0.005 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.004 |
kin | -0.004 |
alk | -0.004 |
ids | -0.004 |
Token | As |
Token ID | 1722 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
ind | +0.017 |
iring | +0.017 |
handed | +0.015 |
cheaper | +0.015 |
faster | +0.015 |
Neg logit contributions | |
isel | -0.016 |
pan | -0.013 |
alk | -0.013 |
kin | -0.012 |
ids | -0.012 |
Token | explore |
Token ID | 7301 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
iring | +0.036 |
ind | +0.035 |
elderly | +0.034 |
faster | +0.033 |
handed | +0.033 |
Neg logit contributions | |
isel | -0.035 |
kin | -0.031 |
pan | -0.030 |
ids | -0.029 |
alk | -0.028 |
Token | what |
Token ID | 644 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
ind | +0.060 |
iring | +0.060 |
handed | +0.056 |
homeless | +0.053 |
ich | +0.053 |
Neg logit contributions | |
isel | -0.032 |
pan | -0.026 |
alk | -0.025 |
lived | -0.024 |
imagination | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
ind | +0.036 |
iring | +0.034 |
king | +0.032 |
handed | +0.032 |
sidelines | +0.031 |
Neg logit contributions | |
isel | -0.017 |
lived | -0.016 |
It | -0.013 |
brush | -0.013 |
can | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
ind | +0.000 |
iring | +0.000 |
handed | +0.000 |
concession | +0.000 |
glers | +0.000 |
Neg logit contributions | |
isel | -0.000 |
pan | -0.000 |
alk | -0.000 |
idea | -0.000 |
lived | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ind | +0.024 |
iring | +0.024 |
handed | +0.022 |
ll | +0.022 |
barking | +0.021 |
Neg logit contributions | |
isel | -0.017 |
pan | -0.014 |
alk | -0.014 |
kin | -0.013 |
imagination | -0.013 |
Token | other |
Token ID | 584 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
ind | +0.040 |
iring | +0.040 |
handed | +0.036 |
glers | +0.034 |
barking | +0.034 |
Neg logit contributions | |
isel | -0.040 |
pan | -0.035 |
alk | -0.034 |
kin | -0.033 |
idea | -0.032 |
Token | side |
Token ID | 1735 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ind | +0.113 |
iring | +0.112 |
handed | +0.094 |
cheaper | +0.094 |
barking | +0.094 |
Neg logit contributions | |
isel | -0.162 |
pan | -0.140 |
kin | -0.137 |
alk | -0.134 |
ids | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
ind | +0.064 |
iring | +0.057 |
homeless | +0.057 |
concession | +0.054 |
handed | +0.054 |
Neg logit contributions | |
isel | -0.026 |
alk | -0.022 |
ids | -0.021 |
kin | -0.021 |
aces | -0.020 |
Token | so |
Token ID | 523 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.010 |
idea | +0.010 |
imagination | +0.010 |
It | +0.010 |
Neg logit contributions | |
ind | -0.016 |
iring | -0.014 |
handed | -0.014 |
ich | -0.012 |
glers | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
ind | +0.009 |
iring | +0.008 |
handed | +0.008 |
cheaper | +0.007 |
barking | +0.007 |
Neg logit contributions | |
isel | -0.010 |
pan | -0.008 |
kin | -0.008 |
lived | -0.008 |
alk | -0.008 |
Token | flew |
Token ID | 13112 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ind | +0.023 |
iring | +0.023 |
faster | +0.021 |
cheaper | +0.021 |
barking | +0.021 |
Neg logit contributions | |
isel | -0.018 |
pan | -0.015 |
alk | -0.015 |
kin | -0.015 |
ids | -0.014 |
Token | see |
Token ID | 766 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
iring | +0.032 |
ind | +0.030 |
elderly | +0.029 |
new | +0.029 |
barking | +0.028 |
Neg logit contributions | |
isel | -0.031 |
kin | -0.031 |
pan | -0.029 |
ids | -0.029 |
aces | -0.027 |
Token | what |
Token ID | 644 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
ind | +0.028 |
iring | +0.027 |
handed | +0.026 |
glers | +0.024 |
concession | +0.024 |
Neg logit contributions | |
isel | -0.019 |
pan | -0.015 |
imagination | -0.014 |
cuc | -0.014 |
ids | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
ind | +0.024 |
iring | +0.023 |
handed | +0.021 |
barking | +0.020 |
homeless | +0.020 |
Neg logit contributions | |
isel | -0.016 |
pan | -0.013 |
lived | -0.013 |
kin | -0.013 |
alk | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
isel | +0.003 |
pan | +0.002 |
kin | +0.002 |
alk | +0.002 |
ids | +0.002 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.002 |
handed | -0.002 |
cheaper | -0.002 |
homeless | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
ind | +0.019 |
iring | +0.018 |
handed | +0.016 |
cheaper | +0.016 |
barking | +0.016 |
Neg logit contributions | |
isel | -0.018 |
pan | -0.015 |
alk | -0.015 |
kin | -0.015 |
ids | -0.014 |
Token | other |
Token ID | 584 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
ind | +0.042 |
iring | +0.041 |
handed | +0.037 |
cheaper | +0.036 |
barking | +0.036 |
Neg logit contributions | |
isel | -0.037 |
pan | -0.031 |
alk | -0.030 |
kin | -0.029 |
ids | -0.029 |
Token | side |
Token ID | 1735 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
iring | +0.102 |
ind | +0.101 |
barking | +0.086 |
faster | +0.084 |
elderly | +0.084 |
Neg logit contributions | |
isel | -0.170 |
pan | -0.151 |
kin | -0.146 |
alk | -0.140 |
ids | -0.139 |
Token | of |
Token ID | 286 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ind | +0.058 |
iring | +0.051 |
homeless | +0.050 |
handed | +0.049 |
concession | +0.048 |
Neg logit contributions | |
isel | -0.024 |
kin | -0.019 |
alk | -0.019 |
pan | -0.019 |
brush | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
ind | +0.059 |
iring | +0.058 |
handed | +0.051 |
cheaper | +0.050 |
barking | +0.050 |
Neg logit contributions | |
isel | -0.057 |
pan | -0.048 |
alk | -0.047 |
kin | -0.047 |
ids | -0.045 |
Token | wall |
Token ID | 3355 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ind | +0.015 |
iring | +0.015 |
handed | +0.013 |
barking | +0.013 |
elderly | +0.013 |
Neg logit contributions | |
isel | -0.013 |
pan | -0.011 |
kin | -0.011 |
ids | -0.011 |
alk | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
isel | +0.027 |
pan | +0.026 |
kin | +0.024 |
aces | +0.024 |
alk | +0.023 |
Neg logit contributions | |
ind | -0.064 |
iring | -0.060 |
homeless | -0.056 |
handed | -0.054 |
ich | -0.054 |
Token | friend |
Token ID | 1545 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
ind | +0.003 |
handed | +0.003 |
shadow | +0.003 |
iring | +0.003 |
concession | +0.003 |
Neg logit contributions | |
kin | -0.002 |
idea | -0.002 |
imagination | -0.002 |
isel | -0.002 |
brush | -0.002 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
ind | +0.061 |
iring | +0.058 |
handed | +0.054 |
izing | +0.053 |
cheaper | +0.052 |
Neg logit contributions | |
lived | -0.019 |
nod | -0.016 |
It | -0.016 |
ily | -0.015 |
are | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
iring | +0.009 |
ind | +0.009 |
cheaper | +0.008 |
handed | +0.008 |
homeless | +0.008 |
Neg logit contributions | |
isel | -0.010 |
pan | -0.009 |
alk | -0.009 |
ids | -0.009 |
lived | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
iring | +0.013 |
ind | +0.012 |
cheaper | +0.011 |
handed | +0.011 |
ours | +0.010 |
Neg logit contributions | |
lived | -0.008 |
isel | -0.007 |
pan | -0.007 |
nod | -0.007 |
ids | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
iring | +0.008 |
ind | +0.007 |
cheaper | +0.007 |
shadow | +0.007 |
ll | +0.007 |
Neg logit contributions | |
isel | -0.005 |
alk | -0.004 |
pan | -0.004 |
kin | -0.004 |
imagination | -0.004 |
Token | other |
Token ID | 584 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
iring | +0.059 |
ind | +0.058 |
cheaper | +0.052 |
shadow | +0.052 |
handed | +0.051 |
Neg logit contributions | |
isel | -0.034 |
pan | -0.033 |
alk | -0.031 |
gard | -0.030 |
kin | -0.029 |
Token | side |
Token ID | 1735 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ind | +0.109 |
iring | +0.106 |
barking | +0.093 |
handed | +0.092 |
faster | +0.091 |
Neg logit contributions | |
isel | -0.167 |
pan | -0.142 |
kin | -0.139 |
alk | -0.136 |
ids | -0.134 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
ind | +0.060 |
iring | +0.057 |
homeless | +0.054 |
cheaper | +0.053 |
shadow | +0.051 |
Neg logit contributions | |
isel | -0.026 |
alk | -0.024 |
pan | -0.024 |
kin | -0.023 |
brush | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
iring | +0.073 |
ind | +0.072 |
cheaper | +0.063 |
ll | +0.063 |
handed | +0.062 |
Neg logit contributions | |
isel | -0.046 |
pan | -0.040 |
alk | -0.039 |
kin | -0.036 |
imagination | -0.035 |
Token | fence |
Token ID | 13990 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
iring | +0.020 |
ind | +0.019 |
shadow | +0.018 |
king | +0.018 |
cheaper | +0.017 |
Neg logit contributions | |
isel | -0.015 |
alk | -0.015 |
gard | -0.014 |
soil | -0.014 |
pan | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ind | +0.000 |
iring | +0.000 |
homeless | +0.000 |
cheaper | +0.000 |
shadow | +0.000 |
Neg logit contributions | |
isel | -0.000 |
pan | -0.000 |
alk | -0.000 |
lived | -0.000 |
kin | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
ind | +0.040 |
iring | +0.037 |
Nice | +0.035 |
handed | +0.034 |
oma | +0.033 |
Neg logit contributions | |
pan | -0.020 |
brush | -0.019 |
isel | -0.018 |
kin | -0.018 |
ids | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
isel | +0.013 |
lived | +0.012 |
idea | +0.011 |
imagination | +0.011 |
understand | +0.011 |
Neg logit contributions | |
ind | -0.027 |
iring | -0.027 |
itating | -0.026 |
king | -0.025 |
ll | -0.025 |
Token | house |
Token ID | 2156 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
cuc | +0.001 |
can | +0.001 |
isel | +0.001 |
imagination | +0.001 |
seed | +0.001 |
Neg logit contributions | |
iring | -0.001 |
ind | -0.001 |
awed | -0.001 |
itating | -0.001 |
handed | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
isel | +0.015 |
pan | +0.014 |
brush | +0.012 |
kin | +0.012 |
alk | +0.012 |
Neg logit contributions | |
ind | -0.019 |
iring | -0.019 |
handed | -0.016 |
cheaper | -0.016 |
ich | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
isel | +0.001 |
pan | +0.001 |
alk | +0.001 |
It | +0.001 |
lived | +0.001 |
Neg logit contributions | |
ll | -0.004 |
iring | -0.004 |
ind | -0.004 |
shadow | -0.004 |
itating | -0.004 |
Token | other |
Token ID | 584 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
iring | +0.064 |
shadow | +0.062 |
rou | +0.059 |
ounce | +0.059 |
awed | +0.059 |
Neg logit contributions | |
roof | -0.036 |
gard | -0.035 |
pan | -0.034 |
soil | -0.033 |
gen | -0.031 |
Token | side |
Token ID | 1735 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
iring | +0.145 |
ind | +0.141 |
cheaper | +0.126 |
itating | +0.125 |
faster | +0.124 |
Neg logit contributions | |
isel | -0.113 |
pan | -0.099 |
lived | -0.098 |
alk | -0.098 |
kin | -0.094 |
Token | of |
Token ID | 286 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ind | +0.060 |
iring | +0.057 |
homeless | +0.052 |
cheaper | +0.052 |
nicer | +0.051 |
Neg logit contributions | |
isel | -0.028 |
alk | -0.024 |
pan | -0.024 |
kin | -0.023 |
ids | -0.023 |
Token | town |
Token ID | 3240 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
iring | +0.080 |
ind | +0.077 |
ll | +0.074 |
itating | +0.073 |
fastest | +0.070 |
Neg logit contributions | |
isel | -0.040 |
pan | -0.036 |
alk | -0.032 |
imagination | -0.031 |
kin | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
isel | +0.001 |
lived | +0.000 |
alk | +0.000 |
pan | +0.000 |
ids | +0.000 |
Neg logit contributions | |
ind | -0.001 |
iring | -0.001 |
Nice | -0.001 |
nicer | -0.001 |
cheaper | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
ind | +0.002 |
iring | +0.002 |
handed | +0.002 |
ich | +0.002 |
cheaper | +0.001 |
Neg logit contributions | |
isel | -0.001 |
It | -0.001 |
imagination | -0.001 |
ids | -0.001 |
lived | -0.001 |
Token | bull |
Token ID | 6473 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
iring | +0.017 |
shadow | +0.017 |
handed | +0.016 |
ind | +0.016 |
har | +0.016 |
Neg logit contributions | |
isel | -0.007 |
idea | -0.007 |
gard | -0.007 |
soil | -0.007 |
imagination | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
iring | +0.087 |
ind | +0.085 |
cheaper | +0.074 |
handed | +0.073 |
homeless | +0.073 |
Neg logit contributions | |
isel | -0.035 |
pan | -0.035 |
alk | -0.034 |
ids | -0.034 |
lived | -0.032 |
Token | play |
Token ID | 711 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
iring | +0.020 |
ind | +0.020 |
handed | +0.017 |
cheaper | +0.017 |
barking | +0.017 |
Neg logit contributions | |
isel | -0.013 |
pan | -0.010 |
kin | -0.010 |
alk | -0.010 |
ids | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
ind | +0.002 |
iring | +0.002 |
cheaper | +0.002 |
handed | +0.002 |
homeless | +0.002 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.002 |
kin | -0.002 |
alk | -0.002 |
ids | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
iring | +0.031 |
ind | +0.029 |
itating | +0.027 |
ll | +0.026 |
shadow | +0.026 |
Neg logit contributions | |
isel | -0.012 |
pan | -0.011 |
alk | -0.010 |
It | -0.010 |
imagination | -0.010 |
Token | other |
Token ID | 584 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
iring | +0.058 |
ind | +0.053 |
handed | +0.051 |
cheaper | +0.050 |
itating | +0.049 |
Neg logit contributions | |
isel | -0.037 |
pan | -0.036 |
bee | -0.034 |
soil | -0.033 |
alk | -0.032 |
Token | side |
Token ID | 1735 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
iring | +0.138 |
ind | +0.132 |
cheaper | +0.121 |
handed | +0.119 |
homeless | +0.119 |
Neg logit contributions | |
isel | -0.124 |
alk | -0.108 |
pan | -0.107 |
kin | -0.103 |
aces | -0.101 |
Token | of |
Token ID | 286 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ind | +0.064 |
iring | +0.063 |
homeless | +0.061 |
shadow | +0.058 |
ograph | +0.057 |
Neg logit contributions | |
isel | -0.026 |
kin | -0.024 |
alk | -0.024 |
ily | -0.023 |
pan | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
iring | +0.076 |
ind | +0.074 |
handed | +0.067 |
cheaper | +0.066 |
homeless | +0.065 |
Neg logit contributions | |
isel | -0.051 |
pan | -0.043 |
alk | -0.042 |
kin | -0.038 |
imagination | -0.038 |
Token | park |
Token ID | 3952 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
iring | +0.025 |
handed | +0.022 |
ind | +0.022 |
shadow | +0.022 |
itating | +0.022 |
Neg logit contributions | |
isel | -0.014 |
alk | -0.013 |
soil | -0.013 |
pan | -0.012 |
gard | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ind | +0.046 |
iring | +0.045 |
shadow | +0.040 |
ograph | +0.039 |
homeless | +0.039 |
Neg logit contributions | |
isel | -0.017 |
kin | -0.016 |
pan | -0.016 |
lived | -0.016 |
alk | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
ind | +0.024 |
iring | +0.024 |
handed | +0.020 |
faster | +0.020 |
barking | +0.020 |
Neg logit contributions | |
isel | -0.028 |
pan | -0.023 |
alk | -0.023 |
kin | -0.023 |
ids | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | +2.59e-01 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.012 |
handed | +0.011 |
faster | +0.010 |
cheaper | +0.010 |
Neg logit contributions | |
isel | -0.012 |
kin | -0.010 |
pan | -0.010 |
cuc | -0.010 |
brush | -0.010 |
Token | box |
Token ID | 3091 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
isel | +0.010 |
pan | +0.008 |
kin | +0.008 |
ids | +0.008 |
alk | +0.008 |
Neg logit contributions | |
ind | -0.011 |
iring | -0.011 |
barking | -0.010 |
cheaper | -0.010 |
faster | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
isel | +0.007 |
pan | +0.006 |
kin | +0.006 |
alk | +0.006 |
ids | +0.006 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.007 |
handed | -0.006 |
cheaper | -0.006 |
barking | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ind | +0.004 |
iring | +0.004 |
new | +0.003 |
elderly | +0.003 |
cheaper | +0.003 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.005 |
kin | -0.005 |
ids | -0.005 |
alk | -0.005 |
Token | other |
Token ID | 584 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
iring | +0.060 |
ind | +0.057 |
shadow | +0.056 |
barking | +0.054 |
cheaper | +0.052 |
Neg logit contributions | |
isel | -0.031 |
pan | -0.031 |
soil | -0.029 |
alk | -0.028 |
gard | -0.028 |
Token | side |
Token ID | 1735 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ind | +0.107 |
iring | +0.103 |
handed | +0.088 |
cheaper | +0.085 |
barking | +0.085 |
Neg logit contributions | |
isel | -0.170 |
pan | -0.146 |
kin | -0.141 |
alk | -0.139 |
ids | -0.138 |
Token | of |
Token ID | 286 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ind | +0.049 |
iring | +0.047 |
homeless | +0.043 |
cheaper | +0.042 |
handed | +0.042 |
Neg logit contributions | |
isel | -0.036 |
alk | -0.031 |
kin | -0.031 |
pan | -0.031 |
ids | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
ind | +0.068 |
iring | +0.068 |
handed | +0.060 |
cheaper | +0.059 |
barking | +0.058 |
Neg logit contributions | |
isel | -0.064 |
pan | -0.054 |
alk | -0.052 |
kin | -0.052 |
ids | -0.050 |
Token | room |
Token ID | 2119 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
iring | +0.022 |
shadow | +0.021 |
king | +0.020 |
ind | +0.020 |
itating | +0.019 |
Neg logit contributions | |
isel | -0.014 |
imagination | -0.013 |
soil | -0.013 |
alk | -0.013 |
gard | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.011 |
kin | +0.011 |
alk | +0.011 |
ids | +0.011 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.017 |
cheaper | -0.015 |
homeless | -0.015 |
handed | -0.015 |
Token | see |
Token ID | 766 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
iring | +0.037 |
ind | +0.035 |
faster | +0.035 |
elderly | +0.034 |
destination | +0.033 |
Neg logit contributions | |
isel | -0.033 |
pan | -0.030 |
kin | -0.030 |
ids | -0.029 |
alk | -0.028 |
Token | what |
Token ID | 644 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
ind | +0.028 |
iring | +0.027 |
handed | +0.025 |
homeless | +0.024 |
barking | +0.024 |
Neg logit contributions | |
isel | -0.024 |
pan | -0.020 |
alk | -0.018 |
kin | -0.018 |
ids | -0.018 |
Token | is |
Token ID | 318 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ind | +0.026 |
iring | +0.026 |
cheaper | +0.023 |
handed | +0.023 |
barking | +0.023 |
Neg logit contributions | |
isel | -0.022 |
pan | -0.018 |
kin | -0.017 |
alk | -0.017 |
ids | -0.017 |
Token | on |
Token ID | 319 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ind | +0.017 |
iring | +0.017 |
handed | +0.015 |
homeless | +0.014 |
cheaper | +0.014 |
Neg logit contributions | |
isel | -0.019 |
pan | -0.016 |
kin | -0.016 |
alk | -0.016 |
ids | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -9.96e-01 |
Pos logit contributions | |
ind | +0.019 |
iring | +0.019 |
cheaper | +0.017 |
handed | +0.017 |
faster | +0.017 |
Neg logit contributions | |
isel | -0.020 |
pan | -0.017 |
kin | -0.017 |
alk | -0.017 |
ids | -0.016 |
Token | other |
Token ID | 584 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
ind | +0.046 |
iring | +0.044 |
handed | +0.042 |
barking | +0.040 |
homeless | +0.040 |
Neg logit contributions | |
isel | -0.033 |
alk | -0.028 |
pan | -0.027 |
kin | -0.027 |
idea | -0.026 |
Token | side |
Token ID | 1735 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ind | +0.117 |
iring | +0.116 |
handed | +0.100 |
cheaper | +0.099 |
barking | +0.098 |
Neg logit contributions | |
isel | -0.153 |
pan | -0.132 |
kin | -0.129 |
alk | -0.128 |
ids | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
ind | +0.063 |
iring | +0.057 |
homeless | +0.055 |
handed | +0.055 |
concession | +0.052 |
Neg logit contributions | |
isel | -0.028 |
alk | -0.024 |
kin | -0.024 |
pan | -0.024 |
ids | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.012 |
barking | +0.011 |
cheaper | +0.011 |
handed | +0.011 |
Neg logit contributions | |
isel | -0.011 |
pan | -0.009 |
kin | -0.009 |
alk | -0.009 |
ids | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
ind | +0.029 |
iring | +0.029 |
handed | +0.026 |
cheaper | +0.026 |
homeless | +0.025 |
Neg logit contributions | |
isel | -0.022 |
pan | -0.017 |
alk | -0.017 |
kin | -0.017 |
ids | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
ind | +0.039 |
iring | +0.038 |
handed | +0.034 |
cheaper | +0.033 |
barking | +0.033 |
Neg logit contributions | |
isel | -0.040 |
pan | -0.033 |
kin | -0.033 |
alk | -0.032 |
ids | -0.031 |
Token | pipe |
Token ID | 12656 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
iring | +0.027 |
ind | +0.027 |
cheaper | +0.023 |
barking | +0.023 |
handed | +0.023 |
Neg logit contributions | |
isel | -0.028 |
pan | -0.025 |
kin | -0.024 |
ids | -0.023 |
alk | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
ind | +0.048 |
iring | +0.047 |
homeless | +0.041 |
handed | +0.041 |
cheaper | +0.040 |
Neg logit contributions | |
isel | -0.028 |
pan | -0.026 |
brush | -0.025 |
kin | -0.025 |
aces | -0.024 |
Token | he |
Token ID | 339 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
handed | +0.006 |
cheaper | +0.006 |
homeless | +0.006 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.005 |
kin | -0.005 |
alk | -0.005 |
imagination | -0.005 |
Token | could |
Token ID | 714 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
iring | +0.053 |
ind | +0.052 |
handed | +0.047 |
cheaper | +0.046 |
barking | +0.046 |
Neg logit contributions | |
isel | -0.030 |
pan | -0.024 |
kin | -0.023 |
lived | -0.023 |
alk | -0.022 |
Token | never |
Token ID | 1239 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
isel | +0.002 |
pan | +0.002 |
alk | +0.002 |
kin | +0.002 |
ids | +0.002 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.003 |
handed | -0.002 |
cheaper | -0.002 |
homeless | -0.002 |
Token | truly |
Token ID | 4988 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ind | +0.012 |
iring | +0.012 |
handed | +0.011 |
cheaper | +0.011 |
elderly | +0.010 |
Neg logit contributions | |
isel | -0.009 |
pan | -0.007 |
alk | -0.007 |
kin | -0.007 |
ids | -0.007 |
Token | hate |
Token ID | 5465 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ind | +0.162 |
iring | +0.161 |
handed | +0.145 |
cheaper | +0.144 |
barking | +0.142 |
Neg logit contributions | |
isel | -0.106 |
pan | -0.085 |
kin | -0.082 |
alk | -0.081 |
ids | -0.078 |
Token | it |
Token ID | 340 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
ind | +0.022 |
iring | +0.021 |
handed | +0.019 |
cheaper | +0.019 |
glers | +0.019 |
Neg logit contributions | |
isel | -0.015 |
pan | -0.012 |
alk | -0.012 |
imagination | -0.011 |
kin | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
ind | +0.019 |
iring | +0.017 |
glers | +0.016 |
ich | +0.016 |
concession | +0.015 |
Neg logit contributions | |
kin | -0.010 |
aces | -0.009 |
pan | -0.009 |
isel | -0.009 |
idea | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
isel | +0.017 |
pan | +0.014 |
kin | +0.014 |
alk | +0.013 |
ids | +0.013 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.018 |
handed | -0.016 |
cheaper | -0.016 |
barking | -0.016 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ind | +0.060 |
iring | +0.059 |
cheaper | +0.053 |
handed | +0.052 |
homeless | +0.051 |
Neg logit contributions | |
isel | -0.048 |
pan | -0.040 |
kin | -0.039 |
alk | -0.039 |
ids | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
lived | +0.001 |
isel | +0.001 |
can | +0.001 |
kin | +0.001 |
pan | +0.001 |
Neg logit contributions | |
iring | -0.003 |
ind | -0.003 |
handed | -0.003 |
sidelines | -0.003 |
cheaper | -0.003 |
Token | unusual |
Token ID | 8468 |
Feature activation | -5.56e-02 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.014 |
spr | +0.013 |
kin | +0.013 |
imagination | +0.013 |
Neg logit contributions | |
handed | -0.021 |
iring | -0.020 |
ind | -0.019 |
concession | -0.019 |
sidelines | -0.018 |
Token | - |
Token ID | 532 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
ind | +0.003 |
iring | +0.003 |
handed | +0.003 |
homeless | +0.002 |
Mrs | +0.002 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.001 |
imagination | -0.001 |
idea | -0.001 |
alk | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +2.14e-02 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.004 |
handed | +0.004 |
glers | +0.004 |
ll | +0.004 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.002 |
imagination | -0.002 |
It | -0.002 |
kin | -0.002 |
Token | could |
Token ID | 714 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
isel | +0.000 |
lived | +0.000 |
kin | +0.000 |
pan | +0.000 |
can | +0.000 |
Neg logit contributions | |
ind | -0.001 |
iring | -0.001 |
handed | -0.001 |
cheaper | -0.001 |
sidelines | -0.001 |
Token | actually |
Token ID | 1682 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
isel | +0.010 |
pan | +0.008 |
alk | +0.008 |
kin | +0.008 |
ids | +0.008 |
Neg logit contributions | |
ind | -0.017 |
iring | -0.017 |
handed | -0.016 |
cheaper | -0.015 |
homeless | -0.014 |
Token | sing |
Token ID | 1702 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
iring | +0.166 |
ind | +0.166 |
handed | +0.148 |
cheaper | +0.146 |
homeless | +0.143 |
Neg logit contributions | |
isel | -0.103 |
pan | -0.082 |
alk | -0.081 |
kin | -0.080 |
ids | -0.077 |
Token | words |
Token ID | 2456 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ind | +0.024 |
iring | +0.024 |
handed | +0.022 |
cheaper | +0.021 |
homeless | +0.021 |
Neg logit contributions | |
isel | -0.018 |
kin | -0.016 |
pan | -0.016 |
alk | -0.015 |
lived | -0.015 |
Token | ! |
Token ID | 0 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
pan | +0.033 |
isel | +0.031 |
brush | +0.031 |
ids | +0.029 |
can | +0.028 |
Neg logit contributions | |
ind | -0.065 |
iring | -0.062 |
handed | -0.061 |
homeless | -0.057 |
ich | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.005 |
cheaper | +0.005 |
handed | +0.005 |
faster | +0.005 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.003 |
alk | -0.003 |
kin | -0.003 |
ids | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
isel | +0.000 |
pan | +0.000 |
kin | +0.000 |
alk | +0.000 |
ids | +0.000 |
Neg logit contributions | |
ind | -0.001 |
iring | -0.001 |
handed | -0.001 |
cheaper | -0.001 |
barking | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.010 |
kin | +0.009 |
alk | +0.009 |
aces | +0.008 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.021 |
cheaper | -0.020 |
handed | -0.020 |
barking | -0.020 |
Token | breakfast |
Token ID | 12607 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
isel | +0.006 |
imagination | +0.005 |
cuc | +0.004 |
pan | +0.004 |
brush | +0.004 |
Neg logit contributions | |
iring | -0.009 |
ind | -0.008 |
glers | -0.008 |
itating | -0.007 |
handed | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
ind | +0.014 |
iring | +0.014 |
handed | +0.012 |
barking | +0.012 |
homeless | +0.012 |
Neg logit contributions | |
isel | -0.011 |
kin | -0.011 |
pan | -0.010 |
brush | -0.010 |
ids | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | +9.14e-02 |
Pos logit contributions | |
isel | +0.004 |
imagination | +0.003 |
kin | +0.003 |
idea | +0.003 |
pan | +0.003 |
Neg logit contributions | |
iring | -0.005 |
ind | -0.005 |
handed | -0.004 |
glers | -0.004 |
ich | -0.004 |
Token | while |
Token ID | 981 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
isel | +0.003 |
pan | +0.003 |
idea | +0.003 |
imagination | +0.003 |
kin | +0.003 |
Neg logit contributions | |
ind | -0.004 |
iring | -0.004 |
handed | -0.003 |
ich | -0.003 |
itating | -0.003 |
Token | ago |
Token ID | 2084 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
ind | +0.028 |
iring | +0.027 |
handed | +0.025 |
glers | +0.024 |
cheaper | +0.023 |
Neg logit contributions | |
isel | -0.020 |
kin | -0.018 |
pan | -0.018 |
ids | -0.017 |
imagination | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
isel | +0.137 |
pan | +0.111 |
kin | +0.107 |
alk | +0.107 |
ids | +0.103 |
Neg logit contributions | |
ind | -0.185 |
iring | -0.183 |
handed | -0.165 |
cheaper | -0.163 |
barking | -0.162 |
Token | so |
Token ID | 523 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
isel | +0.011 |
pan | +0.009 |
kin | +0.009 |
imagination | +0.009 |
ids | +0.009 |
Neg logit contributions | |
ind | -0.012 |
iring | -0.012 |
handed | -0.010 |
glers | -0.010 |
cheaper | -0.010 |
Token | I |
Token ID | 314 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ind | +0.020 |
iring | +0.019 |
handed | +0.017 |
cheaper | +0.017 |
homeless | +0.017 |
Neg logit contributions | |
isel | -0.020 |
kin | -0.016 |
imagination | -0.016 |
lived | -0.016 |
pan | -0.015 |
Token | 'm |
Token ID | 1101 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
isel | +0.016 |
pan | +0.013 |
kin | +0.012 |
alk | +0.012 |
ids | +0.012 |
Neg logit contributions | |
ind | -0.026 |
iring | -0.025 |
cheaper | -0.023 |
handed | -0.023 |
barking | -0.023 |
Token | not |
Token ID | 407 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
ind | +0.029 |
iring | +0.029 |
handed | +0.025 |
glers | +0.024 |
cheaper | +0.023 |
Neg logit contributions | |
isel | -0.036 |
pan | -0.032 |
ids | -0.030 |
kin | -0.030 |
imagination | -0.029 |
Token | Her |
Token ID | 2332 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
isel | +0.001 |
It | +0.001 |
pan | +0.001 |
imagination | +0.001 |
alk | +0.001 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.002 |
handed | -0.002 |
faster | -0.002 |
fastest | -0.002 |
Token | grandma |
Token ID | 49890 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
iring | +0.006 |
ind | +0.006 |
glers | +0.006 |
handed | +0.006 |
itating | +0.006 |
Neg logit contributions | |
imagination | -0.006 |
idea | -0.005 |
brush | -0.005 |
kin | -0.005 |
nod | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.012 |
handed | +0.011 |
sidelines | +0.011 |
itating | +0.011 |
Neg logit contributions | |
lived | -0.006 |
isel | -0.005 |
kin | -0.005 |
pan | -0.004 |
can | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
brush | +0.014 |
imagination | +0.014 |
lived | +0.014 |
pan | +0.013 |
aces | +0.013 |
Neg logit contributions | |
iring | -0.039 |
ind | -0.037 |
itating | -0.034 |
izing | -0.033 |
handed | -0.032 |
Token | delicate |
Token ID | 19217 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
isel | +0.006 |
imagination | +0.005 |
idea | +0.005 |
kin | +0.005 |
pan | +0.005 |
Neg logit contributions | |
iring | -0.006 |
ind | -0.006 |
handed | -0.006 |
glers | -0.005 |
ups | -0.005 |
Token | v |
Token ID | 410 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
isel | +0.036 |
pan | +0.029 |
alk | +0.028 |
kin | +0.028 |
ids | +0.027 |
Neg logit contributions | |
ind | -0.044 |
iring | -0.044 |
cheaper | -0.039 |
barking | -0.039 |
handed | -0.039 |
Token | ase |
Token ID | 589 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
isel | +0.095 |
pan | +0.074 |
alk | +0.072 |
kin | +0.069 |
ids | +0.068 |
Neg logit contributions | |
ind | -0.144 |
iring | -0.143 |
handed | -0.130 |
cheaper | -0.124 |
barking | -0.124 |
Token | on |
Token ID | 319 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
brush | +0.062 |
kin | +0.060 |
pan | +0.059 |
aces | +0.055 |
isel | +0.053 |
Neg logit contributions | |
ind | -0.099 |
iring | -0.097 |
handed | -0.083 |
cheaper | -0.083 |
Nice | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
iring | +0.000 |
ind | +0.000 |
handed | +0.000 |
ll | +0.000 |
cheaper | +0.000 |
Neg logit contributions | |
isel | -0.000 |
pan | -0.000 |
kin | -0.000 |
alk | -0.000 |
imagination | -0.000 |
Token | table |
Token ID | 3084 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
iring | +0.049 |
shadow | +0.043 |
itating | +0.043 |
ind | +0.041 |
Nice | +0.041 |
Neg logit contributions | |
pan | -0.023 |
tul | -0.022 |
brush | -0.021 |
roof | -0.020 |
kin | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -6.13e-03 |
Pos logit contributions | |
pan | +0.035 |
isel | +0.034 |
kin | +0.034 |
brush | +0.032 |
ids | +0.031 |
Neg logit contributions | |
ind | -0.059 |
iring | -0.057 |
homeless | -0.050 |
cheaper | -0.049 |
shadow | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
isel | +0.008 |
pan | +0.007 |
brush | +0.007 |
ids | +0.006 |
It | +0.006 |
Neg logit contributions | |
ind | -0.019 |
ich | -0.017 |
iring | -0.016 |
homeless | -0.016 |
handed | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
isel | +0.001 |
pan | +0.000 |
kin | +0.000 |
alk | +0.000 |
ids | +0.000 |
Neg logit contributions | |
iring | -0.001 |
ind | -0.001 |
barking | -0.001 |
handed | -0.001 |
cheaper | -0.001 |
Token | used |
Token ID | 973 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.009 |
kin | +0.009 |
ids | +0.009 |
lived | +0.009 |
Neg logit contributions | |
iring | -0.019 |
ind | -0.019 |
handed | -0.017 |
cheaper | -0.016 |
homeless | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ind | +0.003 |
iring | +0.003 |
cheaper | +0.003 |
handed | +0.003 |
faster | +0.003 |
Neg logit contributions | |
isel | -0.003 |
pan | -0.002 |
kin | -0.002 |
alk | -0.002 |
ids | -0.002 |
Token | m |
Token ID | 285 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
isel | +0.043 |
pan | +0.036 |
kin | +0.035 |
alk | +0.035 |
ids | +0.034 |
Neg logit contributions | |
ind | -0.041 |
iring | -0.041 |
handed | -0.035 |
barking | -0.034 |
cheaper | -0.034 |
Token | itt |
Token ID | 715 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
isel | +0.050 |
pan | +0.042 |
alk | +0.042 |
kin | +0.041 |
ids | +0.038 |
Neg logit contributions | |
iring | -0.063 |
ind | -0.063 |
handed | -0.056 |
cheaper | -0.055 |
homeless | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
isel | +0.134 |
pan | +0.114 |
kin | +0.112 |
alk | +0.111 |
ids | +0.108 |
Neg logit contributions | |
ind | -0.111 |
iring | -0.110 |
handed | -0.095 |
cheaper | -0.094 |
barking | -0.093 |
Token | take |
Token ID | 1011 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.028 |
kin | +0.027 |
alk | +0.025 |
ids | +0.025 |
Neg logit contributions | |
ind | -0.062 |
iring | -0.061 |
handed | -0.055 |
barking | -0.054 |
cheaper | -0.053 |
Token | out |
Token ID | 503 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
isel | +0.009 |
pan | +0.008 |
ids | +0.007 |
kin | +0.007 |
alk | +0.007 |
Neg logit contributions | |
ind | -0.012 |
iring | -0.012 |
handed | -0.011 |
barking | -0.011 |
homeless | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ind | +0.011 |
iring | +0.011 |
handed | +0.010 |
ich | +0.010 |
homeless | +0.010 |
Neg logit contributions | |
isel | -0.008 |
pan | -0.007 |
ids | -0.006 |
brush | -0.006 |
kin | -0.006 |
Token | pan |
Token ID | 3425 |
Feature activation | +8.47e-01 |
Pos logit contributions | |
isel | +0.010 |
pan | +0.009 |
kin | +0.008 |
imagination | +0.008 |
brush | +0.008 |
Neg logit contributions | |
iring | -0.013 |
ind | -0.013 |
barking | -0.012 |
handed | -0.011 |
glers | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
isel | +0.010 |
pan | +0.008 |
alk | +0.008 |
kin | +0.008 |
ids | +0.008 |
Neg logit contributions | |
ind | -0.017 |
iring | -0.017 |
cheaper | -0.015 |
handed | -0.015 |
homeless | -0.015 |
Token | George |
Token ID | 20191 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ind | +0.001 |
iring | +0.001 |
barking | +0.001 |
cheaper | +0.001 |
handed | +0.001 |
Neg logit contributions | |
isel | -0.001 |
pan | -0.001 |
kin | -0.001 |
brush | -0.001 |
alk | -0.001 |
Token | yelled |
Token ID | 22760 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
iring | +0.024 |
ind | +0.024 |
handed | +0.022 |
cheaper | +0.022 |
homeless | +0.022 |
Neg logit contributions | |
isel | -0.016 |
kin | -0.013 |
lived | -0.013 |
pan | -0.013 |
alk | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
ind | +0.009 |
iring | +0.009 |
handed | +0.008 |
cheaper | +0.008 |
barking | +0.008 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.005 |
kin | -0.005 |
alk | -0.005 |
ids | -0.005 |
Token | g |
Token ID | 308 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
isel | +0.058 |
pan | +0.052 |
alk | +0.051 |
kin | +0.050 |
ids | +0.050 |
Neg logit contributions | |
iring | -0.051 |
ind | -0.051 |
faster | -0.050 |
barking | -0.046 |
new | -0.046 |
Token | lee |
Token ID | 7197 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
isel | +0.017 |
pan | +0.015 |
kin | +0.014 |
brush | +0.013 |
alk | +0.013 |
Neg logit contributions | |
ind | -0.023 |
iring | -0.023 |
handed | -0.019 |
barking | -0.019 |
elderly | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
isel | +0.092 |
pan | +0.077 |
kin | +0.073 |
alk | +0.073 |
ids | +0.072 |
Neg logit contributions | |
ind | -0.148 |
iring | -0.145 |
handed | -0.130 |
cheaper | -0.130 |
homeless | -0.127 |
Token | scrambled |
Token ID | 34351 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.010 |
lived | +0.010 |
kin | +0.010 |
brush | +0.009 |
Neg logit contributions | |
ind | -0.020 |
iring | -0.019 |
handed | -0.017 |
cheaper | -0.016 |
ich | -0.016 |
Token | onto |
Token ID | 4291 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
ind | +0.021 |
iring | +0.021 |
handed | +0.019 |
homeless | +0.018 |
cheaper | +0.018 |
Neg logit contributions | |
isel | -0.022 |
pan | -0.020 |
ids | -0.019 |
alk | -0.018 |
kin | -0.018 |
Token | Cloud |
Token ID | 10130 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
isel | +0.007 |
pan | +0.006 |
It | +0.005 |
imagination | +0.005 |
ids | +0.005 |
Neg logit contributions | |
ind | -0.011 |
iring | -0.011 |
ll | -0.010 |
handed | -0.010 |
ich | -0.010 |
Token | y |
Token ID | 88 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
iring | +0.032 |
ind | +0.031 |
cheaper | +0.030 |
homeless | +0.030 |
handed | +0.029 |
Neg logit contributions | |
isel | -0.025 |
alk | -0.022 |
pan | -0.022 |
ids | -0.021 |
kin | -0.021 |
Token | as |
Token ID | 355 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.011 |
alk | +0.010 |
kin | +0.010 |
ids | +0.010 |
Neg logit contributions | |
ind | -0.017 |
iring | -0.016 |
handed | -0.014 |
cheaper | -0.014 |
homeless | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
kin | +0.004 |
alk | +0.004 |
imagination | +0.004 |
Neg logit contributions | |
ind | -0.006 |
iring | -0.006 |
handed | -0.005 |
itating | -0.005 |
barking | -0.005 |
Token | fairy |
Token ID | 25607 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.010 |
kin | +0.010 |
alk | +0.010 |
ids | +0.010 |
Neg logit contributions | |
ind | -0.014 |
iring | -0.014 |
handed | -0.012 |
cheaper | -0.012 |
barking | -0.012 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
ind | +0.014 |
iring | +0.013 |
handed | +0.012 |
homeless | +0.012 |
cheaper | +0.012 |
Neg logit contributions | |
isel | -0.008 |
pan | -0.007 |
ids | -0.007 |
kin | -0.007 |
alk | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
isel | +0.064 |
pan | +0.055 |
ids | +0.053 |
kin | +0.053 |
alk | +0.052 |
Neg logit contributions | |
ind | -0.087 |
iring | -0.085 |
handed | -0.077 |
ich | -0.075 |
fastest | -0.074 |
Token | r |
Token ID | 374 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
isel | +0.055 |
pan | +0.047 |
ids | +0.045 |
kin | +0.045 |
alk | +0.045 |
Neg logit contributions | |
ind | -0.066 |
iring | -0.063 |
handed | -0.058 |
homeless | -0.055 |
barking | -0.055 |
Token | iddle |
Token ID | 2509 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
isel | +0.102 |
pan | +0.085 |
kin | +0.083 |
alk | +0.079 |
ids | +0.076 |
Neg logit contributions | |
iring | -0.147 |
ind | -0.145 |
handed | -0.126 |
elderly | -0.124 |
cheaper | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
isel | +0.047 |
pan | +0.044 |
kin | +0.043 |
ids | +0.042 |
alk | +0.042 |
Neg logit contributions | |
ind | -0.075 |
iring | -0.071 |
handed | -0.066 |
homeless | -0.063 |
ich | -0.063 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
isel | +0.006 |
It | +0.006 |
pan | +0.006 |
ids | +0.005 |
cuc | +0.005 |
Neg logit contributions | |
ind | -0.023 |
iring | -0.022 |
fastest | -0.020 |
ich | -0.020 |
glers | -0.020 |
Token | thought |
Token ID | 1807 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
isel | +0.011 |
pan | +0.009 |
kin | +0.009 |
alk | +0.009 |
ids | +0.009 |
Neg logit contributions | |
ind | -0.013 |
iring | -0.013 |
handed | -0.012 |
cheaper | -0.012 |
barking | -0.012 |
Token | hard |
Token ID | 1327 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.012 |
kin | +0.012 |
ids | +0.012 |
alk | +0.011 |
Neg logit contributions | |
ind | -0.017 |
iring | -0.016 |
handed | -0.015 |
ich | -0.014 |
barking | -0.014 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
isel | +0.008 |
pan | +0.006 |
kin | +0.006 |
alk | +0.006 |
ids | +0.006 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.007 |
handed | -0.006 |
cheaper | -0.006 |
barking | -0.006 |
Token | were |
Token ID | 547 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
ind | +0.006 |
iring | +0.006 |
handed | +0.005 |
faster | +0.005 |
cheaper | +0.005 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.004 |
alk | -0.004 |
kin | -0.004 |
ids | -0.003 |
Token | proud |
Token ID | 6613 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
isel | +0.009 |
pan | +0.008 |
kin | +0.008 |
ids | +0.008 |
alk | +0.008 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.007 |
handed | -0.006 |
barking | -0.006 |
cheaper | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
ind | +0.070 |
handed | +0.064 |
iring | +0.060 |
ich | +0.058 |
shadow | +0.057 |
Neg logit contributions | |
isel | -0.037 |
imagination | -0.030 |
pan | -0.029 |
idea | -0.029 |
cuc | -0.028 |
Token | they |
Token ID | 484 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
isel | +0.016 |
kin | +0.013 |
pan | +0.013 |
alk | +0.013 |
imagination | +0.013 |
Neg logit contributions | |
ind | -0.020 |
iring | -0.019 |
handed | -0.017 |
cheaper | -0.017 |
barking | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.010 |
alk | +0.010 |
kin | +0.009 |
ids | +0.009 |
Neg logit contributions | |
iring | -0.018 |
ind | -0.018 |
cheaper | -0.016 |
handed | -0.016 |
faster | -0.016 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
isel | +0.033 |
pan | +0.027 |
alk | +0.026 |
kin | +0.026 |
ids | +0.025 |
Neg logit contributions | |
ind | -0.042 |
iring | -0.041 |
handed | -0.036 |
barking | -0.036 |
cheaper | -0.035 |
Token | together |
Token ID | 1978 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.005 |
ich | +0.005 |
concession | +0.005 |
barking | +0.005 |
Neg logit contributions | |
isel | -0.005 |
idea | -0.004 |
alk | -0.004 |
imagination | -0.004 |
kin | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
isel | +0.016 |
pan | +0.014 |
alk | +0.014 |
kin | +0.013 |
imagination | +0.013 |
Neg logit contributions | |
ind | -0.023 |
iring | -0.022 |
handed | -0.020 |
glers | -0.019 |
homeless | -0.019 |
Token | restore |
Token ID | 11169 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ind | +0.002 |
iring | +0.002 |
handed | +0.002 |
cheaper | +0.002 |
faster | +0.002 |
Neg logit contributions | |
isel | -0.002 |
pan | -0.001 |
kin | -0.001 |
alk | -0.001 |
ids | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
ind | +0.060 |
iring | +0.060 |
ich | +0.055 |
handed | +0.053 |
ll | +0.053 |
Neg logit contributions | |
isel | -0.036 |
imagination | -0.029 |
alk | -0.029 |
idea | -0.028 |
kin | -0.027 |
Token | room |
Token ID | 2119 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
isel | +0.005 |
imagination | +0.005 |
idea | +0.005 |
lived | +0.004 |
kin | +0.004 |
Neg logit contributions | |
ind | -0.005 |
iring | -0.005 |
king | -0.005 |
ich | -0.005 |
glers | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
pan | +0.014 |
kin | +0.014 |
lived | +0.013 |
isel | +0.013 |
ids | +0.013 |
Neg logit contributions | |
ind | -0.042 |
iring | -0.038 |
homeless | -0.035 |
ich | -0.035 |
shadow | -0.034 |
Token | she |
Token ID | 673 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
ind | +0.016 |
handed | +0.015 |
king | +0.015 |
ograph | +0.015 |
barking | +0.015 |
Neg logit contributions | |
isel | -0.007 |
lived | -0.006 |
kin | -0.006 |
It | -0.006 |
ily | -0.006 |
Token | started |
Token ID | 2067 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
ind | +0.007 |
iring | +0.007 |
handed | +0.007 |
cheaper | +0.007 |
barking | +0.007 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.003 |
kin | -0.003 |
alk | -0.003 |
ids | -0.003 |
Token | walking |
Token ID | 6155 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.013 |
alk | +0.012 |
ids | +0.012 |
imagination | +0.012 |
Neg logit contributions | |
ind | -0.012 |
iring | -0.012 |
handed | -0.010 |
cheaper | -0.010 |
homeless | -0.010 |
Token | around |
Token ID | 1088 |
Feature activation | +6.49e-01 |
Pos logit contributions | |
ind | +0.018 |
iring | +0.018 |
handed | +0.016 |
homeless | +0.016 |
cheaper | +0.016 |
Neg logit contributions | |
isel | -0.013 |
pan | -0.011 |
alk | -0.011 |
kin | -0.011 |
ids | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
isel | +0.024 |
pan | +0.021 |
alk | +0.020 |
kin | +0.020 |
ids | +0.019 |
Neg logit contributions | |
ind | -0.028 |
iring | -0.028 |
handed | -0.025 |
cheaper | -0.025 |
homeless | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
isel | +0.015 |
kin | +0.014 |
pan | +0.013 |
alk | +0.012 |
bee | +0.011 |
Neg logit contributions | |
iring | -0.015 |
ind | -0.014 |
barking | -0.013 |
handed | -0.013 |
elderly | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ind | +0.006 |
iring | +0.005 |
handed | +0.005 |
cheaper | +0.005 |
barking | +0.005 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.004 |
alk | -0.003 |
kin | -0.003 |
ids | -0.003 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
iring | +0.014 |
ind | +0.014 |
handed | +0.012 |
faster | +0.012 |
barking | +0.011 |
Neg logit contributions | |
isel | -0.023 |
pan | -0.020 |
kin | -0.020 |
alk | -0.019 |
ids | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
iring | +0.006 |
ind | +0.006 |
new | +0.006 |
faster | +0.006 |
barking | +0.005 |
Neg logit contributions | |
isel | -0.006 |
alk | -0.005 |
pan | -0.005 |
kin | -0.005 |
aces | -0.004 |
Token | € |
Token ID | 26391 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.005 |
handed | +0.004 |
cheaper | +0.004 |
barking | +0.004 |
Neg logit contributions | |
isel | -0.005 |
pan | -0.004 |
kin | -0.004 |
alk | -0.004 |
ids | -0.004 |
Token | � |
Token ID | 129 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
isel | +0.031 |
pan | +0.027 |
alk | +0.026 |
kin | +0.026 |
ids | +0.024 |
Neg logit contributions | |
ind | -0.027 |
iring | -0.026 |
handed | -0.024 |
barking | -0.023 |
ich | -0.023 |
Token | � |
Token ID | 241 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
isel | +0.041 |
alk | +0.033 |
pan | +0.033 |
kin | +0.032 |
ids | +0.032 |
Neg logit contributions | |
iring | -0.051 |
ind | -0.050 |
cheaper | -0.045 |
handed | -0.045 |
homeless | -0.044 |
Token | It |
Token ID | 1026 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
isel | +0.015 |
kin | +0.012 |
It | +0.012 |
ids | +0.012 |
alk | +0.011 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.018 |
handed | -0.016 |
cheaper | -0.015 |
nicer | -0.015 |
Token | â |
Token ID | 22940 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
isel | +0.008 |
pan | +0.006 |
kin | +0.006 |
alk | +0.006 |
ids | +0.006 |
Neg logit contributions | |
ind | -0.010 |
iring | -0.010 |
handed | -0.009 |
cheaper | -0.009 |
barking | -0.008 |
Token | € |
Token ID | 26391 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
ind | +0.025 |
iring | +0.025 |
handed | +0.023 |
cheaper | +0.022 |
faster | +0.022 |
Neg logit contributions | |
isel | -0.023 |
pan | -0.020 |
kin | -0.019 |
alk | -0.018 |
ids | -0.018 |
Token | ™ |
Token ID | 8151 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
isel | +0.029 |
pan | +0.026 |
alk | +0.024 |
kin | +0.024 |
cuc | +0.022 |
Neg logit contributions | |
ind | -0.027 |
iring | -0.027 |
handed | -0.025 |
barking | -0.025 |
ich | -0.024 |
Token | s |
Token ID | 82 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
isel | +0.055 |
kin | +0.052 |
ids | +0.050 |
alk | +0.049 |
lived | +0.048 |
Neg logit contributions | |
ind | -0.069 |
iring | -0.062 |
nicer | -0.059 |
cheaper | -0.058 |
homeless | -0.056 |
Token | winter |
Token ID | 7374 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
isel | +0.007 |
pan | +0.006 |
kin | +0.006 |
alk | +0.006 |
ids | +0.005 |
Neg logit contributions | |
ind | -0.008 |
iring | -0.008 |
handed | -0.007 |
cheaper | -0.007 |
barking | -0.007 |
Token | time |
Token ID | 2435 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
ind | +0.009 |
iring | +0.009 |
handed | +0.008 |
homeless | +0.008 |
cheaper | +0.008 |
Neg logit contributions | |
isel | -0.007 |
kin | -0.006 |
pan | -0.006 |
alk | -0.006 |
brush | -0.006 |
Token | ! |
Token ID | 0 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
ind | +0.027 |
iring | +0.027 |
handed | +0.024 |
ich | +0.023 |
king | +0.023 |
Neg logit contributions | |
isel | -0.017 |
kin | -0.016 |
lived | -0.015 |
idea | -0.015 |
pan | -0.015 |
Token | my |
Token ID | 616 |
Feature activation | +7.73e-02 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.011 |
handed | +0.011 |
homeless | +0.010 |
glers | +0.010 |
Neg logit contributions | |
isel | -0.010 |
imagination | -0.009 |
ids | -0.009 |
pan | -0.008 |
kin | -0.008 |
Token | r |
Token ID | 374 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
isel | +0.003 |
pan | +0.002 |
kin | +0.002 |
alk | +0.002 |
ids | +0.002 |
Neg logit contributions | |
ind | -0.004 |
iring | -0.004 |
handed | -0.003 |
cheaper | -0.003 |
homeless | -0.003 |
Token | iddles |
Token ID | 29319 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
isel | +0.107 |
pan | +0.094 |
cuc | +0.091 |
kin | +0.089 |
lived | +0.087 |
Neg logit contributions | |
iring | -0.107 |
ind | -0.105 |
elderly | -0.086 |
ich | -0.085 |
handed | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
isel | +0.043 |
pan | +0.037 |
kin | +0.037 |
alk | +0.036 |
ids | +0.036 |
Neg logit contributions | |
ind | -0.050 |
iring | -0.049 |
handed | -0.043 |
cheaper | -0.043 |
homeless | -0.042 |
Token | Are |
Token ID | 4231 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ind | +0.008 |
iring | +0.008 |
handed | +0.007 |
cheaper | +0.007 |
barking | +0.007 |
Neg logit contributions | |
isel | -0.007 |
pan | -0.006 |
kin | -0.006 |
alk | -0.006 |
ids | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
isel | +0.087 |
kin | +0.077 |
ids | +0.077 |
pan | +0.077 |
imagination | +0.076 |
Neg logit contributions | |
iring | -0.041 |
ind | -0.041 |
handed | -0.035 |
cheaper | -0.031 |
homeless | -0.031 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
isel | +0.062 |
imagination | +0.053 |
kin | +0.052 |
pan | +0.052 |
ids | +0.052 |
Neg logit contributions | |
ind | -0.075 |
iring | -0.074 |
handed | -0.066 |
glers | -0.063 |
cheaper | -0.061 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
iring | +0.072 |
ind | +0.072 |
handed | +0.069 |
Nice | +0.063 |
homeless | +0.061 |
Neg logit contributions | |
isel | -0.034 |
pan | -0.031 |
ids | -0.029 |
kin | -0.029 |
imagination | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
isel | +0.028 |
It | +0.022 |
alk | +0.022 |
pan | +0.022 |
ids | +0.021 |
Neg logit contributions | |
ind | -0.060 |
iring | -0.058 |
handed | -0.051 |
cheaper | -0.051 |
glers | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
isel | +0.008 |
pan | +0.006 |
kin | +0.006 |
alk | +0.006 |
ids | +0.006 |
Neg logit contributions | |
ind | -0.013 |
iring | -0.013 |
handed | -0.012 |
cheaper | -0.012 |
barking | -0.011 |
Token | Anna |
Token ID | 31160 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
iring | +0.007 |
ind | +0.007 |
barking | +0.006 |
handed | +0.006 |
cheaper | +0.006 |
Neg logit contributions | |
isel | -0.006 |
kin | -0.005 |
pan | -0.005 |
brush | -0.005 |
alk | -0.005 |
Token | job |
Token ID | 1693 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ind | +0.027 |
iring | +0.027 |
handed | +0.023 |
glers | +0.023 |
cheaper | +0.023 |
Neg logit contributions | |
isel | -0.025 |
imagination | -0.024 |
idea | -0.023 |
kin | -0.022 |
alk | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
ind | +0.083 |
iring | +0.078 |
handed | +0.072 |
ich | +0.072 |
shadow | +0.071 |
Neg logit contributions | |
isel | -0.037 |
imagination | -0.034 |
kin | -0.033 |
idea | -0.032 |
pan | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | -8.76e-01 |
Pos logit contributions | |
isel | +0.018 |
pan | +0.015 |
imagination | +0.014 |
kin | +0.014 |
alk | +0.014 |
Neg logit contributions | |
ind | -0.023 |
iring | -0.022 |
handed | -0.020 |
cheaper | -0.020 |
homeless | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
iring | +0.044 |
ind | +0.043 |
handed | +0.039 |
cheaper | +0.039 |
barking | +0.038 |
Neg logit contributions | |
isel | -0.027 |
pan | -0.021 |
kin | -0.021 |
alk | -0.021 |
lived | -0.020 |
Token | always |
Token ID | 1464 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
isel | +0.012 |
pan | +0.010 |
kin | +0.010 |
ids | +0.009 |
lived | +0.009 |
Neg logit contributions | |
ind | -0.013 |
iring | -0.013 |
handed | -0.011 |
cheaper | -0.011 |
glers | -0.011 |
Token | telling |
Token ID | 5149 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
ind | +0.001 |
iring | +0.001 |
glers | +0.000 |
handed | +0.000 |
cheaper | +0.000 |
Neg logit contributions | |
isel | -0.000 |
kin | -0.000 |
pan | -0.000 |
imagination | -0.000 |
idea | -0.000 |
Token | stories |
Token ID | 3923 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
isel | +0.029 |
imagination | +0.024 |
pan | +0.023 |
alk | +0.022 |
idea | +0.022 |
Neg logit contributions | |
ind | -0.039 |
iring | -0.039 |
ich | -0.035 |
handed | -0.035 |
cheaper | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
pan | +0.014 |
brush | +0.014 |
aces | +0.013 |
isel | +0.013 |
can | +0.013 |
Neg logit contributions | |
ind | -0.029 |
iring | -0.025 |
handed | -0.024 |
homeless | -0.024 |
ich | -0.024 |
Token | And |
Token ID | 843 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
isel | +0.022 |
pan | +0.019 |
kin | +0.018 |
ids | +0.017 |
alk | +0.017 |
Neg logit contributions | |
iring | -0.022 |
ind | -0.022 |
handed | -0.019 |
barking | -0.019 |
cheaper | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
ind | +0.028 |
iring | +0.025 |
handed | +0.024 |
cheaper | +0.022 |
homeless | +0.022 |
Neg logit contributions | |
isel | -0.021 |
imagination | -0.018 |
lived | -0.017 |
kin | -0.017 |
alk | -0.017 |
Token | is |
Token ID | 318 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
isel | +0.016 |
kin | +0.013 |
alk | +0.013 |
pan | +0.013 |
imagination | +0.013 |
Neg logit contributions | |
ind | -0.024 |
iring | -0.024 |
handed | -0.022 |
cheaper | -0.021 |
homeless | -0.021 |
Token | mill |
Token ID | 3939 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
isel | +0.015 |
pan | +0.012 |
kin | +0.012 |
alk | +0.012 |
imagination | +0.012 |
Neg logit contributions | |
iring | -0.018 |
ind | -0.018 |
handed | -0.017 |
cheaper | -0.016 |
homeless | -0.015 |
Token | near |
Token ID | 1474 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
isel | +0.025 |
pan | +0.024 |
kin | +0.022 |
brush | +0.022 |
alk | +0.021 |
Neg logit contributions | |
ind | -0.028 |
iring | -0.027 |
handed | -0.024 |
cheaper | -0.023 |
homeless | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
isel | +0.006 |
It | +0.005 |
idea | +0.005 |
alk | +0.005 |
lived | +0.004 |
Neg logit contributions | |
ll | -0.017 |
ind | -0.016 |
iring | -0.016 |
itating | -0.016 |
shadow | -0.015 |
Token | house |
Token ID | 2156 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
iring | +0.041 |
ind | +0.039 |
shadow | +0.038 |
glers | +0.038 |
cheaper | +0.036 |
Neg logit contributions | |
isel | -0.025 |
imagination | -0.024 |
alk | -0.023 |
ear | -0.022 |
kin | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
isel | +0.004 |
pan | +0.003 |
kin | +0.003 |
alk | +0.003 |
brush | +0.003 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.006 |
handed | -0.006 |
homeless | -0.006 |
cheaper | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
ind | +0.023 |
iring | +0.023 |
handed | +0.020 |
cheaper | +0.020 |
barking | +0.020 |
Neg logit contributions | |
isel | -0.018 |
pan | -0.015 |
kin | -0.014 |
alk | -0.014 |
ids | -0.014 |
Token | mill |
Token ID | 3939 |
Feature activation | +4.00e-01 |
Pos logit contributions | |
isel | +0.009 |
pan | +0.008 |
alk | +0.008 |
kin | +0.008 |
ids | +0.007 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.007 |
cheaper | -0.006 |
elderly | -0.006 |
homeless | -0.006 |
Token | has |
Token ID | 468 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.012 |
kin | +0.011 |
alk | +0.011 |
ids | +0.011 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.018 |
handed | -0.016 |
cheaper | -0.016 |
barking | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +9.08e-02 |
Pos logit contributions | |
isel | +0.005 |
pan | +0.004 |
alk | +0.004 |
ids | +0.004 |
kin | +0.004 |
Neg logit contributions | |
ind | -0.006 |
iring | -0.006 |
handed | -0.005 |
barking | -0.005 |
cheaper | -0.005 |
Token | wheel |
Token ID | 7825 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
isel | +0.004 |
pan | +0.003 |
kin | +0.003 |
alk | +0.003 |
brush | +0.003 |
Neg logit contributions | |
ind | -0.004 |
iring | -0.004 |
handed | -0.003 |
cheaper | -0.003 |
faster | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
isel | +0.024 |
brush | +0.022 |
pan | +0.022 |
aces | +0.021 |
ids | +0.021 |
Neg logit contributions | |
ind | -0.037 |
iring | -0.034 |
handed | -0.034 |
homeless | -0.032 |
cheaper | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
isel | +0.006 |
pan | +0.005 |
kin | +0.005 |
ily | +0.005 |
ids | +0.005 |
Neg logit contributions | |
ind | -0.011 |
iring | -0.011 |
barking | -0.010 |
cheaper | -0.010 |
handed | -0.010 |
Token | paper |
Token ID | 3348 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
kin | +0.009 |
pan | +0.009 |
isel | +0.009 |
brush | +0.009 |
imagination | +0.008 |
Neg logit contributions | |
iring | -0.015 |
ind | -0.014 |
barking | -0.012 |
shadow | -0.012 |
itating | -0.012 |
Token | into |
Token ID | 656 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
isel | +0.037 |
pan | +0.034 |
kin | +0.033 |
alk | +0.032 |
ids | +0.031 |
Neg logit contributions | |
iring | -0.032 |
ind | -0.032 |
handed | -0.028 |
cheaper | -0.028 |
homeless | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
isel | +0.020 |
pan | +0.018 |
kin | +0.017 |
imagination | +0.016 |
alk | +0.016 |
Neg logit contributions | |
ind | -0.035 |
iring | -0.035 |
ll | -0.032 |
itating | -0.032 |
ich | -0.031 |
Token | pocket |
Token ID | 10000 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
iring | +0.011 |
ind | +0.010 |
ll | +0.009 |
shadow | +0.009 |
itating | +0.009 |
Neg logit contributions | |
isel | -0.007 |
pan | -0.007 |
kin | -0.007 |
brush | -0.006 |
imagination | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ind | +0.037 |
iring | +0.036 |
barking | +0.033 |
homeless | +0.031 |
Nice | +0.031 |
Neg logit contributions | |
isel | -0.021 |
pan | -0.021 |
kin | -0.020 |
brush | -0.019 |
alk | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
iring | +0.070 |
ind | +0.069 |
itating | +0.062 |
handed | +0.062 |
ll | +0.059 |
Neg logit contributions | |
isel | -0.044 |
kin | -0.038 |
imagination | -0.037 |
pan | -0.036 |
alk | -0.035 |
Token | dress |
Token ID | 6576 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
isel | +0.009 |
kin | +0.009 |
imagination | +0.008 |
alk | +0.008 |
ids | +0.008 |
Neg logit contributions | |
iring | -0.013 |
ind | -0.013 |
itating | -0.012 |
glers | -0.011 |
handed | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
pan | +0.004 |
kin | +0.004 |
brush | +0.004 |
isel | +0.004 |
aces | +0.004 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.007 |
barking | -0.006 |
homeless | -0.006 |
handed | -0.006 |
Token | shut |
Token ID | 4423 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
ind | +0.008 |
iring | +0.008 |
handed | +0.007 |
cheaper | +0.007 |
itating | +0.007 |
Neg logit contributions | |
isel | -0.005 |
kin | -0.004 |
pan | -0.004 |
imagination | -0.004 |
ids | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
iring | +0.002 |
ind | +0.002 |
handed | +0.002 |
homeless | +0.002 |
glers | +0.002 |
Neg logit contributions | |
isel | -0.001 |
pan | -0.001 |
ids | -0.001 |
kin | -0.001 |
brush | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
isel | +0.025 |
kin | +0.023 |
alk | +0.022 |
pan | +0.021 |
cuc | +0.021 |
Neg logit contributions | |
iring | -0.040 |
ind | -0.040 |
fastest | -0.035 |
ich | -0.035 |
handed | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | +8.04e-01 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.011 |
kin | +0.011 |
alk | +0.011 |
ids | +0.011 |
Neg logit contributions | |
ind | -0.021 |
iring | -0.021 |
handed | -0.019 |
cheaper | -0.019 |
barking | -0.018 |
Token | knew |
Token ID | 2993 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
isel | +0.026 |
kin | +0.021 |
pan | +0.020 |
alk | +0.020 |
lived | +0.020 |
Neg logit contributions | |
ind | -0.039 |
iring | -0.039 |
handed | -0.035 |
cheaper | -0.034 |
barking | -0.034 |
Token | that |
Token ID | 326 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.029 |
lived | +0.028 |
kin | +0.028 |
imagination | +0.027 |
Neg logit contributions | |
ind | -0.045 |
iring | -0.040 |
handed | -0.038 |
barking | -0.038 |
glers | -0.038 |
Token | no |
Token ID | 645 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
isel | +0.006 |
pan | +0.005 |
kin | +0.005 |
imagination | +0.005 |
alk | +0.005 |
Neg logit contributions | |
ind | -0.008 |
iring | -0.008 |
handed | -0.007 |
cheaper | -0.007 |
barking | -0.007 |
Token | matter |
Token ID | 2300 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
isel | +0.001 |
idea | +0.001 |
imagination | +0.001 |
kin | +0.001 |
nod | +0.001 |
Neg logit contributions | |
iring | -0.002 |
ind | -0.002 |
concession | -0.002 |
glers | -0.002 |
handed | -0.002 |
Token | how |
Token ID | 703 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ind | +0.042 |
iring | +0.041 |
handed | +0.040 |
homeless | +0.038 |
cheaper | +0.038 |
Neg logit contributions | |
isel | -0.024 |
alk | -0.019 |
lived | -0.018 |
imagination | -0.018 |
pan | -0.018 |
Token | confused |
Token ID | 10416 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
isel | +0.058 |
alk | +0.049 |
imagination | +0.046 |
pan | +0.044 |
cuc | +0.044 |
Neg logit contributions | |
ind | -0.052 |
iring | -0.049 |
handed | -0.045 |
barking | -0.045 |
glers | -0.044 |
Token | he |
Token ID | 339 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
isel | +0.036 |
pan | +0.030 |
kin | +0.029 |
alk | +0.028 |
imagination | +0.028 |
Neg logit contributions | |
ind | -0.051 |
iring | -0.050 |
handed | -0.046 |
cheaper | -0.044 |
barking | -0.043 |
Token | might |
Token ID | 1244 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
ind | +0.022 |
iring | +0.021 |
barking | +0.019 |
handed | +0.019 |
cheaper | +0.019 |
Neg logit contributions | |
isel | -0.010 |
lived | -0.008 |
kin | -0.008 |
alk | -0.007 |
aces | -0.007 |
Token | be |
Token ID | 307 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
isel | +0.002 |
alk | +0.001 |
pan | +0.001 |
kin | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.003 |
iring | -0.003 |
handed | -0.002 |
cheaper | -0.002 |
barking | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +8.38e-01 |
Pos logit contributions | |
isel | +0.025 |
pan | +0.023 |
kin | +0.022 |
idea | +0.020 |
lived | +0.019 |
Neg logit contributions | |
ind | -0.093 |
iring | -0.087 |
handed | -0.086 |
ograph | -0.084 |
homeless | -0.083 |
Token | he |
Token ID | 339 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
isel | +0.028 |
pan | +0.023 |
It | +0.022 |
imagination | +0.022 |
lived | +0.022 |
Neg logit contributions | |
ind | -0.043 |
iring | -0.038 |
handed | -0.036 |
cheaper | -0.035 |
glers | -0.033 |
Token | quickly |
Token ID | 2952 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
iring | +0.017 |
ind | +0.017 |
handed | +0.016 |
cheaper | +0.015 |
homeless | +0.015 |
Neg logit contributions | |
isel | -0.009 |
lived | -0.007 |
kin | -0.007 |
pan | -0.007 |
ids | -0.007 |
Token | z |
Token ID | 1976 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
isel | +0.020 |
pan | +0.016 |
kin | +0.015 |
alk | +0.015 |
ids | +0.015 |
Neg logit contributions | |
iring | -0.032 |
ind | -0.032 |
handed | -0.028 |
cheaper | -0.027 |
homeless | -0.027 |
Token | ipped |
Token ID | 3949 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
isel | +0.043 |
pan | +0.037 |
alk | +0.036 |
kin | +0.036 |
ids | +0.035 |
Neg logit contributions | |
ind | -0.032 |
iring | -0.032 |
handed | -0.027 |
cheaper | -0.027 |
barking | -0.027 |
Token | up |
Token ID | 510 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.011 |
It | +0.011 |
imagination | +0.010 |
idea | +0.010 |
Neg logit contributions | |
ind | -0.017 |
iring | -0.017 |
handed | -0.015 |
ich | -0.015 |
homeless | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
ind | +0.015 |
iring | +0.015 |
ich | +0.014 |
handed | +0.013 |
ograph | +0.013 |
Neg logit contributions | |
isel | -0.007 |
pan | -0.007 |
alk | -0.006 |
imagination | -0.006 |
kin | -0.006 |
Token | fur |
Token ID | 9230 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
imagination | +0.006 |
kin | +0.005 |
isel | +0.005 |
idea | +0.005 |
aces | +0.005 |
Neg logit contributions | |
iring | -0.010 |
ind | -0.009 |
handed | -0.009 |
itating | -0.008 |
homeless | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
pan | +0.034 |
isel | +0.033 |
kin | +0.032 |
brush | +0.031 |
aces | +0.030 |
Neg logit contributions | |
ind | -0.054 |
iring | -0.051 |
homeless | -0.047 |
cheaper | -0.046 |
handed | -0.046 |
Token | hopped |
Token ID | 45230 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
isel | +0.009 |
pan | +0.008 |
lived | +0.008 |
imagination | +0.007 |
kin | +0.007 |
Neg logit contributions | |
ind | -0.019 |
iring | -0.018 |
handed | -0.016 |
homeless | -0.015 |
cheaper | -0.015 |
Token | off |
Token ID | 572 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
ind | +0.010 |
iring | +0.010 |
handed | +0.009 |
homeless | +0.009 |
ich | +0.009 |
Neg logit contributions | |
isel | -0.010 |
pan | -0.009 |
kin | -0.009 |
ids | -0.008 |
alk | -0.008 |
Token | something |
Token ID | 1223 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
ind | +0.014 |
iring | +0.013 |
handed | +0.013 |
ich | +0.013 |
sidelines | +0.012 |
Neg logit contributions | |
isel | -0.010 |
pan | -0.010 |
alk | -0.010 |
imagination | -0.010 |
idea | -0.010 |
Token | new |
Token ID | 649 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ind | +0.009 |
handed | +0.008 |
sidelines | +0.008 |
ich | +0.007 |
iring | +0.007 |
Neg logit contributions | |
idea | -0.016 |
isel | -0.015 |
imagination | -0.015 |
can | -0.015 |
alk | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
ind | +0.044 |
iring | +0.042 |
handed | +0.038 |
homeless | +0.037 |
cheaper | +0.037 |
Neg logit contributions | |
isel | -0.038 |
alk | -0.032 |
pan | -0.032 |
kin | -0.032 |
ids | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
iring | +0.006 |
ind | +0.006 |
elderly | +0.005 |
cheaper | +0.005 |
barking | +0.005 |
Neg logit contributions | |
isel | -0.005 |
kin | -0.005 |
pan | -0.004 |
ids | -0.004 |
brush | -0.004 |
Token | would |
Token ID | 561 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.011 |
kin | +0.011 |
alk | +0.011 |
ids | +0.010 |
Neg logit contributions | |
ind | -0.018 |
iring | -0.017 |
cheaper | -0.016 |
faster | -0.015 |
barking | -0.015 |
Token | learn |
Token ID | 2193 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
ind | +0.048 |
iring | +0.046 |
barking | +0.042 |
cheaper | +0.042 |
faster | +0.042 |
Neg logit contributions | |
isel | -0.042 |
kin | -0.035 |
pan | -0.034 |
alk | -0.033 |
ids | -0.032 |
Token | how |
Token ID | 703 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
ind | +0.015 |
handed | +0.014 |
iring | +0.013 |
ich | +0.013 |
concession | +0.013 |
Neg logit contributions | |
isel | -0.011 |
alk | -0.010 |
imagination | -0.010 |
pan | -0.010 |
idea | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
isel | +0.018 |
alk | +0.015 |
pan | +0.015 |
imagination | +0.015 |
ids | +0.014 |
Neg logit contributions | |
ind | -0.015 |
iring | -0.015 |
handed | -0.013 |
barking | -0.012 |
cheaper | -0.012 |
Token | count |
Token ID | 954 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
ind | +0.017 |
iring | +0.017 |
handed | +0.015 |
cheaper | +0.015 |
barking | +0.015 |
Neg logit contributions | |
isel | -0.012 |
pan | -0.010 |
kin | -0.010 |
alk | -0.010 |
ids | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
handed | +0.024 |
ind | +0.024 |
iring | +0.023 |
homeless | +0.022 |
concession | +0.021 |
Neg logit contributions | |
isel | -0.016 |
alk | -0.014 |
pan | -0.014 |
ids | -0.014 |
aces | -0.014 |
Token | how |
Token ID | 703 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
isel | +0.025 |
pan | +0.020 |
alk | +0.020 |
imagination | +0.019 |
ids | +0.019 |
Neg logit contributions | |
ind | -0.033 |
iring | -0.032 |
handed | -0.029 |
homeless | -0.028 |
cheaper | -0.028 |
Token | this |
Token ID | 428 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ind | +0.037 |
iring | +0.034 |
handed | +0.031 |
barking | +0.030 |
glers | +0.030 |
Neg logit contributions | |
isel | -0.028 |
kin | -0.024 |
pan | -0.022 |
lived | -0.022 |
imagination | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.028 |
kin | +0.028 |
alk | +0.027 |
ids | +0.026 |
Neg logit contributions | |
ind | -0.051 |
iring | -0.051 |
handed | -0.045 |
cheaper | -0.045 |
barking | -0.045 |
Token | it |
Token ID | 340 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ind | +0.028 |
iring | +0.026 |
handed | +0.023 |
itating | +0.023 |
ich | +0.023 |
Neg logit contributions | |
isel | -0.017 |
kin | -0.014 |
lived | -0.014 |
pan | -0.014 |
ids | -0.013 |
Token | did |
Token ID | 750 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
isel | +0.004 |
kin | +0.003 |
pan | +0.003 |
lived | +0.003 |
alk | +0.003 |
Neg logit contributions | |
ind | -0.007 |
iring | -0.007 |
handed | -0.006 |
cheaper | -0.006 |
barking | -0.006 |
Token | not |
Token ID | 407 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
isel | +0.023 |
kin | +0.020 |
pan | +0.020 |
alk | +0.019 |
imagination | +0.018 |
Neg logit contributions | |
ind | -0.024 |
iring | -0.023 |
handed | -0.020 |
ich | -0.019 |
elderly | -0.019 |
Token | taste |
Token ID | 6938 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
ind | +0.012 |
iring | +0.012 |
handed | +0.010 |
cheaper | +0.010 |
barking | +0.010 |
Neg logit contributions | |
isel | -0.007 |
pan | -0.006 |
kin | -0.006 |
alk | -0.006 |
ids | -0.005 |
Token | good |
Token ID | 922 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ind | +0.123 |
iring | +0.118 |
ich | +0.115 |
handed | +0.112 |
concession | +0.107 |
Neg logit contributions | |
isel | -0.090 |
kin | -0.073 |
idea | -0.072 |
alk | -0.072 |
cuc | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
ind | +0.025 |
iring | +0.024 |
handed | +0.022 |
homeless | +0.021 |
ich | +0.021 |
Neg logit contributions | |
isel | -0.022 |
pan | -0.018 |
alk | -0.018 |
kin | -0.018 |
imagination | -0.017 |
Token | |
Token ID | 220 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
isel | +0.018 |
pan | +0.015 |
kin | +0.014 |
alk | +0.014 |
ids | +0.014 |
Neg logit contributions | |
ind | -0.022 |
iring | -0.022 |
handed | -0.019 |
cheaper | -0.019 |
barking | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ind | +0.038 |
iring | +0.037 |
cheaper | +0.033 |
handed | +0.033 |
barking | +0.033 |
Neg logit contributions | |
isel | -0.027 |
pan | -0.022 |
alk | -0.022 |
kin | -0.021 |
ids | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
isel | +0.006 |
pan | +0.005 |
kin | +0.005 |
alk | +0.005 |
ids | +0.005 |
Neg logit contributions | |
ind | -0.008 |
iring | -0.008 |
handed | -0.007 |
cheaper | -0.007 |
barking | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
isel | +0.019 |
pan | +0.017 |
kin | +0.016 |
alk | +0.016 |
ids | +0.015 |
Neg logit contributions | |
ind | -0.021 |
iring | -0.021 |
handed | -0.018 |
cheaper | -0.018 |
homeless | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ind | +0.010 |
iring | +0.010 |
handed | +0.009 |
homeless | +0.009 |
cheaper | +0.008 |
Neg logit contributions | |
isel | -0.006 |
pan | -0.005 |
kin | -0.005 |
alk | -0.005 |
ids | -0.005 |
Token | picked |
Token ID | 6497 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
isel | +0.016 |
alk | +0.014 |
pan | +0.013 |
kin | +0.013 |
ids | +0.013 |
Neg logit contributions | |
iring | -0.010 |
ind | -0.010 |
cheaper | -0.010 |
elderly | -0.009 |
glers | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
isel | +0.001 |
pan | +0.001 |
kin | +0.001 |
alk | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.001 |
iring | -0.001 |
handed | -0.001 |
barking | -0.001 |
cheaper | -0.001 |
Token | prett |
Token ID | 46442 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
ind | +0.004 |
iring | +0.004 |
cheaper | +0.004 |
faster | +0.003 |
elderly | +0.003 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.004 |
alk | -0.004 |
kin | -0.004 |
ids | -0.003 |
Token | iest |
Token ID | 6386 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
iring | +0.025 |
ind | +0.023 |
cheaper | +0.021 |
faster | +0.020 |
glers | +0.020 |
Neg logit contributions | |
isel | -0.033 |
pan | -0.029 |
alk | -0.028 |
AAAA | -0.027 |
imagination | -0.027 |
Token | pe |
Token ID | 613 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
ind | +0.084 |
iring | +0.083 |
cheaper | +0.074 |
handed | +0.073 |
faster | +0.072 |
Neg logit contributions | |
isel | -0.073 |
pan | -0.061 |
alk | -0.059 |
kin | -0.059 |
ids | -0.057 |
Token | b |
Token ID | 65 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
isel | +0.088 |
pan | +0.078 |
alk | +0.076 |
kin | +0.076 |
imagination | +0.073 |
Neg logit contributions | |
ind | -0.045 |
iring | -0.045 |
cheaper | -0.037 |
faster | -0.035 |
handed | -0.034 |
Token | bles |
Token ID | 7689 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
isel | +0.048 |
pan | +0.042 |
alk | +0.041 |
imagination | +0.040 |
kin | +0.039 |
Neg logit contributions | |
iring | -0.034 |
ind | -0.031 |
ich | -0.027 |
faster | -0.026 |
cheaper | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
isel | +0.026 |
pan | +0.023 |
kin | +0.023 |
alk | +0.022 |
ids | +0.022 |
Neg logit contributions | |
ind | -0.032 |
iring | -0.031 |
handed | -0.028 |
barking | -0.027 |
homeless | -0.027 |
Token | started |
Token ID | 2067 |
Feature activation | +7.65e-02 |
Pos logit contributions | |
isel | +0.001 |
pan | +0.001 |
kin | +0.001 |
alk | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.001 |
handed | -0.001 |
barking | -0.001 |
cheaper | -0.001 |
Token | close |
Token ID | 1969 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
ind | +0.019 |
iring | +0.018 |
cheaper | +0.017 |
faster | +0.017 |
barking | +0.017 |
Neg logit contributions | |
isel | -0.016 |
pan | -0.013 |
alk | -0.013 |
kin | -0.013 |
aces | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
ind | +0.023 |
iring | +0.023 |
handed | +0.021 |
homeless | +0.020 |
cheaper | +0.020 |
Neg logit contributions | |
isel | -0.020 |
pan | -0.017 |
alk | -0.016 |
ids | -0.016 |
kin | -0.016 |
Token | cabinet |
Token ID | 13447 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.012 |
cheaper | +0.010 |
handed | +0.010 |
barking | +0.010 |
Neg logit contributions | |
isel | -0.018 |
pan | -0.015 |
kin | -0.015 |
alk | -0.015 |
ids | -0.014 |
Token | doors |
Token ID | 8215 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
isel | +0.014 |
pan | +0.012 |
kin | +0.012 |
alk | +0.012 |
ids | +0.011 |
Neg logit contributions | |
ind | -0.015 |
iring | -0.015 |
handed | -0.013 |
homeless | -0.013 |
barking | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
isel | +0.035 |
pan | +0.030 |
kin | +0.029 |
alk | +0.029 |
ids | +0.028 |
Neg logit contributions | |
ind | -0.040 |
iring | -0.038 |
handed | -0.035 |
homeless | -0.034 |
barking | -0.034 |
Token | look |
Token ID | 804 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
iring | +0.020 |
ind | +0.020 |
cheaper | +0.018 |
faster | +0.018 |
homeless | +0.018 |
Neg logit contributions | |
isel | -0.017 |
pan | -0.014 |
alk | -0.013 |
kin | -0.013 |
ids | -0.013 |
Token | at |
Token ID | 379 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
ind | +0.077 |
iring | +0.075 |
handed | +0.070 |
barking | +0.065 |
homeless | +0.065 |
Neg logit contributions | |
isel | -0.079 |
pan | -0.066 |
kin | -0.064 |
ids | -0.064 |
alk | -0.063 |
Token | the |
Token ID | 262 |
Feature activation | -8.04e-01 |
Pos logit contributions | |
isel | +0.013 |
pan | +0.011 |
imagination | +0.011 |
kin | +0.010 |
alk | +0.010 |
Neg logit contributions | |
ind | -0.019 |
iring | -0.019 |
handed | -0.018 |
shadow | -0.018 |
barking | -0.017 |
Token | things |
Token ID | 1243 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
ind | +0.034 |
iring | +0.032 |
handed | +0.030 |
barking | +0.030 |
shadow | +0.030 |
Neg logit contributions | |
isel | -0.029 |
pan | -0.026 |
kin | -0.025 |
brush | -0.025 |
idea | -0.024 |
Token | inside |
Token ID | 2641 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ind | +0.002 |
iring | +0.002 |
handed | +0.002 |
barking | +0.002 |
homeless | +0.002 |
Neg logit contributions | |
isel | -0.001 |
pan | -0.001 |
kin | -0.001 |
brush | -0.001 |
ids | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
ind | +0.030 |
iring | +0.028 |
shadow | +0.027 |
handed | +0.027 |
ich | +0.027 |
Neg logit contributions | |
isel | -0.014 |
kin | -0.012 |
are | -0.012 |
pan | -0.012 |
lived | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ich | +0.042 |
iring | +0.041 |
ind | +0.040 |
sidelines | +0.039 |
handed | +0.039 |
Neg logit contributions | |
idea | -0.022 |
lived | -0.020 |
isel | -0.020 |
imagination | -0.019 |
It | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
ind | +0.018 |
iring | +0.018 |
handed | +0.016 |
cheaper | +0.016 |
barking | +0.016 |
Neg logit contributions | |
isel | -0.015 |
pan | -0.012 |
kin | -0.012 |
alk | -0.012 |
ids | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
ind | +0.067 |
iring | +0.065 |
cheaper | +0.059 |
handed | +0.059 |
barking | +0.059 |
Neg logit contributions | |
isel | -0.046 |
pan | -0.037 |
alk | -0.036 |
kin | -0.036 |
ids | -0.034 |
Token | always |
Token ID | 1464 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
iring | +0.003 |
ind | +0.003 |
handed | +0.003 |
cheaper | +0.003 |
barking | +0.003 |
Neg logit contributions | |
isel | -0.004 |
pan | -0.003 |
kin | -0.003 |
ids | -0.003 |
imagination | -0.003 |
Token | looking |
Token ID | 2045 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
ind | +0.017 |
iring | +0.017 |
handed | +0.017 |
glers | +0.016 |
sidelines | +0.015 |
Neg logit contributions | |
isel | -0.012 |
kin | -0.011 |
lived | -0.010 |
idea | -0.010 |
pan | -0.010 |
Token | forward |
Token ID | 2651 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
ind | +0.037 |
handed | +0.036 |
iring | +0.036 |
glers | +0.035 |
ich | +0.035 |
Neg logit contributions | |
isel | -0.030 |
imagination | -0.024 |
idea | -0.024 |
cuc | -0.022 |
ids | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ind | +0.093 |
iring | +0.089 |
handed | +0.088 |
glers | +0.087 |
homeless | +0.085 |
Neg logit contributions | |
isel | -0.068 |
imagination | -0.060 |
alk | -0.059 |
pan | -0.058 |
ids | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
isel | +0.001 |
imagination | +0.001 |
lived | +0.001 |
idea | +0.001 |
alk | +0.001 |
Neg logit contributions | |
iring | -0.002 |
ind | -0.002 |
handed | -0.001 |
glers | -0.001 |
itating | -0.001 |
Token | next |
Token ID | 1306 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
handed | +0.031 |
iring | +0.030 |
shadow | +0.029 |
glers | +0.029 |
sidelines | +0.029 |
Neg logit contributions | |
imagination | -0.026 |
idea | -0.024 |
lived | -0.022 |
gard | -0.021 |
name | -0.021 |
Token | adventure |
Token ID | 8855 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
isel | +0.026 |
imagination | +0.024 |
alk | +0.022 |
idea | +0.022 |
pan | +0.021 |
Neg logit contributions | |
iring | -0.034 |
ind | -0.031 |
handed | -0.030 |
homeless | -0.029 |
shadow | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
iring | +0.012 |
ind | +0.012 |
itating | +0.012 |
shadow | +0.012 |
iqu | +0.012 |
Neg logit contributions | |
aces | -0.002 |
idea | -0.002 |
lived | -0.002 |
ily | -0.001 |
guys | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
isel | +0.001 |
pan | +0.001 |
kin | +0.001 |
alk | +0.001 |
ids | +0.001 |
Neg logit contributions | |
ind | -0.002 |
iring | -0.002 |
handed | -0.001 |
cheaper | -0.001 |
barking | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
isel | +0.005 |
kin | +0.004 |
imagination | +0.004 |
pan | +0.004 |
cuc | +0.004 |
Neg logit contributions | |
iring | -0.009 |
ind | -0.009 |
handed | -0.008 |
barking | -0.007 |
shadow | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
isel | +0.002 |
pan | +0.002 |
kin | +0.002 |
imagination | +0.002 |
idea | +0.002 |
Neg logit contributions | |
ind | -0.004 |
iring | -0.004 |
handed | -0.003 |
barking | -0.003 |
shadow | -0.003 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
iring | +0.014 |
ind | +0.014 |
handed | +0.012 |
cheaper | +0.012 |
homeless | +0.012 |
Neg logit contributions | |
isel | -0.007 |
lived | -0.006 |
pan | -0.005 |
imagination | -0.005 |
ids | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
isel | +0.014 |
kin | +0.012 |
pan | +0.012 |
imagination | +0.011 |
alk | +0.011 |
Neg logit contributions | |
iring | -0.017 |
ind | -0.017 |
handed | -0.015 |
cheaper | -0.015 |
itating | -0.014 |
Token | rest |
Token ID | 1334 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
ind | +0.005 |
iring | +0.005 |
shadow | +0.004 |
barking | +0.004 |
handed | +0.004 |
Neg logit contributions | |
isel | -0.005 |
idea | -0.005 |
kin | -0.005 |
imagination | -0.005 |
nod | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ind | +0.105 |
iring | +0.098 |
handed | +0.093 |
homeless | +0.093 |
cheaper | +0.092 |
Neg logit contributions | |
kin | -0.065 |
isel | -0.063 |
pan | -0.059 |
aces | -0.054 |
alk | -0.053 |
Token | their |
Token ID | 511 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
iring | +0.057 |
ind | +0.055 |
handed | +0.049 |
itating | +0.048 |
cheaper | +0.048 |
Neg logit contributions | |
isel | -0.036 |
pan | -0.031 |
kin | -0.030 |
alk | -0.030 |
imagination | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
imagination | +0.007 |
isel | +0.007 |
kin | +0.006 |
lived | +0.006 |
idea | +0.006 |
Neg logit contributions | |
iring | -0.011 |
ind | -0.010 |
itating | -0.010 |
handed | -0.010 |
shadow | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
ind | +0.050 |
iring | +0.050 |
handed | +0.047 |
cheaper | +0.046 |
oma | +0.045 |
Neg logit contributions | |
isel | -0.026 |
kin | -0.025 |
imagination | -0.025 |
alk | -0.024 |
aces | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
isel | +0.023 |
imagination | +0.021 |
pan | +0.021 |
alk | +0.020 |
kin | +0.020 |
Neg logit contributions | |
iring | -0.039 |
ind | -0.038 |
ich | -0.033 |
handed | -0.033 |
shadow | -0.032 |