Token | time |
Token ID | 640 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
age | +0.004 |
est | +0.003 |
� | +0.003 |
tted | +0.003 |
ok | +0.003 |
Neg logit contributions | |
yles | -0.004 |
brushes | -0.004 |
passports | -0.004 |
ries | -0.003 |
outed | -0.003 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
yles | +0.005 |
outing | +0.004 |
ries | +0.004 |
outed | +0.004 |
ateful | +0.004 |
Neg logit contributions | |
age | -0.004 |
est | -0.004 |
� | -0.003 |
ok | -0.003 |
ze | -0.003 |
Token | with |
Token ID | 351 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
age | +0.041 |
est | +0.032 |
ok | +0.030 |
� | +0.028 |
sy | +0.026 |
Neg logit contributions | |
yles | -0.043 |
ries | -0.039 |
their | -0.038 |
nam | -0.037 |
they | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.006 |
outed | +0.005 |
ateful | +0.005 |
eling | +0.005 |
Neg logit contributions | |
age | -0.011 |
est | -0.010 |
� | -0.009 |
ok | -0.009 |
ze | -0.008 |
Token | or |
Token ID | 393 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
yles | +0.020 |
outing | +0.018 |
ries | +0.018 |
nam | +0.017 |
outed | +0.017 |
Neg logit contributions | |
age | -0.022 |
est | -0.018 |
� | -0.016 |
ok | -0.015 |
ze | -0.015 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
age | +0.034 |
est | +0.030 |
� | +0.027 |
ok | +0.026 |
ze | +0.025 |
Neg logit contributions | |
yles | -0.024 |
outing | -0.023 |
outed | -0.021 |
ries | -0.021 |
ateful | -0.020 |
Token | ents |
Token ID | 658 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
yles | +0.123 |
outing | +0.107 |
eling | +0.099 |
ries | +0.096 |
outed | +0.096 |
Neg logit contributions | |
age | -0.347 |
est | -0.310 |
� | -0.293 |
ok | -0.272 |
sy | -0.267 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
yles | +0.123 |
outing | +0.115 |
outed | +0.110 |
ateful | +0.109 |
ries | +0.109 |
Neg logit contributions | |
age | -0.078 |
est | -0.064 |
� | -0.054 |
ok | -0.049 |
ze | -0.046 |
Token | making |
Token ID | 1642 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
age | +0.003 |
est | +0.003 |
� | +0.003 |
ok | +0.002 |
best | +0.002 |
Neg logit contributions | |
yles | -0.003 |
outing | -0.002 |
outed | -0.002 |
ateful | -0.002 |
eling | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
age | +0.057 |
est | +0.049 |
� | +0.044 |
ok | +0.042 |
ze | +0.040 |
Neg logit contributions | |
yles | -0.048 |
outing | -0.044 |
ries | -0.041 |
outed | -0.041 |
ateful | -0.041 |
Token | special |
Token ID | 2041 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
yles | +0.018 |
nam | +0.016 |
outing | +0.016 |
outed | +0.016 |
ries | +0.016 |
Neg logit contributions | |
age | -0.017 |
est | -0.014 |
� | -0.012 |
ok | -0.012 |
sy | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.003 |
ries | +0.003 |
outed | +0.002 |
ateful | +0.002 |
Neg logit contributions | |
age | -0.005 |
est | -0.004 |
� | -0.004 |
ok | -0.003 |
ze | -0.003 |
Token | rest |
Token ID | 1334 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
age | +0.019 |
est | +0.016 |
ok | +0.014 |
sy | +0.014 |
nob | +0.013 |
Neg logit contributions | |
yles | -0.013 |
nam | -0.013 |
outing | -0.013 |
ries | -0.012 |
ateful | -0.012 |
Token | of |
Token ID | 286 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
yles | +0.022 |
outing | +0.020 |
outed | +0.019 |
ateful | +0.019 |
ries | +0.019 |
Neg logit contributions | |
age | -0.016 |
est | -0.013 |
� | -0.011 |
ok | -0.010 |
ze | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -9.82e-03 |
Pos logit contributions | |
outing | +0.043 |
yles | +0.043 |
outed | +0.041 |
ateful | +0.038 |
eling | +0.037 |
Neg logit contributions | |
age | -0.040 |
est | -0.035 |
� | -0.034 |
right | -0.031 |
ok | -0.031 |
Token | or |
Token ID | 393 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
age | +0.019 |
est | +0.017 |
ok | +0.014 |
� | +0.013 |
sy | +0.013 |
Neg logit contributions | |
yles | -0.015 |
nam | -0.014 |
outing | -0.014 |
ries | -0.014 |
spill | -0.014 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
age | +0.037 |
est | +0.032 |
� | +0.030 |
ok | +0.028 |
ze | +0.027 |
Neg logit contributions | |
yles | -0.034 |
outing | -0.032 |
outed | -0.030 |
ries | -0.030 |
ateful | -0.029 |
Token | ents |
Token ID | 658 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
yles | +0.121 |
outing | +0.103 |
eling | +0.099 |
ries | +0.094 |
outed | +0.094 |
Neg logit contributions | |
age | -0.339 |
est | -0.299 |
� | -0.289 |
ok | -0.264 |
ench | -0.261 |
Token | onto |
Token ID | 4291 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
yles | +0.114 |
outing | +0.106 |
outed | +0.102 |
ateful | +0.102 |
ries | +0.101 |
Neg logit contributions | |
age | -0.075 |
est | -0.062 |
� | -0.053 |
ok | -0.048 |
ze | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
yles | +0.022 |
outing | +0.020 |
ries | +0.019 |
ateful | +0.019 |
outed | +0.018 |
Neg logit contributions | |
age | -0.032 |
est | -0.029 |
� | -0.025 |
ok | -0.024 |
ze | -0.024 |
Token | tree |
Token ID | 5509 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
age | +0.009 |
est | +0.008 |
ok | +0.007 |
ench | +0.007 |
iver | +0.007 |
Neg logit contributions | |
nam | -0.007 |
yles | -0.007 |
salon | -0.007 |
brushes | -0.006 |
spill | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
yles | +0.076 |
outing | +0.072 |
ries | +0.068 |
outed | +0.068 |
ateful | +0.067 |
Neg logit contributions | |
age | -0.058 |
est | -0.049 |
� | -0.041 |
ok | -0.040 |
ze | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | -1.68e-04 |
Pos logit contributions | |
age | +0.010 |
est | +0.009 |
� | +0.008 |
ok | +0.008 |
ze | +0.007 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.007 |
outed | -0.006 |
ateful | -0.006 |
ries | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
age | +0.000 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.000 |
outing | -0.000 |
ries | -0.000 |
outed | -0.000 |
ateful | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | +9.20e-03 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
� | +0.005 |
ok | +0.005 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.007 |
outed | -0.006 |
ries | -0.006 |
ateful | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
yles | +0.014 |
outing | +0.013 |
outed | +0.012 |
ateful | +0.012 |
eling | +0.011 |
Neg logit contributions | |
age | -0.019 |
est | -0.017 |
� | -0.016 |
ok | -0.015 |
best | -0.015 |
Token | or |
Token ID | 393 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
yles | +0.023 |
outing | +0.021 |
ries | +0.020 |
outed | +0.020 |
ateful | +0.020 |
Neg logit contributions | |
age | -0.021 |
est | -0.017 |
� | -0.015 |
ok | -0.014 |
ze | -0.014 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
age | +0.023 |
est | +0.020 |
� | +0.019 |
ok | +0.018 |
best | +0.017 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.019 |
outed | -0.018 |
ries | -0.017 |
ateful | -0.017 |
Token | ents |
Token ID | 658 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
yles | +0.112 |
outing | +0.095 |
eling | +0.085 |
outed | +0.085 |
ries | +0.085 |
Neg logit contributions | |
age | -0.347 |
est | -0.311 |
� | -0.295 |
ok | -0.277 |
ze | -0.271 |
Token | . |
Token ID | 13 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
yles | +0.112 |
outing | +0.105 |
outed | +0.100 |
ries | +0.100 |
ateful | +0.100 |
Neg logit contributions | |
age | -0.079 |
est | -0.066 |
� | -0.056 |
ok | -0.052 |
ze | -0.049 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
yles | +0.008 |
outing | +0.007 |
outed | +0.007 |
ries | +0.007 |
ateful | +0.007 |
Neg logit contributions | |
age | -0.007 |
est | -0.006 |
ze | -0.005 |
ok | -0.005 |
� | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
yles | +0.059 |
ries | +0.051 |
outing | +0.049 |
ila | +0.049 |
outed | +0.048 |
Neg logit contributions | |
age | -0.069 |
est | -0.060 |
ok | -0.054 |
ze | -0.052 |
biggest | -0.048 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
yles | +0.043 |
outing | +0.038 |
eling | +0.037 |
ries | +0.037 |
ateful | +0.036 |
Neg logit contributions | |
age | -0.056 |
est | -0.052 |
� | -0.049 |
ok | -0.046 |
best | -0.046 |
Token | who |
Token ID | 508 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
age | +0.035 |
est | +0.031 |
ok | +0.027 |
� | +0.026 |
biggest | +0.025 |
Neg logit contributions | |
yles | -0.030 |
outing | -0.029 |
ries | -0.027 |
ateful | -0.027 |
outed | -0.027 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.51e-03 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.002 |
ok | +0.001 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.002 |
outing | -0.002 |
outed | -0.002 |
ateful | -0.002 |
eling | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
yles | +0.008 |
outing | +0.008 |
eling | +0.007 |
outed | +0.007 |
ateful | +0.007 |
Neg logit contributions | |
age | -0.004 |
est | -0.003 |
� | -0.003 |
ze | -0.003 |
right | -0.003 |
Token | collect |
Token ID | 2824 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
yles | +0.039 |
outing | +0.035 |
ries | +0.034 |
ateful | +0.034 |
nam | +0.033 |
Neg logit contributions | |
age | -0.048 |
est | -0.042 |
� | -0.037 |
ok | -0.036 |
sy | -0.034 |
Token | or |
Token ID | 393 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
yles | +0.034 |
outing | +0.031 |
ries | +0.030 |
outed | +0.029 |
ateful | +0.029 |
Neg logit contributions | |
age | -0.039 |
est | -0.033 |
� | -0.030 |
ok | -0.029 |
ze | -0.027 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
age | +0.030 |
est | +0.028 |
� | +0.027 |
ok | +0.026 |
biggest | +0.026 |
Neg logit contributions | |
yles | -0.008 |
outing | -0.007 |
outed | -0.006 |
ries | -0.006 |
ateful | -0.005 |
Token | ents |
Token ID | 658 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
yles | +0.118 |
outing | +0.104 |
eling | +0.098 |
outed | +0.094 |
ateful | +0.092 |
Neg logit contributions | |
age | -0.333 |
est | -0.298 |
� | -0.282 |
ok | -0.259 |
ench | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
yles | +0.124 |
outing | +0.116 |
outed | +0.112 |
ateful | +0.110 |
eling | +0.109 |
Neg logit contributions | |
age | -0.073 |
est | -0.059 |
� | -0.048 |
ok | -0.043 |
ze | -0.040 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
age | +0.004 |
est | +0.003 |
� | +0.003 |
ok | +0.003 |
ze | +0.003 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.003 |
outed | -0.003 |
ries | -0.003 |
ateful | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -4.84e-04 |
Pos logit contributions | |
age | +0.072 |
est | +0.068 |
� | +0.065 |
best | +0.059 |
ok | +0.058 |
Neg logit contributions | |
yles | -0.038 |
outing | -0.038 |
outed | -0.032 |
ateful | -0.032 |
eling | -0.031 |
Token | went |
Token ID | 1816 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
� | +0.001 |
nob | +0.001 |
sy | +0.001 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
ries | -0.001 |
ateful | -0.001 |
outed | -0.001 |
Token | never |
Token ID | 1239 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
age | +0.007 |
� | +0.005 |
est | +0.005 |
ok | +0.005 |
best | +0.004 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.009 |
ries | -0.008 |
outed | -0.008 |
eling | -0.008 |
Token | played |
Token ID | 2826 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
age | +0.078 |
� | +0.068 |
est | +0.067 |
ok | +0.060 |
right | +0.057 |
Neg logit contributions | |
yles | -0.073 |
outing | -0.067 |
ries | -0.064 |
outed | -0.062 |
ateful | -0.060 |
Token | with |
Token ID | 351 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
age | +0.024 |
est | +0.020 |
� | +0.019 |
sy | +0.016 |
> | +0.015 |
Neg logit contributions | |
yles | -0.026 |
ries | -0.024 |
outing | -0.022 |
their | -0.021 |
spill | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
outed | +0.002 |
ateful | +0.002 |
eling | +0.002 |
Neg logit contributions | |
age | -0.003 |
est | -0.003 |
ok | -0.002 |
� | -0.002 |
best | -0.002 |
Token | or |
Token ID | 393 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
age | +0.014 |
est | +0.012 |
� | +0.011 |
sy | +0.010 |
ok | +0.010 |
Neg logit contributions | |
yles | -0.009 |
ries | -0.009 |
outing | -0.008 |
nam | -0.008 |
brushes | -0.008 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.28e-01 |
Pos logit contributions | |
age | +0.041 |
est | +0.034 |
� | +0.033 |
ok | +0.031 |
back | +0.030 |
Neg logit contributions | |
yles | -0.043 |
outing | -0.040 |
outed | -0.038 |
ries | -0.036 |
ateful | -0.036 |
Token | ents |
Token ID | 658 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
yles | +0.113 |
outing | +0.096 |
eling | +0.087 |
outed | +0.086 |
ries | +0.085 |
Neg logit contributions | |
age | -0.346 |
est | -0.309 |
� | -0.291 |
ok | -0.273 |
ze | -0.268 |
Token | again |
Token ID | 757 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
yles | +0.121 |
outing | +0.114 |
outed | +0.110 |
ries | +0.109 |
ateful | +0.109 |
Neg logit contributions | |
age | -0.061 |
est | -0.049 |
� | -0.040 |
ok | -0.036 |
ze | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -9.93e-04 |
Pos logit contributions | |
age | +0.025 |
est | +0.021 |
� | +0.018 |
ok | +0.016 |
ze | +0.015 |
Neg logit contributions | |
yles | -0.042 |
outing | -0.039 |
outed | -0.038 |
ries | -0.037 |
ateful | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
� | +0.001 |
ok | +0.001 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.002 |
outing | -0.002 |
ries | -0.002 |
outed | -0.002 |
ateful | -0.002 |
Token | still |
Token ID | 991 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
age | +0.003 |
� | +0.002 |
est | +0.002 |
ok | +0.002 |
best | +0.002 |
Neg logit contributions | |
yles | -0.003 |
outing | -0.003 |
ries | -0.003 |
outed | -0.003 |
ateful | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | +3.44e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
� | +0.001 |
nob | +0.001 |
sy | +0.001 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
ries | -0.001 |
ateful | -0.001 |
outed | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | -3.27e-03 |
Pos logit contributions | |
yles | +0.007 |
ries | +0.007 |
outing | +0.006 |
ateful | +0.006 |
nam | +0.006 |
Neg logit contributions | |
age | -0.005 |
est | -0.004 |
ok | -0.004 |
ze | -0.004 |
� | -0.003 |
Token | searched |
Token ID | 16499 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.004 |
ze | +0.004 |
ok | +0.004 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.006 |
ries | -0.005 |
ateful | -0.005 |
outed | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
age | +0.018 |
est | +0.016 |
� | +0.013 |
ok | +0.012 |
best | +0.012 |
Neg logit contributions | |
yles | -0.032 |
outing | -0.030 |
outed | -0.028 |
ateful | -0.028 |
ries | -0.027 |
Token | or |
Token ID | 393 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
age | +0.029 |
est | +0.027 |
� | +0.022 |
ok | +0.022 |
best | +0.021 |
Neg logit contributions | |
yles | -0.030 |
outing | -0.029 |
outed | -0.027 |
ateful | -0.026 |
eling | -0.025 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
age | +0.052 |
est | +0.048 |
� | +0.046 |
right | +0.046 |
ok | +0.046 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.012 |
ries | -0.012 |
outed | -0.011 |
irs | -0.010 |
Token | ents |
Token ID | 658 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
yles | +0.111 |
outing | +0.095 |
eling | +0.085 |
outed | +0.084 |
ries | +0.083 |
Neg logit contributions | |
age | -0.342 |
est | -0.307 |
� | -0.289 |
ok | -0.272 |
ze | -0.265 |
Token | , |
Token ID | 11 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
yles | +0.114 |
outing | +0.106 |
outed | +0.103 |
ateful | +0.102 |
eling | +0.101 |
Neg logit contributions | |
age | -0.065 |
est | -0.053 |
� | -0.042 |
ok | -0.038 |
best | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -2.96e-04 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
� | +0.005 |
ok | +0.005 |
best | +0.005 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.006 |
outed | -0.006 |
ateful | -0.006 |
ries | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.000 |
� | +0.000 |
best | +0.000 |
ok | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.000 |
ateful | -0.000 |
eling | -0.000 |
Token | more |
Token ID | 517 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
age | +0.010 |
est | +0.008 |
� | +0.008 |
sy | +0.007 |
ze | +0.007 |
Neg logit contributions | |
nam | -0.008 |
yles | -0.008 |
outing | -0.007 |
ries | -0.007 |
ateful | -0.007 |
Token | All |
Token ID | 1439 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
age | +0.004 |
est | +0.003 |
ze | +0.003 |
ok | +0.003 |
sy | +0.003 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.004 |
outed | -0.004 |
ries | -0.003 |
ateful | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
yles | +0.094 |
outing | +0.088 |
outed | +0.082 |
nam | +0.082 |
ateful | +0.082 |
Neg logit contributions | |
age | -0.068 |
est | -0.062 |
� | -0.053 |
ok | -0.045 |
best | -0.044 |
Token | these |
Token ID | 777 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
outing | +0.051 |
yles | +0.051 |
outed | +0.049 |
ateful | +0.044 |
ours | +0.044 |
Neg logit contributions | |
age | -0.036 |
est | -0.033 |
� | -0.030 |
ok | -0.027 |
best | -0.027 |
Token | lovely |
Token ID | 14081 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
age | +0.032 |
est | +0.030 |
� | +0.025 |
ok | +0.025 |
best | +0.025 |
Neg logit contributions | |
yles | -0.029 |
outing | -0.027 |
ateful | -0.024 |
outed | -0.024 |
ries | -0.024 |
Token | or |
Token ID | 393 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
age | +0.026 |
est | +0.022 |
� | +0.020 |
ok | +0.019 |
ze | +0.018 |
Neg logit contributions | |
yles | -0.024 |
outing | -0.022 |
ries | -0.021 |
outed | -0.021 |
ateful | -0.020 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
age | +0.043 |
est | +0.041 |
� | +0.039 |
ok | +0.037 |
best | +0.036 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.016 |
outed | -0.015 |
ries | -0.013 |
ateful | -0.013 |
Token | ents |
Token ID | 658 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
yles | +0.118 |
outing | +0.102 |
eling | +0.096 |
outed | +0.093 |
ateful | +0.092 |
Neg logit contributions | |
age | -0.331 |
est | -0.293 |
� | -0.279 |
ok | -0.255 |
sy | -0.254 |
Token | reminded |
Token ID | 14516 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
yles | +0.092 |
outing | +0.084 |
ateful | +0.080 |
outed | +0.080 |
nam | +0.078 |
Neg logit contributions | |
age | -0.096 |
est | -0.084 |
� | -0.073 |
ok | -0.067 |
ze | -0.065 |
Token | him |
Token ID | 683 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
age | +0.066 |
est | +0.059 |
� | +0.053 |
ok | +0.051 |
ze | +0.048 |
Neg logit contributions | |
yles | -0.048 |
outing | -0.044 |
outed | -0.041 |
ateful | -0.040 |
ries | -0.040 |
Token | of |
Token ID | 286 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
age | +0.022 |
est | +0.019 |
� | +0.017 |
ok | +0.016 |
ze | +0.016 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.017 |
ries | -0.016 |
outed | -0.015 |
ateful | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -6.38e-03 |
Pos logit contributions | |
yles | +0.050 |
outing | +0.049 |
outed | +0.046 |
ateful | +0.042 |
ries | +0.042 |
Neg logit contributions | |
age | -0.050 |
est | -0.046 |
� | -0.041 |
ok | -0.041 |
best | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
yles | +0.051 |
outing | +0.047 |
ries | +0.045 |
outed | +0.044 |
ateful | +0.044 |
Neg logit contributions | |
age | -0.048 |
est | -0.041 |
� | -0.035 |
ok | -0.033 |
ze | -0.032 |
Token | help |
Token ID | 1037 |
Feature activation | +6.53e-03 |
Pos logit contributions | |
yles | +0.025 |
ateful | +0.022 |
outing | +0.022 |
spill | +0.021 |
ila | +0.021 |
Neg logit contributions | |
age | -0.030 |
est | -0.028 |
ok | -0.023 |
� | -0.023 |
sy | -0.023 |
Token | sort |
Token ID | 3297 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
yles | +0.009 |
outing | +0.008 |
ries | +0.008 |
ateful | +0.008 |
nam | +0.008 |
Neg logit contributions | |
age | -0.014 |
est | -0.012 |
� | -0.011 |
ok | -0.011 |
ze | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -8.58e-03 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
� | +0.006 |
ok | +0.006 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.004 |
ries | -0.003 |
ateful | -0.003 |
outed | -0.003 |
Token | or |
Token ID | 393 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
age | +0.019 |
est | +0.015 |
� | +0.013 |
ok | +0.013 |
ze | +0.013 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.012 |
nam | -0.012 |
ries | -0.012 |
outed | -0.011 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
age | +0.046 |
est | +0.042 |
� | +0.040 |
ok | +0.039 |
right | +0.037 |
Neg logit contributions | |
yles | -0.029 |
outing | -0.026 |
ries | -0.025 |
outed | -0.024 |
ateful | -0.023 |
Token | ents |
Token ID | 658 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
yles | +0.116 |
outing | +0.100 |
eling | +0.091 |
outed | +0.090 |
ries | +0.089 |
Neg logit contributions | |
age | -0.333 |
est | -0.300 |
� | -0.283 |
ok | -0.264 |
ze | -0.257 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e-03 |
Pos logit contributions | |
yles | +0.109 |
outing | +0.102 |
outed | +0.098 |
ateful | +0.097 |
ries | +0.097 |
Neg logit contributions | |
age | -0.072 |
est | -0.060 |
� | -0.051 |
ok | -0.046 |
ze | -0.043 |
Token | She |
Token ID | 1375 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
ze | +0.006 |
ok | +0.006 |
� | +0.006 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.006 |
outed | -0.006 |
ries | -0.006 |
nam | -0.006 |
Token | picked |
Token ID | 6497 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
age | +0.034 |
est | +0.030 |
� | +0.027 |
ok | +0.026 |
ze | +0.025 |
Neg logit contributions | |
yles | -0.024 |
outing | -0.022 |
ries | -0.020 |
outed | -0.020 |
ateful | -0.020 |
Token | up |
Token ID | 510 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
yles | +0.021 |
outing | +0.020 |
ries | +0.019 |
outed | +0.019 |
ateful | +0.019 |
Neg logit contributions | |
age | -0.018 |
est | -0.015 |
� | -0.013 |
ok | -0.012 |
ze | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.005 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.009 |
ries | -0.008 |
outed | -0.008 |
ateful | -0.008 |
Token | especially |
Token ID | 2592 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
yles | +0.027 |
outing | +0.024 |
outed | +0.023 |
ateful | +0.023 |
ries | +0.023 |
Neg logit contributions | |
age | -0.031 |
est | -0.027 |
� | -0.024 |
ok | -0.023 |
ze | -0.022 |
Token | liked |
Token ID | 8288 |
Feature activation | -3.21e-03 |
Pos logit contributions | |
age | +0.092 |
est | +0.082 |
� | +0.073 |
ok | +0.070 |
ze | +0.067 |
Neg logit contributions | |
yles | -0.095 |
outing | -0.087 |
ries | -0.084 |
irs | -0.084 |
ateful | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.004 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.005 |
outed | -0.005 |
ries | -0.005 |
ateful | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
age | +0.017 |
est | +0.014 |
� | +0.013 |
ze | +0.012 |
sy | +0.012 |
Neg logit contributions | |
yles | -0.015 |
nam | -0.014 |
outing | -0.014 |
passports | -0.014 |
brushes | -0.014 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
age | +0.036 |
est | +0.032 |
� | +0.029 |
ok | +0.028 |
ze | +0.026 |
Neg logit contributions | |
yles | -0.028 |
outing | -0.026 |
outed | -0.024 |
ries | -0.024 |
ateful | -0.023 |
Token | ents |
Token ID | 658 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
yles | +0.117 |
outing | +0.100 |
eling | +0.092 |
outed | +0.091 |
ries | +0.090 |
Neg logit contributions | |
age | -0.333 |
est | -0.298 |
� | -0.281 |
ok | -0.261 |
ze | -0.257 |
Token | he |
Token ID | 339 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
yles | +0.115 |
outing | +0.107 |
outed | +0.103 |
ateful | +0.102 |
ries | +0.102 |
Neg logit contributions | |
age | -0.075 |
est | -0.062 |
� | -0.053 |
ok | -0.048 |
ze | -0.045 |
Token | kept |
Token ID | 4030 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
yles | +0.034 |
outing | +0.031 |
ries | +0.029 |
ateful | +0.029 |
outed | +0.029 |
Neg logit contributions | |
age | -0.040 |
est | -0.035 |
� | -0.032 |
ok | -0.030 |
ze | -0.029 |
Token | around |
Token ID | 1088 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
yles | +0.009 |
outing | +0.009 |
ries | +0.008 |
ateful | +0.008 |
outed | +0.008 |
Neg logit contributions | |
age | -0.008 |
est | -0.007 |
� | -0.006 |
ok | -0.006 |
ze | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-03 |
Pos logit contributions | |
yles | +0.029 |
nam | +0.026 |
ries | +0.026 |
outing | +0.026 |
ateful | +0.025 |
Neg logit contributions | |
age | -0.032 |
est | -0.026 |
� | -0.022 |
ok | -0.021 |
ench | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
back | +0.005 |
� | +0.005 |
right | +0.005 |
Neg logit contributions | |
outing | -0.010 |
outed | -0.009 |
yles | -0.009 |
eling | -0.009 |
ateful | -0.009 |
Token | look |
Token ID | 804 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
yles | +0.033 |
outing | +0.032 |
outed | +0.030 |
ateful | +0.029 |
ries | +0.029 |
Neg logit contributions | |
age | -0.028 |
est | -0.024 |
� | -0.022 |
ok | -0.019 |
ze | -0.019 |
Token | at |
Token ID | 379 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
yles | +0.028 |
outing | +0.026 |
ries | +0.025 |
outed | +0.025 |
nam | +0.024 |
Neg logit contributions | |
age | -0.048 |
est | -0.038 |
� | -0.035 |
nob | -0.034 |
ze | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -3.66e-03 |
Pos logit contributions | |
outing | +0.049 |
yles | +0.048 |
outed | +0.045 |
eling | +0.043 |
ateful | +0.041 |
Neg logit contributions | |
age | -0.039 |
est | -0.038 |
� | -0.031 |
biggest | -0.031 |
best | -0.030 |
Token | or |
Token ID | 393 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
age | +0.008 |
est | +0.006 |
ok | +0.006 |
� | +0.006 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.005 |
ries | -0.005 |
ateful | -0.005 |
nam | -0.005 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
age | +0.037 |
est | +0.033 |
� | +0.033 |
ok | +0.031 |
right | +0.030 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.017 |
ries | -0.016 |
outed | -0.015 |
ateful | -0.014 |
Token | ents |
Token ID | 658 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
yles | +0.119 |
outing | +0.101 |
eling | +0.099 |
ries | +0.094 |
outed | +0.093 |
Neg logit contributions | |
age | -0.326 |
est | -0.288 |
� | -0.277 |
ench | -0.252 |
ok | -0.251 |
Token | on |
Token ID | 319 |
Feature activation | -6.37e-03 |
Pos logit contributions | |
yles | +0.116 |
outing | +0.109 |
outed | +0.106 |
ateful | +0.104 |
ries | +0.103 |
Neg logit contributions | |
age | -0.069 |
est | -0.057 |
� | -0.047 |
ok | -0.042 |
ze | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
age | +0.012 |
est | +0.011 |
� | +0.010 |
ok | +0.009 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.010 |
outed | -0.010 |
ateful | -0.009 |
eling | -0.009 |
Token | tree |
Token ID | 5509 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
age | +0.003 |
ok | +0.003 |
est | +0.003 |
ench | +0.003 |
tted | +0.002 |
Neg logit contributions | |
nam | -0.002 |
salon | -0.002 |
ries | -0.002 |
brushes | -0.002 |
yles | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
yles | +0.086 |
outing | +0.080 |
outed | +0.077 |
ateful | +0.077 |
ries | +0.076 |
Neg logit contributions | |
age | -0.053 |
est | -0.042 |
� | -0.037 |
ok | -0.031 |
ze | -0.030 |
Token | take |
Token ID | 1011 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
yles | +0.031 |
ateful | +0.028 |
outing | +0.028 |
eling | +0.028 |
ries | +0.028 |
Neg logit contributions | |
age | -0.040 |
est | -0.036 |
ok | -0.030 |
� | -0.029 |
sy | -0.029 |
Token | one |
Token ID | 530 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.001 |
ok | +0.001 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.002 |
ries | -0.002 |
outing | -0.002 |
ateful | -0.002 |
nam | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
age | +0.024 |
est | +0.020 |
ze | +0.019 |
ok | +0.019 |
sy | +0.018 |
Neg logit contributions | |
yles | -0.021 |
ries | -0.021 |
outing | -0.021 |
nam | -0.020 |
salon | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
yles | +0.049 |
outing | +0.047 |
outed | +0.044 |
ateful | +0.042 |
ries | +0.041 |
Neg logit contributions | |
age | -0.055 |
est | -0.048 |
� | -0.044 |
ok | -0.042 |
best | -0.039 |
Token | or |
Token ID | 393 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
age | +0.014 |
est | +0.011 |
� | +0.011 |
ze | +0.010 |
sy | +0.010 |
Neg logit contributions | |
yles | -0.012 |
nam | -0.012 |
ries | -0.011 |
outing | -0.011 |
ateful | -0.010 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
age | +0.035 |
est | +0.031 |
� | +0.029 |
ok | +0.028 |
ze | +0.027 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.017 |
outed | -0.015 |
ries | -0.015 |
ateful | -0.015 |
Token | ents |
Token ID | 658 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
yles | +0.113 |
outing | +0.096 |
eling | +0.088 |
outed | +0.087 |
ries | +0.086 |
Neg logit contributions | |
age | -0.336 |
est | -0.300 |
� | -0.285 |
ok | -0.265 |
ze | -0.260 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
yles | +0.105 |
outing | +0.098 |
ries | +0.093 |
outed | +0.093 |
ateful | +0.093 |
Neg logit contributions | |
age | -0.078 |
est | -0.065 |
� | -0.056 |
ok | -0.052 |
ze | -0.049 |
Token | for |
Token ID | 329 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
yles | +0.031 |
outing | +0.029 |
ries | +0.027 |
ateful | +0.027 |
outed | +0.027 |
Neg logit contributions | |
age | -0.027 |
est | -0.022 |
� | -0.019 |
ok | -0.019 |
ze | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
age | +0.025 |
est | +0.020 |
� | +0.018 |
ok | +0.017 |
ze | +0.016 |
Neg logit contributions | |
yles | -0.036 |
outing | -0.035 |
outed | -0.034 |
ateful | -0.032 |
ries | -0.032 |
Token | walk |
Token ID | 2513 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.004 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.005 |
outing | -0.005 |
nam | -0.005 |
spill | -0.004 |
salon | -0.004 |
Token | box |
Token ID | 3091 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
age | +0.046 |
est | +0.036 |
ok | +0.034 |
ze | +0.033 |
tted | +0.033 |
Neg logit contributions | |
ries | -0.033 |
yles | -0.033 |
nam | -0.032 |
spill | -0.032 |
passports | -0.031 |
Token | full |
Token ID | 1336 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
age | +0.032 |
est | +0.028 |
ok | +0.023 |
� | +0.023 |
ze | +0.022 |
Neg logit contributions | |
yles | -0.039 |
outing | -0.038 |
ries | -0.036 |
outed | -0.036 |
nam | -0.035 |
Token | of |
Token ID | 286 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
age | +0.005 |
est | +0.004 |
ze | +0.004 |
ok | +0.004 |
sy | +0.004 |
Neg logit contributions | |
outing | -0.003 |
yles | -0.003 |
ries | -0.003 |
nam | -0.003 |
outed | -0.003 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
yles | +0.046 |
outing | +0.042 |
ries | +0.040 |
outed | +0.039 |
ateful | +0.039 |
Neg logit contributions | |
age | -0.058 |
est | -0.050 |
� | -0.045 |
ok | -0.043 |
ze | -0.041 |
Token | or |
Token ID | 393 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
ok | +0.006 |
� | +0.005 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.005 |
ries | -0.005 |
outing | -0.004 |
brushes | -0.004 |
nam | -0.004 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
age | +0.044 |
est | +0.041 |
� | +0.039 |
ok | +0.038 |
biggest | +0.037 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.008 |
outed | -0.007 |
ries | -0.006 |
eling | -0.006 |
Token | ents |
Token ID | 658 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
yles | +0.112 |
outing | +0.096 |
eling | +0.087 |
outed | +0.086 |
ries | +0.085 |
Neg logit contributions | |
age | -0.334 |
est | -0.300 |
� | -0.284 |
ok | -0.265 |
sy | -0.260 |
Token | . |
Token ID | 13 |
Feature activation | +5.79e-04 |
Pos logit contributions | |
yles | +0.116 |
outing | +0.108 |
outed | +0.105 |
ateful | +0.104 |
ries | +0.101 |
Neg logit contributions | |
age | -0.067 |
est | -0.054 |
� | -0.046 |
ok | -0.040 |
ze | -0.038 |
Token | |
Token ID | 220 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
yles | +0.001 |
outing | +0.001 |
outed | +0.001 |
nam | +0.001 |
ries | +0.001 |
Neg logit contributions | |
age | -0.001 |
est | -0.001 |
ok | -0.001 |
ze | -0.001 |
� | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -9.45e-03 |
Pos logit contributions | |
yles | +0.073 |
outing | +0.068 |
outed | +0.065 |
ries | +0.064 |
ateful | +0.063 |
Neg logit contributions | |
age | -0.055 |
est | -0.048 |
� | -0.038 |
ze | -0.037 |
ok | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | -9.96e-03 |
Pos logit contributions | |
age | +0.016 |
est | +0.014 |
ok | +0.011 |
ze | +0.011 |
� | +0.011 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.016 |
outed | -0.016 |
ries | -0.015 |
nam | -0.015 |
Token | many |
Token ID | 867 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
age | +0.016 |
est | +0.014 |
� | +0.012 |
ok | +0.012 |
ze | +0.011 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.016 |
outed | -0.015 |
ries | -0.015 |
ateful | -0.015 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
yles | +0.106 |
outing | +0.096 |
ries | +0.092 |
outed | +0.090 |
ateful | +0.089 |
Neg logit contributions | |
age | -0.146 |
est | -0.127 |
� | -0.116 |
ok | -0.110 |
ze | -0.107 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-03 |
Pos logit contributions | |
yles | +0.032 |
outing | +0.030 |
outed | +0.028 |
ateful | +0.028 |
eling | +0.028 |
Neg logit contributions | |
age | -0.020 |
est | -0.017 |
� | -0.014 |
ok | -0.013 |
ze | -0.012 |
Token | Some |
Token ID | 2773 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.002 |
outed | +0.002 |
ries | +0.002 |
ateful | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.002 |
ze | -0.002 |
� | -0.001 |
ok | -0.001 |
Token | or |
Token ID | 393 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
yles | +0.049 |
outing | +0.045 |
ateful | +0.041 |
outed | +0.041 |
eling | +0.040 |
Neg logit contributions | |
age | -0.060 |
est | -0.055 |
� | -0.048 |
ok | -0.044 |
best | -0.043 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
age | +0.040 |
est | +0.038 |
� | +0.036 |
ok | +0.033 |
best | +0.033 |
Neg logit contributions | |
yles | -0.022 |
outing | -0.020 |
outed | -0.019 |
ateful | -0.018 |
eling | -0.017 |
Token | ents |
Token ID | 658 |
Feature activation | +5.00e-02 |
Pos logit contributions | |
yles | +0.122 |
outing | +0.106 |
eling | +0.105 |
outed | +0.098 |
ateful | +0.097 |
Neg logit contributions | |
age | -0.321 |
est | -0.283 |
� | -0.269 |
sy | -0.244 |
ench | -0.244 |
Token | were |
Token ID | 547 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
yles | +0.097 |
outing | +0.089 |
outed | +0.085 |
ateful | +0.084 |
nam | +0.084 |
Neg logit contributions | |
age | -0.086 |
est | -0.074 |
� | -0.064 |
back | -0.058 |
ok | -0.057 |
Token | round |
Token ID | 2835 |
Feature activation | -3.21e-04 |
Pos logit contributions | |
yles | +0.049 |
outing | +0.045 |
outed | +0.042 |
eling | +0.042 |
ries | +0.042 |
Neg logit contributions | |
age | -0.040 |
est | -0.033 |
� | -0.030 |
ok | -0.028 |
best | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -6.48e-06 |
Pos logit contributions | |
age | +0.000 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
ries | -0.001 |
outed | -0.001 |
ateful | -0.001 |
Token | some |
Token ID | 617 |
Feature activation | +4.29e-02 |
Token | not |
Token ID | 407 |
Feature activation | -1.28e-04 |
Pos logit contributions | |
yles | +0.028 |
outing | +0.027 |
ries | +0.025 |
outed | +0.025 |
ateful | +0.025 |
Neg logit contributions | |
age | -0.031 |
est | -0.028 |
� | -0.023 |
ok | -0.021 |
ze | -0.021 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
age | +0.000 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
best | +0.000 |
Neg logit contributions | |
yles | -0.000 |
outing | -0.000 |
outed | -0.000 |
ries | -0.000 |
ateful | -0.000 |
Token | ." |
Token ID | 526 |
Feature activation | +7.82e-03 |
Pos logit contributions | |
age | +0.030 |
est | +0.024 |
� | +0.022 |
sy | +0.021 |
ok | +0.021 |
Neg logit contributions | |
yles | -0.032 |
ries | -0.031 |
outing | -0.030 |
ateful | -0.030 |
outed | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
yles | +0.016 |
outing | +0.015 |
eling | +0.014 |
ries | +0.014 |
ateful | +0.014 |
Neg logit contributions | |
age | -0.012 |
est | -0.010 |
� | -0.010 |
ok | -0.009 |
ze | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.001 |
ok | +0.001 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.003 |
outing | -0.003 |
outed | -0.002 |
ries | -0.002 |
ateful | -0.002 |
Token | Un |
Token ID | 3118 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
age | +0.005 |
est | +0.004 |
� | +0.004 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.005 |
outing | -0.004 |
ries | -0.004 |
outed | -0.004 |
ateful | -0.004 |
Token | cle |
Token ID | 2375 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
yles | +0.225 |
outing | +0.198 |
outed | +0.191 |
ries | +0.190 |
eling | +0.189 |
Neg logit contributions | |
age | -0.236 |
est | -0.193 |
� | -0.178 |
ok | -0.162 |
sy | -0.154 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
yles | +0.033 |
outing | +0.029 |
ries | +0.026 |
outed | +0.026 |
ateful | +0.025 |
Neg logit contributions | |
age | -0.089 |
est | -0.080 |
� | -0.073 |
ok | -0.071 |
ze | -0.070 |
Token | laughed |
Token ID | 13818 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
yles | +0.084 |
outing | +0.077 |
ateful | +0.073 |
ries | +0.073 |
outed | +0.072 |
Neg logit contributions | |
age | -0.076 |
est | -0.065 |
� | -0.059 |
ok | -0.055 |
ze | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +4.71e-04 |
Pos logit contributions | |
age | +0.015 |
est | +0.012 |
sy | +0.011 |
nob | +0.011 |
ench | +0.010 |
Neg logit contributions | |
outing | -0.011 |
yles | -0.011 |
outed | -0.011 |
ries | -0.010 |
ateful | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
yles | +0.001 |
outing | +0.001 |
eling | +0.001 |
ries | +0.001 |
ateful | +0.001 |
Neg logit contributions | |
age | -0.001 |
est | -0.000 |
� | -0.000 |
ok | -0.000 |
right | -0.000 |
Token | before |
Token ID | 878 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
yles | +0.041 |
outing | +0.037 |
ries | +0.035 |
ateful | +0.034 |
nam | +0.034 |
Neg logit contributions | |
age | -0.031 |
est | -0.026 |
� | -0.023 |
ok | -0.022 |
ench | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +5.82e-03 |
Pos logit contributions | |
yles | +0.064 |
outing | +0.060 |
outed | +0.058 |
ateful | +0.057 |
ries | +0.057 |
Neg logit contributions | |
age | -0.039 |
est | -0.032 |
� | -0.028 |
ok | -0.025 |
ze | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
yles | +0.012 |
outing | +0.011 |
ries | +0.010 |
eling | +0.010 |
ateful | +0.010 |
Neg logit contributions | |
age | -0.009 |
est | -0.008 |
� | -0.007 |
ok | -0.007 |
ze | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -4.48e-03 |
Pos logit contributions | |
age | +0.005 |
est | +0.004 |
� | +0.003 |
ok | +0.003 |
ze | +0.003 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.007 |
outed | -0.006 |
ries | -0.006 |
ateful | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.006 |
ok | +0.006 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.008 |
outing | -0.008 |
ries | -0.007 |
outed | -0.007 |
ateful | -0.007 |
Token | Un |
Token ID | 3118 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
yles | +0.033 |
eling | +0.032 |
outing | +0.032 |
ries | +0.031 |
outed | +0.030 |
Neg logit contributions | |
age | -0.024 |
� | -0.020 |
est | -0.019 |
ze | -0.016 |
right | -0.016 |
Token | ic |
Token ID | 291 |
Feature activation | -6.92e-03 |
Pos logit contributions | |
yles | +0.212 |
outing | +0.196 |
outed | +0.186 |
ries | +0.184 |
ateful | +0.182 |
Neg logit contributions | |
age | -0.239 |
est | -0.205 |
� | -0.185 |
ok | -0.172 |
ze | -0.166 |
Token | orn |
Token ID | 1211 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
age | +0.009 |
est | +0.007 |
� | +0.007 |
ok | +0.007 |
biggest | +0.006 |
Neg logit contributions | |
eling | -0.014 |
yles | -0.014 |
outing | -0.014 |
ries | -0.014 |
ateful | -0.013 |
Token | is |
Token ID | 318 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
yles | +0.089 |
outing | +0.084 |
ries | +0.082 |
eling | +0.081 |
outed | +0.079 |
Neg logit contributions | |
age | -0.075 |
est | -0.061 |
� | -0.054 |
ok | -0.052 |
ench | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
yles | +0.045 |
outing | +0.041 |
outed | +0.039 |
nam | +0.039 |
ateful | +0.039 |
Neg logit contributions | |
age | -0.047 |
est | -0.040 |
� | -0.033 |
ench | -0.032 |
nob | -0.030 |
Token | rare |
Token ID | 4071 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
age | +0.016 |
est | +0.014 |
ench | +0.013 |
� | +0.013 |
ok | +0.012 |
Neg logit contributions | |
yles | -0.012 |
nam | -0.010 |
outing | -0.010 |
ateful | -0.010 |
passports | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
age | +0.018 |
est | +0.015 |
� | +0.012 |
biggest | +0.011 |
best | +0.011 |
Neg logit contributions | |
yles | -0.038 |
outing | -0.037 |
eling | -0.035 |
outed | -0.034 |
ateful | -0.034 |
Token | tree |
Token ID | 5509 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.006 |
ok | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.008 |
outed | -0.008 |
ries | -0.008 |
ateful | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
yles | +0.099 |
outing | +0.095 |
ries | +0.091 |
outed | +0.091 |
ateful | +0.089 |
Neg logit contributions | |
age | -0.056 |
est | -0.046 |
ok | -0.037 |
� | -0.036 |
ze | -0.033 |
Token | shiny |
Token ID | 22441 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
yles | +0.018 |
outing | +0.017 |
eling | +0.016 |
outed | +0.016 |
ateful | +0.016 |
Neg logit contributions | |
age | -0.013 |
est | -0.011 |
� | -0.009 |
biggest | -0.009 |
middle | -0.008 |
Token | or |
Token ID | 393 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
yles | +0.021 |
outing | +0.019 |
ries | +0.018 |
outed | +0.018 |
ateful | +0.018 |
Neg logit contributions | |
age | -0.022 |
est | -0.019 |
� | -0.017 |
ok | -0.016 |
ze | -0.016 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
age | +0.026 |
est | +0.024 |
� | +0.023 |
ok | +0.021 |
biggest | +0.021 |
Neg logit contributions | |
yles | -0.014 |
outing | -0.013 |
outed | -0.012 |
ries | -0.011 |
eling | -0.011 |
Token | ents |
Token ID | 658 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
yles | +0.110 |
outing | +0.093 |
eling | +0.085 |
outed | +0.083 |
ries | +0.082 |
Neg logit contributions | |
age | -0.333 |
est | -0.300 |
� | -0.282 |
ok | -0.264 |
ze | -0.258 |
Token | hanging |
Token ID | 10938 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
yles | +0.132 |
outing | +0.122 |
ateful | +0.119 |
outed | +0.119 |
eling | +0.117 |
Neg logit contributions | |
age | -0.060 |
est | -0.047 |
� | -0.036 |
right | -0.031 |
back | -0.030 |
Token | from |
Token ID | 422 |
Feature activation | +6.03e-03 |
Pos logit contributions | |
age | +0.030 |
est | +0.025 |
� | +0.022 |
ok | +0.021 |
ze | +0.020 |
Neg logit contributions | |
yles | -0.036 |
outing | -0.034 |
ries | -0.033 |
outed | -0.032 |
ateful | -0.032 |
Token | its |
Token ID | 663 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
yles | +0.011 |
outing | +0.010 |
ries | +0.010 |
outed | +0.010 |
ateful | +0.010 |
Neg logit contributions | |
age | -0.011 |
est | -0.009 |
� | -0.008 |
ok | -0.008 |
ze | -0.007 |
Token | branches |
Token ID | 13737 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
nam | +0.060 |
yles | +0.058 |
ries | +0.058 |
brushes | +0.056 |
outing | +0.056 |
Neg logit contributions | |
age | -0.056 |
est | -0.050 |
� | -0.045 |
ok | -0.044 |
ze | -0.041 |
Token | at |
Token ID | 379 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
age | +0.031 |
est | +0.024 |
� | +0.023 |
nob | +0.022 |
ze | +0.021 |
Neg logit contributions | |
yles | -0.028 |
outing | -0.027 |
outed | -0.027 |
ries | -0.025 |
ateful | -0.025 |
Token | all |
Token ID | 477 |
Feature activation | +5.50e-02 |
Pos logit contributions | |
outing | +0.037 |
yles | +0.036 |
outed | +0.033 |
eling | +0.032 |
ateful | +0.032 |
Neg logit contributions | |
age | -0.032 |
est | -0.031 |
� | -0.027 |
best | -0.027 |
biggest | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
yles | +0.095 |
outing | +0.086 |
outed | +0.081 |
ateful | +0.079 |
nam | +0.077 |
Neg logit contributions | |
age | -0.104 |
est | -0.097 |
� | -0.086 |
ok | -0.077 |
best | -0.076 |
Token | different |
Token ID | 1180 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
age | +0.025 |
est | +0.021 |
� | +0.019 |
ok | +0.018 |
ze | +0.018 |
Neg logit contributions | |
yles | -0.021 |
outing | -0.020 |
ries | -0.019 |
ateful | -0.018 |
outed | -0.018 |
Token | or |
Token ID | 393 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
age | +0.011 |
est | +0.009 |
� | +0.008 |
ok | +0.008 |
ze | +0.008 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.008 |
ries | -0.008 |
ateful | -0.008 |
outed | -0.008 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
age | +0.042 |
est | +0.040 |
� | +0.039 |
ok | +0.038 |
best | +0.037 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.018 |
outed | -0.017 |
ries | -0.016 |
ila | -0.016 |
Token | ents |
Token ID | 658 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
yles | +0.115 |
outing | +0.097 |
eling | +0.094 |
outed | +0.089 |
ries | +0.089 |
Neg logit contributions | |
age | -0.324 |
est | -0.288 |
� | -0.275 |
ok | -0.252 |
sy | -0.251 |
Token | and |
Token ID | 290 |
Feature activation | -7.36e-04 |
Pos logit contributions | |
yles | +0.109 |
outing | +0.101 |
outed | +0.098 |
ateful | +0.097 |
ries | +0.095 |
Neg logit contributions | |
age | -0.065 |
est | -0.054 |
� | -0.045 |
ok | -0.039 |
ze | -0.038 |
Token | adm |
Token ID | 6178 |
Feature activation | -2.73e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
� | +0.001 |
ok | +0.001 |
best | +0.001 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.001 |
ateful | -0.001 |
eling | -0.001 |
Token | iring |
Token ID | 3428 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.004 |
ok | +0.004 |
best | +0.004 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.004 |
eling | -0.003 |
ries | -0.003 |
nam | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -8.81e-03 |
Pos logit contributions | |
yles | +0.040 |
outing | +0.038 |
outed | +0.036 |
ateful | +0.034 |
eling | +0.034 |
Neg logit contributions | |
age | -0.046 |
est | -0.043 |
� | -0.039 |
ok | -0.037 |
best | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
age | +0.030 |
est | +0.025 |
� | +0.023 |
ok | +0.021 |
ze | +0.020 |
Neg logit contributions | |
yles | -0.034 |
outing | -0.032 |
ateful | -0.030 |
outed | -0.030 |
ries | -0.030 |
Token | box |
Token ID | 3091 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
age | +0.025 |
est | +0.022 |
nob | +0.018 |
� | +0.018 |
ze | +0.017 |
Neg logit contributions | |
yles | -0.018 |
nam | -0.017 |
brushes | -0.017 |
outing | -0.017 |
passports | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
age | +0.046 |
est | +0.042 |
� | +0.037 |
ok | +0.036 |
ze | +0.036 |
Neg logit contributions | |
outing | -0.039 |
yles | -0.036 |
outed | -0.035 |
ries | -0.035 |
brushes | -0.035 |
Token | shiny |
Token ID | 22441 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
yles | +0.030 |
outing | +0.027 |
ries | +0.026 |
nam | +0.026 |
outed | +0.025 |
Neg logit contributions | |
age | -0.044 |
est | -0.038 |
� | -0.035 |
ok | -0.034 |
ze | -0.033 |
Token | or |
Token ID | 393 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
yles | +0.008 |
ries | +0.007 |
outing | +0.007 |
nam | +0.006 |
outed | +0.006 |
Neg logit contributions | |
age | -0.013 |
est | -0.011 |
� | -0.010 |
ok | -0.010 |
ze | -0.010 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
age | +0.052 |
est | +0.048 |
� | +0.046 |
ok | +0.043 |
best | +0.042 |
Neg logit contributions | |
yles | -0.025 |
outing | -0.023 |
outed | -0.021 |
eling | -0.020 |
ateful | -0.020 |
Token | ents |
Token ID | 658 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
yles | +0.109 |
outing | +0.094 |
eling | +0.085 |
outed | +0.083 |
ries | +0.082 |
Neg logit contributions | |
age | -0.331 |
est | -0.297 |
� | -0.281 |
ok | -0.262 |
ze | -0.256 |
Token | that |
Token ID | 326 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
yles | +0.107 |
outing | +0.100 |
outed | +0.096 |
ries | +0.095 |
ateful | +0.095 |
Neg logit contributions | |
age | -0.069 |
est | -0.057 |
� | -0.048 |
ok | -0.044 |
ze | -0.041 |
Token | spark |
Token ID | 9009 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
yles | +0.013 |
outing | +0.012 |
outed | +0.011 |
ateful | +0.011 |
ries | +0.011 |
Neg logit contributions | |
age | -0.024 |
est | -0.021 |
� | -0.020 |
ok | -0.019 |
ze | -0.018 |
Token | led |
Token ID | 992 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
yles | +0.060 |
outing | +0.056 |
nam | +0.054 |
ateful | +0.053 |
outed | +0.051 |
Neg logit contributions | |
age | -0.074 |
est | -0.071 |
� | -0.057 |
ze | -0.053 |
best | -0.052 |
Token | in |
Token ID | 287 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
yles | +0.071 |
outing | +0.068 |
ries | +0.066 |
nam | +0.065 |
outed | +0.064 |
Neg logit contributions | |
age | -0.068 |
est | -0.052 |
� | -0.044 |
ze | -0.043 |
ench | -0.043 |
Token | he |
Token ID | 339 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
ries | +0.001 |
outed | +0.001 |
ateful | +0.001 |
Neg logit contributions | |
age | -0.003 |
est | -0.002 |
� | -0.002 |
ok | -0.002 |
ze | -0.002 |
Token | noticed |
Token ID | 6810 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
yles | +0.020 |
outing | +0.018 |
outed | +0.017 |
ries | +0.016 |
eling | +0.016 |
Neg logit contributions | |
age | -0.029 |
est | -0.025 |
� | -0.022 |
ok | -0.022 |
ze | -0.021 |
Token | some |
Token ID | 617 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
age | +0.092 |
est | +0.080 |
� | +0.071 |
ok | +0.067 |
ze | +0.064 |
Neg logit contributions | |
yles | -0.092 |
outing | -0.085 |
outed | -0.081 |
ries | -0.080 |
ateful | -0.080 |
Token | other |
Token ID | 584 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
yles | +0.080 |
outing | +0.074 |
outed | +0.070 |
ries | +0.070 |
ateful | +0.069 |
Neg logit contributions | |
age | -0.075 |
est | -0.065 |
� | -0.057 |
ok | -0.054 |
ze | -0.052 |
Token | cater |
Token ID | 20825 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
yles | +0.052 |
outing | +0.046 |
ries | +0.046 |
ateful | +0.044 |
eling | +0.043 |
Neg logit contributions | |
age | -0.076 |
est | -0.062 |
� | -0.057 |
ok | -0.056 |
ze | -0.054 |
Token | pill |
Token ID | 27215 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
yles | +0.019 |
outing | +0.016 |
ries | +0.014 |
eling | +0.014 |
outed | +0.013 |
Neg logit contributions | |
age | -0.050 |
est | -0.045 |
� | -0.041 |
ok | -0.041 |
ze | -0.039 |
Token | ars |
Token ID | 945 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
yles | +0.241 |
outing | +0.232 |
eling | +0.220 |
outed | +0.214 |
ateful | +0.210 |
Neg logit contributions | |
age | -0.180 |
est | -0.164 |
ok | -0.131 |
� | -0.127 |
ze | -0.120 |
Token | stretching |
Token ID | 20880 |
Feature activation | -5.55e-03 |
Pos logit contributions | |
yles | +0.101 |
outing | +0.093 |
outed | +0.090 |
ateful | +0.090 |
ries | +0.089 |
Neg logit contributions | |
age | -0.072 |
est | -0.061 |
� | -0.054 |
ok | -0.049 |
ze | -0.047 |
Token | towards |
Token ID | 3371 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
age | +0.009 |
est | +0.008 |
� | +0.007 |
ok | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.010 |
ries | -0.009 |
outed | -0.009 |
ateful | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +9.92e-04 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
outed | +0.002 |
ries | +0.002 |
ateful | +0.002 |
Neg logit contributions | |
age | -0.004 |
est | -0.003 |
� | -0.003 |
ok | -0.003 |
ze | -0.003 |
Token | too |
Token ID | 1165 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
ries | +0.002 |
outed | +0.001 |
eling | +0.001 |
Neg logit contributions | |
age | -0.002 |
est | -0.001 |
ok | -0.001 |
> | -0.001 |
ze | -0.001 |
Token | can |
Token ID | 460 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
age | +0.010 |
est | +0.009 |
� | +0.007 |
ze | +0.007 |
ok | +0.007 |
Neg logit contributions | |
yles | -0.008 |
outing | -0.007 |
ries | -0.007 |
nam | -0.007 |
ateful | -0.007 |
Token | we |
Token ID | 356 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
yles | +0.038 |
outing | +0.036 |
outed | +0.034 |
ateful | +0.034 |
ries | +0.034 |
Neg logit contributions | |
age | -0.032 |
est | -0.027 |
� | -0.024 |
ok | -0.022 |
ze | -0.021 |
Token | have |
Token ID | 423 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
ok | +0.006 |
� | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.006 |
nam | -0.006 |
ries | -0.006 |
ateful | -0.006 |
Token | some |
Token ID | 617 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
yles | +0.043 |
outing | +0.042 |
outed | +0.039 |
ateful | +0.039 |
ries | +0.038 |
Neg logit contributions | |
age | -0.034 |
est | -0.029 |
� | -0.026 |
ok | -0.024 |
ze | -0.022 |
Token | or |
Token ID | 393 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
yles | +0.069 |
ries | +0.065 |
outing | +0.062 |
nam | +0.062 |
ateful | +0.060 |
Neg logit contributions | |
age | -0.084 |
est | -0.069 |
� | -0.061 |
ze | -0.060 |
sy | -0.059 |
Token | nam |
Token ID | 7402 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
age | +0.039 |
est | +0.034 |
� | +0.033 |
ok | +0.031 |
best | +0.029 |
Neg logit contributions | |
yles | -0.025 |
outing | -0.024 |
outed | -0.022 |
eling | -0.021 |
ateful | -0.021 |
Token | ents |
Token ID | 658 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
yles | +0.109 |
outing | +0.094 |
eling | +0.086 |
outed | +0.085 |
ateful | +0.083 |
Neg logit contributions | |
age | -0.326 |
est | -0.292 |
� | -0.277 |
ok | -0.258 |
ze | -0.253 |
Token | for |
Token ID | 329 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
yles | +0.102 |
outing | +0.096 |
ries | +0.093 |
outed | +0.092 |
ateful | +0.091 |
Neg logit contributions | |
age | -0.072 |
est | -0.060 |
� | -0.051 |
ok | -0.048 |
ze | -0.046 |
Token | our |
Token ID | 674 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
age | +0.030 |
est | +0.026 |
� | +0.025 |
ok | +0.023 |
ze | +0.022 |
Neg logit contributions | |
yles | -0.036 |
outing | -0.035 |
outed | -0.033 |
ateful | -0.032 |
eling | -0.030 |
Token | snow |
Token ID | 6729 |
Feature activation | +6.86e-03 |
Pos logit contributions | |
age | +0.046 |
est | +0.039 |
� | +0.035 |
ok | +0.033 |
sy | +0.033 |
Neg logit contributions | |
yles | -0.036 |
ries | -0.032 |
outing | -0.032 |
nam | -0.032 |
ateful | -0.031 |
Token | man |
Token ID | 805 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
yles | +0.014 |
ries | +0.013 |
salon | +0.012 |
outing | +0.012 |
outed | +0.012 |
Neg logit contributions | |
age | -0.009 |
est | -0.008 |
� | -0.008 |
ok | -0.007 |
sy | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
yles | +0.048 |
outing | +0.045 |
ries | +0.043 |
outed | +0.043 |
ateful | +0.042 |
Neg logit contributions | |
age | -0.039 |
est | -0.033 |
� | -0.028 |
ok | -0.026 |
ze | -0.025 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -3.31e-03 |
Pos logit contributions | |
yles | +0.029 |
outing | +0.026 |
ries | +0.026 |
eling | +0.025 |
ateful | +0.025 |
Neg logit contributions | |
age | -0.019 |
est | -0.016 |
� | -0.016 |
ok | -0.013 |
sy | -0.013 |
Token | inside |
Token ID | 2641 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
age | +0.005 |
est | +0.004 |
� | +0.003 |
ok | +0.003 |
ze | +0.003 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.007 |
ries | -0.006 |
outed | -0.006 |
ateful | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -8.73e-04 |
Pos logit contributions | |
yles | +0.031 |
outing | +0.029 |
outed | +0.027 |
ateful | +0.027 |
nam | +0.026 |
Neg logit contributions | |
age | -0.031 |
est | -0.028 |
� | -0.025 |
ok | -0.023 |
best | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
age | +0.002 |
est | +0.001 |
� | +0.001 |
ok | +0.001 |
best | +0.001 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
ateful | -0.001 |
outed | -0.001 |
eling | -0.001 |
Token | fringe |
Token ID | 26821 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
age | +0.022 |
est | +0.018 |
� | +0.016 |
ok | +0.015 |
ze | +0.015 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.017 |
outed | -0.016 |
ries | -0.016 |
ateful | -0.016 |
Token | from |
Token ID | 422 |
Feature activation | +3.93e-04 |
Pos logit contributions | |
age | +0.220 |
est | +0.185 |
� | +0.161 |
ok | +0.151 |
ze | +0.144 |
Neg logit contributions | |
yles | -0.267 |
outing | -0.250 |
ries | -0.237 |
outed | -0.237 |
ateful | -0.235 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
yles | +0.001 |
outing | +0.001 |
outed | +0.001 |
ateful | +0.001 |
eling | +0.001 |
Neg logit contributions | |
age | -0.001 |
est | -0.001 |
� | -0.001 |
ok | -0.000 |
biggest | -0.000 |
Token | cut |
Token ID | 2005 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
age | +0.022 |
est | +0.018 |
� | +0.016 |
ok | +0.016 |
house | +0.015 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.014 |
outed | -0.013 |
eling | -0.013 |
ries | -0.013 |
Token | shells |
Token ID | 19679 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
age | +0.022 |
est | +0.018 |
� | +0.016 |
ok | +0.015 |
ze | +0.015 |
Neg logit contributions | |
yles | -0.023 |
outing | -0.022 |
ries | -0.021 |
outed | -0.020 |
ateful | -0.020 |
Token | made |
Token ID | 925 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
yles | +0.031 |
outing | +0.029 |
outed | +0.028 |
ateful | +0.028 |
ries | +0.028 |
Neg logit contributions | |
age | -0.021 |
est | -0.018 |
� | -0.016 |
ok | -0.014 |
ze | -0.013 |
Token | replied |
Token ID | 8712 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
age | +0.028 |
est | +0.025 |
� | +0.022 |
ok | +0.021 |
ze | +0.020 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.015 |
outed | -0.015 |
ries | -0.014 |
eling | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
age | +0.007 |
est | +0.005 |
entire | +0.005 |
iver | +0.005 |
� | +0.005 |
Neg logit contributions | |
outing | -0.007 |
they | -0.007 |
yles | -0.006 |
their | -0.006 |
outed | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
yles | +0.004 |
outing | +0.003 |
ateful | +0.003 |
outed | +0.003 |
ries | +0.003 |
Neg logit contributions | |
age | -0.003 |
est | -0.003 |
� | -0.002 |
ok | -0.002 |
ze | -0.002 |
Token | gentle |
Token ID | 10296 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
age | +0.020 |
est | +0.018 |
� | +0.015 |
nob | +0.015 |
ze | +0.015 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.015 |
outed | -0.014 |
nam | -0.014 |
ateful | -0.013 |
Token | ' |
Token ID | 705 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
yles | +0.025 |
outing | +0.025 |
outed | +0.024 |
frowned | +0.023 |
passports | +0.022 |
Neg logit contributions | |
age | -0.040 |
est | -0.034 |
� | -0.033 |
ok | -0.031 |
biggest | -0.031 |
Token | yip |
Token ID | 39666 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
yles | +0.033 |
outing | +0.032 |
outed | +0.030 |
ateful | +0.030 |
ries | +0.030 |
Neg logit contributions | |
age | -0.033 |
est | -0.028 |
� | -0.026 |
ok | -0.022 |
sy | -0.021 |
Token | '. |
Token ID | 4458 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
age | +0.166 |
est | +0.123 |
biggest | +0.110 |
nob | +0.108 |
middle | +0.104 |
Neg logit contributions | |
outing | -0.261 |
yles | -0.249 |
ries | -0.241 |
ateful | -0.237 |
outed | -0.234 |
Token |
|
Token ID | 198 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
age | +0.047 |
est | +0.041 |
ze | +0.033 |
� | +0.033 |
ok | +0.032 |
Neg logit contributions | |
yles | -0.056 |
outing | -0.052 |
outed | -0.051 |
ries | -0.049 |
nam | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -9.99e-03 |
Pos logit contributions | |
est | +0.019 |
age | +0.018 |
ok | +0.015 |
biggest | +0.014 |
ze | +0.014 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.012 |
ila | -0.012 |
outed | -0.011 |
irs | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | -9.93e-03 |
Pos logit contributions | |
est | +0.018 |
age | +0.017 |
ok | +0.014 |
best | +0.014 |
biggest | +0.014 |
Neg logit contributions | |
outing | -0.016 |
yles | -0.015 |
outed | -0.014 |
ateful | -0.014 |
ila | -0.014 |
Token | little |
Token ID | 1310 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
age | +0.019 |
est | +0.016 |
� | +0.014 |
ok | +0.014 |
nob | +0.013 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.015 |
outed | -0.015 |
nam | -0.014 |
ateful | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
yles | +0.038 |
outing | +0.035 |
outed | +0.033 |
ateful | +0.032 |
ries | +0.032 |
Neg logit contributions | |
age | -0.045 |
est | -0.039 |
� | -0.037 |
ok | -0.035 |
ze | -0.033 |
Token | cars |
Token ID | 5006 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
age | +0.034 |
est | +0.030 |
� | +0.026 |
ok | +0.025 |
ze | +0.024 |
Neg logit contributions | |
yles | -0.031 |
outing | -0.029 |
outed | -0.028 |
ries | -0.027 |
ateful | -0.027 |
Token | stopped |
Token ID | 5025 |
Feature activation | +2.88e-03 |
Pos logit contributions | |
age | +0.048 |
est | +0.041 |
� | +0.038 |
ok | +0.035 |
ze | +0.034 |
Neg logit contributions | |
yles | -0.039 |
outing | -0.036 |
ateful | -0.034 |
ries | -0.033 |
nam | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -6.77e-03 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.005 |
ries | +0.005 |
outed | +0.005 |
ateful | +0.005 |
Neg logit contributions | |
age | -0.005 |
est | -0.004 |
� | -0.003 |
ok | -0.003 |
ze | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
age | +0.013 |
est | +0.011 |
� | +0.011 |
ok | +0.010 |
right | +0.010 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.011 |
ateful | -0.010 |
outed | -0.010 |
ries | -0.010 |
Token | pedestrian |
Token ID | 22382 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
age | +0.029 |
est | +0.025 |
� | +0.022 |
ok | +0.021 |
ench | +0.021 |
Neg logit contributions | |
yles | -0.024 |
outing | -0.023 |
nam | -0.022 |
outed | -0.022 |
passports | -0.022 |
Token | light |
Token ID | 1657 |
Feature activation | +3.96e-02 |
Pos logit contributions | |
age | +0.208 |
est | +0.151 |
� | +0.146 |
ze | +0.142 |
ok | +0.141 |
Neg logit contributions | |
outing | -0.224 |
yles | -0.217 |
outed | -0.211 |
ries | -0.205 |
brushes | -0.201 |
Token | turned |
Token ID | 2900 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
yles | +0.080 |
outing | +0.074 |
ateful | +0.071 |
outed | +0.070 |
nam | +0.070 |
Neg logit contributions | |
age | -0.064 |
est | -0.055 |
� | -0.047 |
ok | -0.043 |
ze | -0.042 |
Token | green |
Token ID | 4077 |
Feature activation | -9.13e-03 |
Pos logit contributions | |
yles | +0.038 |
outing | +0.035 |
outed | +0.033 |
ries | +0.033 |
ateful | +0.033 |
Neg logit contributions | |
age | -0.034 |
est | -0.030 |
� | -0.026 |
ok | -0.024 |
ze | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -7.53e-03 |
Pos logit contributions | |
age | +0.017 |
est | +0.015 |
� | +0.013 |
ok | +0.012 |
ze | +0.012 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.015 |
outed | -0.014 |
ries | -0.014 |
ateful | -0.014 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
age | +0.014 |
est | +0.012 |
ze | +0.010 |
ok | +0.009 |
sy | +0.009 |
Neg logit contributions | |
yles | -0.014 |
outed | -0.012 |
outing | -0.012 |
nam | -0.011 |
ries | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
age | +0.020 |
est | +0.017 |
� | +0.014 |
ok | +0.013 |
ze | +0.012 |
Neg logit contributions | |
yles | -0.029 |
outing | -0.027 |
ries | -0.026 |
outed | -0.026 |
ateful | -0.025 |
Token | books |
Token ID | 3835 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
age | +0.011 |
est | +0.010 |
� | +0.009 |
middle | +0.008 |
ze | +0.008 |
Neg logit contributions | |
outing | -0.011 |
yles | -0.011 |
outed | -0.010 |
ries | -0.010 |
eling | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-03 |
Pos logit contributions | |
age | +0.058 |
est | +0.046 |
� | +0.042 |
right | +0.032 |
ok | +0.031 |
Neg logit contributions | |
yles | -0.119 |
outing | -0.113 |
outed | -0.112 |
ateful | -0.109 |
nam | -0.108 |
Token | They |
Token ID | 1119 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.004 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.004 |
outed | -0.004 |
ateful | -0.004 |
ries | -0.004 |
Token | see |
Token ID | 766 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
age | +0.008 |
� | +0.007 |
est | +0.007 |
ok | +0.006 |
right | +0.006 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.010 |
outed | -0.010 |
ries | -0.010 |
ateful | -0.009 |
Token | alt |
Token ID | 5988 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.006 |
ok | +0.006 |
best | +0.006 |
Neg logit contributions | |
yles | -0.008 |
outing | -0.007 |
outed | -0.007 |
eling | -0.007 |
ries | -0.007 |
Token | ars |
Token ID | 945 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
age | +0.159 |
est | +0.112 |
� | +0.102 |
ze | +0.080 |
ok | +0.080 |
Neg logit contributions | |
yles | -0.310 |
ries | -0.286 |
outing | -0.282 |
ateful | -0.280 |
nam | -0.280 |
Token | and |
Token ID | 290 |
Feature activation | -6.69e-03 |
Pos logit contributions | |
yles | +0.074 |
outing | +0.069 |
outed | +0.067 |
ries | +0.066 |
ateful | +0.066 |
Neg logit contributions | |
age | -0.043 |
est | -0.035 |
� | -0.030 |
ok | -0.027 |
ze | -0.025 |
Token | offerings |
Token ID | 18369 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
age | +0.012 |
est | +0.010 |
� | +0.010 |
middle | +0.009 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.012 |
outing | -0.011 |
outed | -0.011 |
ries | -0.010 |
ateful | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
age | +0.026 |
est | +0.022 |
� | +0.018 |
best | +0.014 |
right | +0.013 |
Neg logit contributions | |
yles | -0.072 |
outing | -0.067 |
outed | -0.067 |
nam | -0.067 |
eling | -0.066 |
Token | priests |
Token ID | 17345 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
age | +0.013 |
est | +0.011 |
� | +0.011 |
ok | +0.009 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.013 |
outed | -0.012 |
ries | -0.011 |
ateful | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | +6.18e-03 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.005 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.008 |
ries | -0.008 |
ateful | -0.008 |
outed | -0.008 |
Token | We |
Token ID | 1135 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
yles | +0.011 |
outing | +0.010 |
ateful | +0.009 |
ries | +0.009 |
outed | +0.009 |
Neg logit contributions | |
age | -0.011 |
est | -0.010 |
ok | -0.009 |
� | -0.008 |
ench | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
age | +0.070 |
est | +0.062 |
ok | +0.052 |
� | +0.052 |
nob | +0.051 |
Neg logit contributions | |
yles | -0.044 |
ateful | -0.038 |
outing | -0.038 |
eling | -0.037 |
outed | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
yles | +0.053 |
nam | +0.045 |
ateful | +0.044 |
ries | +0.042 |
eling | +0.041 |
Neg logit contributions | |
age | -0.093 |
est | -0.083 |
nob | -0.067 |
ench | -0.066 |
� | -0.064 |
Token | weapon |
Token ID | 4282 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
age | +0.012 |
est | +0.009 |
� | +0.007 |
nob | +0.007 |
ench | +0.007 |
Neg logit contributions | |
yles | -0.017 |
ateful | -0.016 |
outing | -0.016 |
nam | -0.016 |
salon | -0.015 |
Token | creators |
Token ID | 16294 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
yles | +0.054 |
outing | +0.051 |
ries | +0.050 |
they | +0.049 |
spill | +0.048 |
Neg logit contributions | |
age | -0.046 |
est | -0.037 |
ench | -0.034 |
ok | -0.033 |
middle | -0.032 |
Token | ! |
Token ID | 0 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
age | +0.173 |
est | +0.136 |
ok | +0.117 |
� | +0.114 |
biggest | +0.112 |
Neg logit contributions | |
yles | -0.256 |
outing | -0.234 |
ateful | -0.227 |
ries | -0.225 |
eling | -0.223 |
Token | We |
Token ID | 775 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
age | +0.015 |
est | +0.014 |
ench | +0.012 |
sy | +0.011 |
ok | +0.011 |
Neg logit contributions | |
yles | -0.014 |
ateful | -0.012 |
outing | -0.011 |
ila | -0.011 |
they | -0.011 |
Token | can |
Token ID | 460 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
yles | +0.009 |
outing | +0.008 |
eling | +0.008 |
ateful | +0.008 |
outed | +0.008 |
Neg logit contributions | |
age | -0.013 |
est | -0.012 |
ok | -0.010 |
� | -0.010 |
ze | -0.010 |
Token | stop |
Token ID | 2245 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
yles | +0.032 |
outing | +0.028 |
spill | +0.027 |
eling | +0.027 |
ateful | +0.027 |
Neg logit contributions | |
age | -0.040 |
est | -0.038 |
ok | -0.031 |
sy | -0.029 |
� | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -9.45e-03 |
Pos logit contributions | |
yles | +0.021 |
outing | +0.018 |
ries | +0.017 |
eling | +0.017 |
ateful | +0.017 |
Neg logit contributions | |
age | -0.033 |
est | -0.028 |
sy | -0.024 |
nob | -0.024 |
tted | -0.023 |
Token | into |
Token ID | 656 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
age | +0.051 |
est | +0.043 |
ok | +0.037 |
� | +0.036 |
ze | +0.035 |
Neg logit contributions | |
yles | -0.058 |
outing | -0.055 |
ries | -0.054 |
outed | -0.052 |
ateful | -0.051 |
Token | two |
Token ID | 734 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
yles | +0.005 |
outing | +0.005 |
outed | +0.005 |
ries | +0.005 |
ateful | +0.005 |
Neg logit contributions | |
age | -0.005 |
est | -0.004 |
� | -0.004 |
ok | -0.003 |
ze | -0.003 |
Token | bowls |
Token ID | 34796 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
yles | +0.037 |
outing | +0.034 |
ries | +0.033 |
eling | +0.032 |
outed | +0.032 |
Neg logit contributions | |
age | -0.039 |
est | -0.032 |
ok | -0.027 |
� | -0.026 |
ze | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -3.12e-03 |
Pos logit contributions | |
age | +0.067 |
est | +0.056 |
ok | +0.047 |
ze | +0.046 |
� | +0.046 |
Neg logit contributions | |
yles | -0.077 |
outing | -0.074 |
ries | -0.072 |
outed | -0.069 |
ateful | -0.067 |
Token | then |
Token ID | 788 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
age | +0.006 |
est | +0.005 |
� | +0.004 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.005 |
outing | -0.005 |
ries | -0.005 |
nam | -0.005 |
outed | -0.005 |
Token | voted |
Token ID | 7052 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
yles | +0.024 |
outing | +0.022 |
ries | +0.021 |
outed | +0.020 |
ateful | +0.020 |
Neg logit contributions | |
age | -0.035 |
est | -0.031 |
� | -0.027 |
ok | -0.026 |
ze | -0.026 |
Token | for |
Token ID | 329 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
age | +0.190 |
est | +0.152 |
� | +0.128 |
ze | +0.121 |
ok | +0.119 |
Neg logit contributions | |
yles | -0.218 |
outing | -0.207 |
ries | -0.199 |
outed | -0.195 |
ateful | -0.193 |
Token | their |
Token ID | 511 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
age | +0.035 |
est | +0.032 |
� | +0.030 |
ok | +0.028 |
best | +0.027 |
Neg logit contributions | |
yles | -0.027 |
outing | -0.025 |
outed | -0.024 |
ateful | -0.023 |
eling | -0.022 |
Token | favourite |
Token ID | 12507 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
yles | +0.040 |
outing | +0.038 |
ries | +0.037 |
outed | +0.037 |
ateful | +0.036 |
Neg logit contributions | |
age | -0.042 |
est | -0.034 |
� | -0.029 |
nob | -0.027 |
sy | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
age | +0.063 |
est | +0.050 |
� | +0.045 |
ok | +0.045 |
sy | +0.043 |
Neg logit contributions | |
yles | -0.054 |
ries | -0.050 |
outing | -0.049 |
eling | -0.047 |
outed | -0.046 |
Token | Toby |
Token ID | 37578 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
yles | +0.004 |
outing | +0.003 |
outed | +0.003 |
ries | +0.003 |
ateful | +0.003 |
Neg logit contributions | |
age | -0.004 |
est | -0.003 |
ze | -0.003 |
ok | -0.003 |
� | -0.003 |
Token | smiled |
Token ID | 13541 |
Feature activation | +4.17e-03 |
Pos logit contributions | |
age | +0.054 |
est | +0.046 |
� | +0.040 |
ok | +0.038 |
ze | +0.036 |
Neg logit contributions | |
yles | -0.059 |
outing | -0.054 |
outed | -0.052 |
ries | -0.051 |
ateful | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -1.66e-03 |
Pos logit contributions | |
yles | +0.008 |
outing | +0.007 |
outed | +0.007 |
ateful | +0.007 |
nam | +0.007 |
Neg logit contributions | |
age | -0.007 |
est | -0.006 |
� | -0.005 |
nob | -0.005 |
ok | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
age | +0.003 |
� | +0.003 |
est | +0.003 |
ok | +0.003 |
back | +0.002 |
Neg logit contributions | |
outing | -0.003 |
yles | -0.003 |
ries | -0.003 |
ateful | -0.002 |
irs | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-03 |
Pos logit contributions | |
age | +0.014 |
est | +0.011 |
� | +0.009 |
nob | +0.009 |
ok | +0.009 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.016 |
outed | -0.015 |
nam | -0.015 |
ateful | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | +7.87e-03 |
Pos logit contributions | |
age | +0.004 |
est | +0.003 |
� | +0.003 |
ok | +0.003 |
ze | +0.003 |
Neg logit contributions | |
yles | -0.005 |
outing | -0.004 |
outed | -0.004 |
ries | -0.004 |
ateful | -0.004 |
Token | Church |
Token ID | 46686 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
yles | +0.014 |
outing | +0.013 |
ries | +0.012 |
outed | +0.012 |
ateful | +0.012 |
Neg logit contributions | |
age | -0.015 |
est | -0.013 |
� | -0.011 |
ok | -0.011 |
ze | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
age | +0.186 |
est | +0.132 |
tted | +0.120 |
� | +0.117 |
ok | +0.116 |
Neg logit contributions | |
yles | -0.201 |
ries | -0.186 |
eling | -0.183 |
outing | -0.183 |
outed | -0.175 |
Token | so |
Token ID | 523 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
yles | +0.043 |
outing | +0.039 |
eling | +0.038 |
ries | +0.038 |
nam | +0.038 |
Neg logit contributions | |
age | -0.045 |
est | -0.037 |
ench | -0.029 |
� | -0.029 |
tted | -0.029 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
yles | +0.029 |
outing | +0.027 |
ries | +0.027 |
outed | +0.026 |
ateful | +0.025 |
Neg logit contributions | |
age | -0.018 |
est | -0.015 |
� | -0.013 |
ok | -0.012 |
best | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
age | +0.030 |
est | +0.023 |
� | +0.020 |
tted | +0.020 |
ok | +0.020 |
Neg logit contributions | |
yles | -0.033 |
ries | -0.030 |
outing | -0.029 |
passports | -0.029 |
they | -0.028 |
Token | my |
Token ID | 1820 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
age | +0.017 |
est | +0.014 |
ze | +0.012 |
� | +0.012 |
middle | +0.011 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.019 |
ries | -0.018 |
outed | -0.017 |
ateful | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
age | +0.014 |
est | +0.012 |
� | +0.012 |
right | +0.010 |
middle | +0.010 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.016 |
outed | -0.016 |
ateful | -0.015 |
eling | -0.014 |
Token | ground |
Token ID | 2323 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
age | +0.021 |
est | +0.018 |
ok | +0.016 |
� | +0.015 |
ench | +0.014 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.019 |
nam | -0.019 |
spill | -0.018 |
ries | -0.018 |
Token | that |
Token ID | 326 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
yles | +0.046 |
outing | +0.041 |
ateful | +0.041 |
nam | +0.040 |
outed | +0.040 |
Neg logit contributions | |
age | -0.025 |
est | -0.020 |
� | -0.017 |
ze | -0.014 |
ok | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | -1.35e-03 |
Pos logit contributions | |
yles | +0.016 |
outing | +0.015 |
eling | +0.014 |
ateful | +0.013 |
ries | +0.013 |
Neg logit contributions | |
age | -0.020 |
est | -0.018 |
� | -0.017 |
right | -0.016 |
best | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.002 |
ench | +0.002 |
entire | +0.002 |
Neg logit contributions | |
yles | -0.002 |
outing | -0.002 |
ries | -0.002 |
ateful | -0.002 |
outed | -0.002 |
Token | short |
Token ID | 19509 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
yles | +0.012 |
outing | +0.011 |
outed | +0.011 |
ries | +0.011 |
ateful | +0.011 |
Neg logit contributions | |
age | -0.013 |
est | -0.012 |
� | -0.010 |
ok | -0.010 |
ze | -0.009 |
Token | cut |
Token ID | 8968 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
age | +0.143 |
est | +0.112 |
ok | +0.096 |
� | +0.091 |
biggest | +0.091 |
Neg logit contributions | |
yles | -0.218 |
outing | -0.211 |
ries | -0.206 |
arose | -0.202 |
passports | -0.200 |
Token | ". |
Token ID | 1911 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
yles | +0.044 |
ries | +0.044 |
outing | +0.042 |
ateful | +0.041 |
eling | +0.038 |
Neg logit contributions | |
age | -0.044 |
� | -0.034 |
est | -0.034 |
ok | -0.032 |
nob | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
yles | +0.012 |
outing | +0.011 |
outed | +0.011 |
ries | +0.011 |
nam | +0.011 |
Neg logit contributions | |
age | -0.015 |
est | -0.013 |
� | -0.012 |
ok | -0.012 |
ze | -0.011 |
Token | thought |
Token ID | 1807 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
age | +0.037 |
est | +0.032 |
� | +0.031 |
ok | +0.028 |
ze | +0.028 |
Neg logit contributions | |
yles | -0.028 |
outing | -0.026 |
ateful | -0.025 |
ries | -0.024 |
nam | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
age | +0.056 |
est | +0.049 |
� | +0.045 |
ok | +0.042 |
ze | +0.040 |
Neg logit contributions | |
yles | -0.049 |
outing | -0.045 |
outed | -0.043 |
ateful | -0.042 |
ries | -0.042 |
Token | little |
Token ID | 1310 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
age | +0.028 |
est | +0.023 |
� | +0.021 |
ok | +0.020 |
ench | +0.020 |
Neg logit contributions | |
yles | -0.021 |
outing | -0.019 |
nam | -0.019 |
outed | -0.018 |
ateful | -0.018 |
Token | one |
Token ID | 530 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
yles | +0.023 |
outing | +0.021 |
ries | +0.020 |
outed | +0.020 |
ateful | +0.020 |
Neg logit contributions | |
age | -0.030 |
est | -0.025 |
� | -0.023 |
ok | -0.022 |
ze | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | +8.78e-03 |
Pos logit contributions | |
age | +0.035 |
est | +0.030 |
� | +0.027 |
ok | +0.026 |
ze | +0.024 |
Neg logit contributions | |
yles | -0.034 |
outing | -0.031 |
outed | -0.030 |
ries | -0.030 |
ateful | -0.029 |
Token | costume |
Token ID | 16569 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
yles | +0.015 |
outing | +0.013 |
outed | +0.013 |
ateful | +0.013 |
ries | +0.012 |
Neg logit contributions | |
age | -0.017 |
est | -0.014 |
� | -0.013 |
ok | -0.012 |
nob | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -9.11e-05 |
Pos logit contributions | |
age | +0.044 |
est | +0.037 |
� | +0.033 |
ok | +0.032 |
ze | +0.030 |
Neg logit contributions | |
yles | -0.042 |
outing | -0.038 |
outed | -0.037 |
ries | -0.036 |
ateful | -0.036 |
Token | voted |
Token ID | 7052 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
age | +0.000 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.000 |
outing | -0.000 |
outed | -0.000 |
ries | -0.000 |
ateful | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
age | +0.181 |
est | +0.143 |
� | +0.121 |
ze | +0.112 |
ok | +0.112 |
Neg logit contributions | |
yles | -0.217 |
outing | -0.205 |
ries | -0.195 |
outed | -0.192 |
ateful | -0.192 |
Token | best |
Token ID | 1266 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
age | +0.017 |
est | +0.011 |
ench | +0.010 |
� | +0.010 |
nob | +0.010 |
Neg logit contributions | |
yles | -0.021 |
passports | -0.020 |
outing | -0.019 |
ateful | -0.019 |
nam | -0.019 |
Token | ! |
Token ID | 0 |
Feature activation | -9.53e-03 |
Pos logit contributions | |
age | +0.103 |
est | +0.083 |
� | +0.073 |
ok | +0.069 |
ze | +0.066 |
Neg logit contributions | |
yles | -0.129 |
outing | -0.118 |
ries | -0.113 |
ateful | -0.113 |
outed | -0.113 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
age | +0.015 |
est | +0.012 |
ok | +0.010 |
� | +0.010 |
ze | +0.010 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.018 |
outed | -0.018 |
ries | -0.017 |
ateful | -0.017 |
Token | cheered |
Token ID | 34767 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
yles | +0.039 |
outing | +0.037 |
ries | +0.035 |
ateful | +0.034 |
outed | +0.034 |
Neg logit contributions | |
age | -0.032 |
est | -0.028 |
� | -0.026 |
ok | -0.021 |
ze | -0.021 |
Token | - |
Token ID | 532 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
age | +0.050 |
est | +0.042 |
� | +0.035 |
ok | +0.035 |
ench | +0.034 |
Neg logit contributions | |
yles | -0.062 |
outing | -0.059 |
ries | -0.056 |
outed | -0.056 |
nam | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.003 |
ries | +0.003 |
nam | +0.003 |
outed | +0.003 |
Neg logit contributions | |
age | -0.004 |
est | -0.003 |
� | -0.003 |
ok | -0.003 |
ench | -0.003 |
Token | shirt |
Token ID | 10147 |
Feature activation | -2.87e-02 |
Pos logit contributions | |
age | +0.018 |
est | +0.015 |
nob | +0.013 |
ok | +0.013 |
ench | +0.012 |
Neg logit contributions | |
yles | -0.013 |
nam | -0.012 |
outing | -0.012 |
salon | -0.012 |
spill | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +8.54e-04 |
Pos logit contributions | |
age | +0.046 |
est | +0.037 |
ok | +0.035 |
ench | +0.034 |
advantage | +0.031 |
Neg logit contributions | |
yles | -0.050 |
outing | -0.048 |
ries | -0.046 |
spill | -0.045 |
brushes | -0.045 |
Token | pants |
Token ID | 12581 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.001 |
ries | +0.001 |
outed | +0.001 |
nam | +0.001 |
Neg logit contributions | |
age | -0.002 |
est | -0.001 |
� | -0.001 |
ok | -0.001 |
ze | -0.001 |
Token | combo |
Token ID | 14831 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
age | +0.060 |
est | +0.050 |
� | +0.042 |
ok | +0.042 |
ze | +0.039 |
Neg logit contributions | |
yles | -0.078 |
outing | -0.073 |
ries | -0.070 |
outed | -0.070 |
ateful | -0.068 |
Token | - |
Token ID | 532 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
age | +0.173 |
est | +0.140 |
ok | +0.122 |
ench | +0.118 |
� | +0.117 |
Neg logit contributions | |
yles | -0.204 |
outing | -0.193 |
ries | -0.183 |
outed | -0.181 |
ateful | -0.177 |
Token | and |
Token ID | 290 |
Feature activation | +3.84e-04 |
Pos logit contributions | |
yles | +0.004 |
outing | +0.004 |
outed | +0.003 |
ries | +0.003 |
ateful | +0.003 |
Neg logit contributions | |
age | -0.005 |
est | -0.004 |
� | -0.004 |
ok | -0.004 |
ze | -0.003 |
Token | brushed |
Token ID | 31782 |
Feature activation | +5.18e-03 |
Pos logit contributions | |
yles | +0.001 |
outing | +0.001 |
ries | +0.001 |
outed | +0.001 |
nam | +0.001 |
Neg logit contributions | |
age | -0.001 |
est | -0.001 |
� | -0.001 |
ok | -0.001 |
ze | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
yles | +0.010 |
outing | +0.010 |
ries | +0.009 |
outed | +0.009 |
ateful | +0.009 |
Neg logit contributions | |
age | -0.008 |
est | -0.007 |
� | -0.006 |
ok | -0.006 |
ze | -0.005 |
Token | hair |
Token ID | 4190 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
yles | +0.045 |
outing | +0.041 |
outed | +0.040 |
ries | +0.038 |
nam | +0.038 |
Neg logit contributions | |
age | -0.061 |
est | -0.052 |
� | -0.047 |
ok | -0.045 |
nob | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -8.94e-03 |
Pos logit contributions | |
yles | +0.008 |
outing | +0.008 |
ateful | +0.007 |
ries | +0.007 |
outed | +0.007 |
Neg logit contributions | |
age | -0.005 |
est | -0.005 |
� | -0.004 |
ok | -0.003 |
ze | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
age | +0.015 |
est | +0.014 |
ok | +0.011 |
� | +0.010 |
biggest | +0.010 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.015 |
outed | -0.015 |
ateful | -0.014 |
ries | -0.014 |
Token | So |
Token ID | 2396 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
age | +0.020 |
est | +0.018 |
ok | +0.015 |
� | +0.015 |
biggest | +0.014 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.018 |
ateful | -0.016 |
outed | -0.016 |
eling | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
age | +0.031 |
est | +0.026 |
� | +0.023 |
ok | +0.020 |
ze | +0.018 |
Neg logit contributions | |
yles | -0.052 |
outing | -0.049 |
ries | -0.047 |
outed | -0.047 |
ateful | -0.046 |
Token | with |
Token ID | 351 |
Feature activation | +3.62e-05 |
Pos logit contributions | |
age | +0.014 |
est | +0.013 |
� | +0.013 |
right | +0.012 |
best | +0.012 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.012 |
ateful | -0.011 |
outed | -0.011 |
ries | -0.011 |
Token | artificial |
Token ID | 11666 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
yles | +0.000 |
outing | +0.000 |
ries | +0.000 |
ateful | +0.000 |
outed | +0.000 |
Neg logit contributions | |
age | -0.000 |
est | -0.000 |
� | -0.000 |
ok | -0.000 |
middle | -0.000 |
Token | so |
Token ID | 523 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
age | +0.202 |
est | +0.163 |
� | +0.149 |
ok | +0.140 |
ze | +0.135 |
Neg logit contributions | |
yles | -0.189 |
outing | -0.177 |
ries | -0.168 |
eling | -0.168 |
outed | -0.168 |
Token | aps |
Token ID | 1686 |
Feature activation | -7.16e-03 |
Pos logit contributions | |
yles | +0.023 |
outing | +0.021 |
ries | +0.020 |
outed | +0.020 |
ateful | +0.020 |
Neg logit contributions | |
age | -0.017 |
est | -0.015 |
� | -0.013 |
ok | -0.012 |
best | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
age | +0.011 |
est | +0.009 |
� | +0.008 |
ok | +0.007 |
ze | +0.007 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.014 |
outed | -0.014 |
ries | -0.013 |
ateful | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
age | +0.011 |
est | +0.011 |
� | +0.011 |
ok | +0.010 |
best | +0.010 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.008 |
outed | -0.008 |
ateful | -0.007 |
eling | -0.007 |
Token | made |
Token ID | 925 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.003 |
ries | +0.003 |
ateful | +0.003 |
outed | +0.003 |
Neg logit contributions | |
age | -0.003 |
� | -0.003 |
est | -0.003 |
sy | -0.002 |
ok | -0.002 |
Token | yellow |
Token ID | 7872 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
age | +0.045 |
est | +0.038 |
ok | +0.034 |
ench | +0.033 |
� | +0.033 |
Neg logit contributions | |
yles | -0.034 |
outing | -0.031 |
ries | -0.030 |
nam | -0.030 |
outed | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
age | +0.024 |
ok | +0.018 |
est | +0.018 |
� | +0.017 |
sy | +0.016 |
Neg logit contributions | |
yles | -0.025 |
ries | -0.025 |
outing | -0.024 |
brushes | -0.024 |
outed | -0.023 |
Token | green |
Token ID | 4077 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
age | +0.029 |
est | +0.025 |
� | +0.022 |
ok | +0.021 |
ze | +0.020 |
Neg logit contributions | |
yles | -0.026 |
outing | -0.024 |
ries | -0.023 |
outed | -0.023 |
ateful | -0.022 |
Token | until |
Token ID | 1566 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
age | +0.021 |
est | +0.017 |
ok | +0.017 |
� | +0.016 |
ench | +0.015 |
Neg logit contributions | |
yles | -0.021 |
ries | -0.021 |
outing | -0.020 |
outed | -0.019 |
brushes | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
outing | +0.030 |
yles | +0.029 |
outed | +0.026 |
ateful | +0.026 |
eling | +0.026 |
Neg logit contributions | |
age | -0.033 |
� | -0.030 |
est | -0.030 |
middle | -0.027 |
ok | -0.027 |
Token | formerly |
Token ID | 15734 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
age | +0.021 |
est | +0.017 |
ok | +0.015 |
� | +0.015 |
ench | +0.015 |
Neg logit contributions | |
yles | -0.017 |
nam | -0.016 |
outing | -0.016 |
ries | -0.016 |
outed | -0.015 |
Token | color |
Token ID | 3124 |
Feature activation | +6.85e-03 |
Pos logit contributions | |
age | +0.219 |
� | +0.173 |
'' | +0.169 |
nob | +0.169 |
ench | +0.163 |
Neg logit contributions | |
brushes | -0.128 |
outing | -0.122 |
outed | -0.121 |
nam | -0.118 |
frowned | -0.113 |
Token | less |
Token ID | 1203 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
yles | +0.012 |
outing | +0.012 |
outed | +0.011 |
ries | +0.011 |
ateful | +0.011 |
Neg logit contributions | |
age | -0.012 |
est | -0.010 |
� | -0.009 |
ok | -0.009 |
ze | -0.008 |
Token | walls |
Token ID | 7714 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
yles | +0.024 |
ries | +0.022 |
outing | +0.022 |
outed | +0.021 |
ateful | +0.021 |
Neg logit contributions | |
age | -0.022 |
est | -0.018 |
� | -0.016 |
ok | -0.015 |
sy | -0.015 |
Token | seemed |
Token ID | 3947 |
Feature activation | -3.13e-04 |
Pos logit contributions | |
age | +0.014 |
est | +0.012 |
� | +0.010 |
ok | +0.009 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.018 |
ries | -0.018 |
outed | -0.017 |
ateful | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
age | +0.001 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.000 |
ries | -0.000 |
ateful | -0.000 |
Token | on |
Token ID | 319 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
yles | +0.001 |
outing | +0.001 |
ries | +0.001 |
ateful | +0.000 |
nam | +0.000 |
Neg logit contributions | |
age | -0.001 |
est | -0.001 |
� | -0.000 |
ok | -0.000 |
ze | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -7.00e-03 |
Pos logit contributions | |
age | +0.012 |
est | +0.010 |
� | +0.009 |
ok | +0.009 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.008 |
ries | -0.008 |
outed | -0.008 |
ateful | -0.008 |
Token | airplane |
Token ID | 19401 |
Feature activation | -3.58e-03 |
Pos logit contributions | |
age | +0.014 |
est | +0.011 |
� | +0.010 |
ok | +0.010 |
ench | +0.010 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.010 |
nam | -0.010 |
passports | -0.010 |
ries | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
� | +0.005 |
ok | +0.005 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.006 |
outed | -0.005 |
ries | -0.005 |
ateful | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +9.91e-03 |
Pos logit contributions | |
age | +0.003 |
est | +0.002 |
� | +0.002 |
sy | +0.002 |
entire | +0.002 |
Neg logit contributions | |
yles | -0.003 |
outing | -0.003 |
outed | -0.003 |
they | -0.003 |
ateful | -0.003 |
Token | 747 |
Token ID | 48882 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
yles | +0.017 |
outing | +0.016 |
outed | +0.015 |
ries | +0.015 |
ateful | +0.015 |
Neg logit contributions | |
age | -0.019 |
est | -0.016 |
� | -0.015 |
ok | -0.014 |
ze | -0.013 |
Token | ". |
Token ID | 1911 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
age | +0.130 |
� | +0.104 |
est | +0.099 |
ok | +0.086 |
biggest | +0.084 |
Neg logit contributions | |
outing | -0.218 |
yles | -0.218 |
ries | -0.204 |
outed | -0.203 |
eling | -0.201 |
Token | The |
Token ID | 383 |
Feature activation | -3.64e-03 |
Pos logit contributions | |
yles | +0.041 |
outing | +0.038 |
outed | +0.038 |
ries | +0.037 |
ateful | +0.036 |
Neg logit contributions | |
age | -0.033 |
est | -0.029 |
ok | -0.023 |
� | -0.023 |
ze | -0.022 |
Token | people |
Token ID | 661 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
� | +0.005 |
ok | +0.005 |
ench | +0.005 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.006 |
ateful | -0.005 |
outed | -0.005 |
ries | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.005 |
ateful | +0.005 |
ries | +0.005 |
nam | +0.005 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
� | -0.005 |
ze | -0.005 |
ok | -0.004 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
yles | +0.058 |
outing | +0.054 |
outed | +0.051 |
ries | +0.051 |
ateful | +0.051 |
Neg logit contributions | |
age | -0.054 |
est | -0.046 |
� | -0.041 |
ok | -0.038 |
ze | -0.036 |
Token | They |
Token ID | 2990 |
Feature activation | +4.30e-03 |
Pos logit contributions | |
age | +0.008 |
est | +0.008 |
ok | +0.007 |
biggest | +0.006 |
ze | +0.006 |
Neg logit contributions | |
outing | -0.005 |
yles | -0.005 |
ila | -0.005 |
outed | -0.005 |
ateful | -0.005 |
Token | chase |
Token ID | 15505 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
yles | +0.008 |
outing | +0.007 |
ries | +0.007 |
outed | +0.007 |
ateful | +0.007 |
Neg logit contributions | |
age | -0.008 |
est | -0.007 |
� | -0.006 |
ok | -0.006 |
ze | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
yles | +0.013 |
outing | +0.012 |
ries | +0.011 |
outed | +0.011 |
ateful | +0.011 |
Neg logit contributions | |
age | -0.022 |
est | -0.019 |
� | -0.018 |
ok | -0.017 |
ze | -0.016 |
Token | car |
Token ID | 1097 |
Feature activation | -6.74e-03 |
Pos logit contributions | |
age | +0.018 |
est | +0.015 |
� | +0.014 |
ok | +0.013 |
ench | +0.012 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.017 |
ateful | -0.016 |
ries | -0.016 |
outed | -0.016 |
Token | - |
Token ID | 12 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
age | +0.009 |
est | +0.008 |
� | +0.006 |
ok | +0.006 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.014 |
ries | -0.014 |
outed | -0.014 |
ateful | -0.013 |
Token | nos |
Token ID | 39369 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
yles | +0.039 |
outing | +0.035 |
ries | +0.034 |
outed | +0.033 |
ateful | +0.033 |
Neg logit contributions | |
age | -0.044 |
est | -0.037 |
� | -0.034 |
ze | -0.031 |
ok | -0.030 |
Token | aur |
Token ID | 2899 |
Feature activation | +9.16e-03 |
Pos logit contributions | |
age | +0.207 |
est | +0.182 |
� | +0.160 |
ok | +0.152 |
ze | +0.146 |
Neg logit contributions | |
yles | -0.177 |
outing | -0.161 |
ries | -0.152 |
outed | -0.151 |
ateful | -0.150 |
Token | around |
Token ID | 1088 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
yles | +0.016 |
outing | +0.015 |
nam | +0.014 |
outed | +0.014 |
ateful | +0.014 |
Neg logit contributions | |
age | -0.017 |
est | -0.015 |
� | -0.013 |
ze | -0.012 |
ok | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -8.39e-03 |
Pos logit contributions | |
yles | +0.030 |
outing | +0.028 |
outed | +0.027 |
nam | +0.026 |
ries | +0.025 |
Neg logit contributions | |
age | -0.031 |
est | -0.028 |
� | -0.026 |
ok | -0.024 |
ze | -0.024 |
Token | room |
Token ID | 2119 |
Feature activation | -6.15e-03 |
Pos logit contributions | |
age | +0.017 |
est | +0.015 |
ok | +0.015 |
ench | +0.013 |
� | +0.013 |
Neg logit contributions | |
yles | -0.012 |
nam | -0.011 |
passports | -0.011 |
spill | -0.011 |
brushes | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-03 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.006 |
ok | +0.005 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.014 |
outing | -0.013 |
ries | -0.013 |
nam | -0.013 |
outed | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +9.22e-03 |
Pos logit contributions | |
yles | +0.048 |
outing | +0.048 |
outed | +0.044 |
ries | +0.042 |
ateful | +0.041 |
Neg logit contributions | |
age | -0.054 |
est | -0.045 |
� | -0.038 |
ench | -0.037 |
ok | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
yles | +0.017 |
outing | +0.016 |
outed | +0.015 |
ries | +0.015 |
ateful | +0.015 |
Neg logit contributions | |
age | -0.016 |
est | -0.014 |
� | -0.012 |
ok | -0.011 |
ze | -0.011 |
Token | A |
Token ID | 32 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
yles | +0.017 |
outing | +0.015 |
ateful | +0.014 |
outed | +0.014 |
nam | +0.014 |
Neg logit contributions | |
age | -0.017 |
est | -0.015 |
� | -0.013 |
ok | -0.013 |
ench | -0.012 |
Token | car |
Token ID | 1097 |
Feature activation | -7.58e-03 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.006 |
ateful | +0.005 |
passports | +0.005 |
ila | +0.005 |
Neg logit contributions | |
age | -0.008 |
est | -0.007 |
ok | -0.006 |
ench | -0.006 |
� | -0.006 |
Token | - |
Token ID | 12 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
age | +0.013 |
est | +0.011 |
� | +0.009 |
ok | +0.009 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.014 |
outing | -0.013 |
ries | -0.012 |
outed | -0.012 |
ateful | -0.012 |
Token | nos |
Token ID | 39369 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
yles | +0.038 |
outing | +0.035 |
ries | +0.033 |
outed | +0.033 |
ateful | +0.033 |
Neg logit contributions | |
age | -0.043 |
est | -0.037 |
� | -0.034 |
ok | -0.030 |
ze | -0.030 |
Token | aur |
Token ID | 2899 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
age | +0.208 |
� | +0.171 |
est | +0.169 |
ok | +0.163 |
ze | +0.156 |
Neg logit contributions | |
yles | -0.158 |
outing | -0.153 |
outed | -0.145 |
ateful | -0.145 |
ila | -0.137 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
yles | +0.018 |
outing | +0.017 |
outed | +0.016 |
ries | +0.016 |
ateful | +0.016 |
Neg logit contributions | |
age | -0.012 |
est | -0.010 |
� | -0.008 |
ok | -0.008 |
ze | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.28e-03 |
Pos logit contributions | |
yles | +0.030 |
outing | +0.028 |
ries | +0.026 |
outed | +0.026 |
ateful | +0.026 |
Neg logit contributions | |
age | -0.021 |
est | -0.017 |
� | -0.015 |
ok | -0.014 |
ze | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
age | +0.004 |
est | +0.003 |
� | +0.003 |
ok | +0.003 |
ze | +0.002 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.004 |
outed | -0.004 |
ries | -0.004 |
ateful | -0.004 |
Token | They |
Token ID | 2990 |
Feature activation | +4.30e-03 |
Pos logit contributions | |
age | +0.008 |
est | +0.008 |
ok | +0.007 |
biggest | +0.006 |
ze | +0.006 |
Neg logit contributions | |
outing | -0.005 |
yles | -0.005 |
ila | -0.005 |
outed | -0.005 |
ateful | -0.005 |
Token | making |
Token ID | 1642 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
yles | +0.034 |
outing | +0.032 |
outed | +0.030 |
ries | +0.030 |
ateful | +0.030 |
Neg logit contributions | |
age | -0.033 |
est | -0.029 |
� | -0.025 |
ok | -0.023 |
ze | -0.023 |
Token | breakfast |
Token ID | 12607 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
age | +0.071 |
est | +0.062 |
� | +0.056 |
ok | +0.052 |
ze | +0.050 |
Neg logit contributions | |
yles | -0.074 |
outing | -0.069 |
outed | -0.065 |
ateful | -0.064 |
ries | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | -3.37e-04 |
Pos logit contributions | |
age | +0.103 |
est | +0.086 |
� | +0.074 |
ok | +0.070 |
ze | +0.065 |
Neg logit contributions | |
yles | -0.134 |
outing | -0.127 |
ries | -0.121 |
outed | -0.119 |
ateful | -0.118 |
Token | They |
Token ID | 1119 |
Feature activation | -7.35e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
� | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.000 |
ries | -0.000 |
ateful | -0.000 |
Token | smelled |
Token ID | 37609 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
age | +0.013 |
� | +0.011 |
est | +0.011 |
sy | +0.010 |
ok | +0.010 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.012 |
ries | -0.012 |
ateful | -0.011 |
outed | -0.011 |
Token | pancakes |
Token ID | 47008 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
age | +0.039 |
est | +0.032 |
� | +0.029 |
ok | +0.027 |
ze | +0.027 |
Neg logit contributions | |
yles | -0.032 |
outing | -0.029 |
ries | -0.028 |
outed | -0.028 |
ateful | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
age | +0.145 |
est | +0.118 |
� | +0.099 |
ok | +0.092 |
ze | +0.086 |
Neg logit contributions | |
yles | -0.234 |
outing | -0.220 |
ries | -0.211 |
outed | -0.210 |
ateful | -0.208 |
Token | syrup |
Token ID | 24208 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.007 |
ok | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.008 |
outing | -0.007 |
ateful | -0.007 |
outed | -0.007 |
ries | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.75e-04 |
Pos logit contributions | |
age | +0.059 |
est | +0.048 |
� | +0.039 |
ok | +0.034 |
ze | +0.034 |
Neg logit contributions | |
yles | -0.113 |
outing | -0.105 |
ateful | -0.102 |
nam | -0.102 |
outed | -0.101 |
Token | They |
Token ID | 1119 |
Feature activation | -7.05e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
� | +0.001 |
ze | +0.001 |
ok | +0.001 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.001 |
ateful | -0.001 |
ries | -0.001 |
Token | were |
Token ID | 547 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
age | +0.012 |
� | +0.011 |
est | +0.011 |
ok | +0.009 |
even | +0.009 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.012 |
ries | -0.011 |
ateful | -0.011 |
irs | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +2.98e-03 |
Pos logit contributions | |
yles | +0.030 |
outing | +0.028 |
outed | +0.025 |
ateful | +0.025 |
eling | +0.025 |
Neg logit contributions | |
age | -0.042 |
est | -0.037 |
� | -0.035 |
ok | -0.033 |
ze | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
yles | +0.005 |
outing | +0.004 |
outed | +0.004 |
ries | +0.004 |
ateful | +0.004 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
� | -0.005 |
ok | -0.004 |
ze | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.48e-03 |
Pos logit contributions | |
yles | +0.047 |
outed | +0.044 |
outing | +0.044 |
ries | +0.041 |
ateful | +0.040 |
Neg logit contributions | |
age | -0.072 |
est | -0.062 |
� | -0.056 |
nob | -0.052 |
ench | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +6.50e-03 |
Pos logit contributions | |
age | +0.004 |
est | +0.003 |
� | +0.003 |
ok | +0.003 |
biggest | +0.003 |
Neg logit contributions | |
yles | -0.005 |
outing | -0.005 |
outed | -0.004 |
ries | -0.004 |
nam | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
yles | +0.012 |
outing | +0.012 |
outed | +0.011 |
ries | +0.011 |
ateful | +0.011 |
Neg logit contributions | |
age | -0.011 |
est | -0.010 |
� | -0.008 |
ok | -0.008 |
ze | -0.007 |
Token | Flags |
Token ID | 40053 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
yles | +0.018 |
outing | +0.017 |
outed | +0.016 |
ries | +0.016 |
ateful | +0.016 |
Neg logit contributions | |
age | -0.020 |
est | -0.018 |
� | -0.016 |
ok | -0.015 |
ze | -0.014 |
Token | go |
Token ID | 467 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
age | +0.216 |
est | +0.189 |
� | +0.163 |
ok | +0.163 |
ze | +0.156 |
Neg logit contributions | |
yles | -0.155 |
outing | -0.140 |
ateful | -0.131 |
ries | -0.131 |
eling | -0.130 |
Token | up |
Token ID | 510 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
yles | +0.009 |
outing | +0.008 |
ries | +0.008 |
outed | +0.008 |
nam | +0.008 |
Neg logit contributions | |
age | -0.009 |
est | -0.007 |
� | -0.006 |
ok | -0.006 |
ze | -0.006 |
Token | there |
Token ID | 612 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
yles | +0.017 |
outing | +0.016 |
ateful | +0.015 |
nam | +0.015 |
ries | +0.015 |
Neg logit contributions | |
age | -0.024 |
est | -0.021 |
ze | -0.017 |
� | -0.017 |
ench | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
age | +0.018 |
est | +0.015 |
� | +0.013 |
ze | +0.012 |
ok | +0.012 |
Neg logit contributions | |
yles | -0.022 |
outing | -0.020 |
ries | -0.019 |
ateful | -0.019 |
outed | -0.019 |
Token | wave |
Token ID | 6769 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
yles | +0.048 |
outing | +0.045 |
outed | +0.044 |
ries | +0.042 |
ateful | +0.041 |
Neg logit contributions | |
age | -0.037 |
est | -0.031 |
� | -0.028 |
ok | -0.026 |
ze | -0.025 |
Token | didn |
Token ID | 1422 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
age | +0.027 |
est | +0.023 |
� | +0.023 |
ok | +0.020 |
ze | +0.020 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.019 |
ries | -0.018 |
ateful | -0.017 |
outed | -0.017 |
Token | 't |
Token ID | 470 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
age | +0.055 |
est | +0.051 |
ok | +0.041 |
ench | +0.038 |
biggest | +0.038 |
Neg logit contributions | |
yles | -0.049 |
outing | -0.044 |
ries | -0.042 |
ateful | -0.041 |
outed | -0.041 |
Token | know |
Token ID | 760 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
age | +0.019 |
est | +0.017 |
� | +0.015 |
ok | +0.014 |
ze | +0.013 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.017 |
outed | -0.016 |
ries | -0.016 |
ateful | -0.015 |
Token | what |
Token ID | 644 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
yles | +0.052 |
outing | +0.051 |
outed | +0.050 |
ateful | +0.047 |
eling | +0.044 |
Neg logit contributions | |
age | -0.062 |
est | -0.059 |
� | -0.055 |
ok | -0.053 |
best | -0.051 |
Token | " |
Token ID | 366 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
yles | +0.027 |
outing | +0.025 |
outed | +0.023 |
ries | +0.023 |
ateful | +0.023 |
Neg logit contributions | |
age | -0.027 |
est | -0.024 |
� | -0.021 |
ok | -0.020 |
ze | -0.019 |
Token | nos |
Token ID | 39369 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
yles | +0.014 |
outing | +0.013 |
outed | +0.012 |
ries | +0.012 |
ateful | +0.012 |
Neg logit contributions | |
age | -0.016 |
est | -0.014 |
� | -0.012 |
ok | -0.011 |
ze | -0.011 |
Token | y |
Token ID | 88 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
age | +0.253 |
est | +0.224 |
� | +0.214 |
ok | +0.206 |
ze | +0.203 |
Neg logit contributions | |
yles | -0.111 |
outing | -0.107 |
ateful | -0.096 |
outed | -0.095 |
ries | -0.091 |
Token | " |
Token ID | 1 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
age | +0.009 |
est | +0.007 |
ok | +0.006 |
� | +0.006 |
biggest | +0.006 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.017 |
ries | -0.017 |
ateful | -0.017 |
arose | -0.016 |
Token | meant |
Token ID | 4001 |
Feature activation | -5.24e-03 |
Pos logit contributions | |
yles | +0.041 |
outing | +0.038 |
outed | +0.036 |
ries | +0.036 |
ateful | +0.035 |
Neg logit contributions | |
age | -0.048 |
est | -0.042 |
� | -0.038 |
ok | -0.036 |
ze | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +4.45e-03 |
Pos logit contributions | |
age | +0.008 |
est | +0.006 |
ench | +0.005 |
� | +0.005 |
biggest | +0.005 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.010 |
ries | -0.010 |
nam | -0.010 |
ateful | -0.009 |
Token | so |
Token ID | 523 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
yles | +0.010 |
outing | +0.009 |
ries | +0.009 |
ateful | +0.009 |
outed | +0.009 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
� | -0.004 |
ok | -0.004 |
ze | -0.004 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
yles | +0.050 |
ries | +0.048 |
outing | +0.047 |
ila | +0.044 |
outed | +0.044 |
Neg logit contributions | |
age | -0.042 |
est | -0.036 |
� | -0.032 |
ok | -0.031 |
biggest | -0.030 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
yles | +0.062 |
outing | +0.060 |
ries | +0.056 |
eling | +0.055 |
ge | +0.054 |
Neg logit contributions | |
age | -0.058 |
� | -0.057 |
est | -0.052 |
middle | -0.048 |
ok | -0.048 |
Token | yells |
Token ID | 42675 |
Feature activation | +4.34e-03 |
Pos logit contributions | |
yles | +0.015 |
nam | +0.013 |
outing | +0.012 |
ateful | +0.012 |
outed | +0.011 |
Neg logit contributions | |
age | -0.027 |
� | -0.025 |
est | -0.025 |
right | -0.022 |
ok | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +8.89e-03 |
Pos logit contributions | |
yles | +0.008 |
outing | +0.007 |
ries | +0.007 |
outed | +0.007 |
ateful | +0.007 |
Neg logit contributions | |
age | -0.008 |
est | -0.007 |
ok | -0.006 |
� | -0.005 |
sy | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
yles | +0.020 |
outing | +0.019 |
eling | +0.018 |
ries | +0.018 |
ateful | +0.018 |
Neg logit contributions | |
age | -0.012 |
est | -0.010 |
� | -0.009 |
ok | -0.008 |
ze | -0.007 |
Token | YOU |
Token ID | 36981 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
yles | +0.024 |
outed | +0.024 |
ries | +0.023 |
outing | +0.023 |
ours | +0.022 |
Neg logit contributions | |
age | -0.017 |
� | -0.015 |
ze | -0.013 |
entire | -0.012 |
est | -0.012 |
Token | ARE |
Token ID | 15986 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
age | +0.183 |
est | +0.160 |
� | +0.137 |
ok | +0.134 |
ze | +0.125 |
Neg logit contributions | |
yles | -0.186 |
outing | -0.175 |
ries | -0.165 |
outed | -0.165 |
eling | -0.164 |
Token | MA |
Token ID | 8779 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
yles | +0.039 |
outing | +0.037 |
ries | +0.036 |
ateful | +0.035 |
eling | +0.034 |
Neg logit contributions | |
age | -0.054 |
est | -0.047 |
sy | -0.038 |
ok | -0.038 |
nob | -0.037 |
Token | KING |
Token ID | 37286 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
age | +0.127 |
est | +0.116 |
� | +0.101 |
ok | +0.098 |
best | +0.092 |
Neg logit contributions | |
yles | -0.114 |
outing | -0.113 |
ateful | -0.106 |
outed | -0.105 |
ries | -0.103 |
Token | A |
Token ID | 317 |
Feature activation | +4.88e-03 |
Pos logit contributions | |
yles | +0.017 |
ries | +0.015 |
outing | +0.015 |
arose | +0.015 |
ila | +0.015 |
Neg logit contributions | |
age | -0.017 |
est | -0.016 |
ok | -0.014 |
best | -0.014 |
sy | -0.014 |
Token | M |
Token ID | 337 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
yles | +0.009 |
outing | +0.008 |
ries | +0.008 |
outed | +0.008 |
ateful | +0.007 |
Neg logit contributions | |
age | -0.009 |
est | -0.008 |
� | -0.007 |
ok | -0.006 |
ze | -0.006 |
Token | she |
Token ID | 673 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
age | +0.007 |
� | +0.006 |
ok | +0.006 |
est | +0.006 |
best | +0.006 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.004 |
outed | -0.004 |
ateful | -0.004 |
eling | -0.004 |
Token | could |
Token ID | 714 |
Feature activation | +8.04e-03 |
Pos logit contributions | |
age | +0.011 |
est | +0.010 |
� | +0.009 |
ok | +0.009 |
ze | +0.008 |
Neg logit contributions | |
yles | -0.008 |
outing | -0.007 |
ries | -0.007 |
outed | -0.007 |
ateful | -0.007 |
Token | help |
Token ID | 1037 |
Feature activation | +3.59e-03 |
Pos logit contributions | |
yles | +0.011 |
spill | +0.010 |
outing | +0.010 |
brushes | +0.009 |
ries | +0.009 |
Neg logit contributions | |
age | -0.016 |
est | -0.015 |
biggest | -0.012 |
> | -0.012 |
ok | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
yles | +0.005 |
ries | +0.005 |
outing | +0.005 |
nam | +0.005 |
eling | +0.005 |
Neg logit contributions | |
age | -0.008 |
est | -0.007 |
� | -0.006 |
ok | -0.006 |
sy | -0.005 |
Token | tea |
Token ID | 8887 |
Feature activation | -5.79e-02 |
Pos logit contributions | |
age | +0.023 |
est | +0.020 |
� | +0.017 |
ok | +0.017 |
sy | +0.016 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.017 |
ries | -0.017 |
ateful | -0.017 |
nam | -0.017 |
Token | del |
Token ID | 1619 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
age | +0.094 |
est | +0.079 |
� | +0.067 |
ok | +0.065 |
ze | +0.062 |
Neg logit contributions | |
yles | -0.108 |
outing | -0.103 |
ries | -0.101 |
outed | -0.097 |
ateful | -0.095 |
Token | ive |
Token ID | 425 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
age | +0.164 |
est | +0.136 |
� | +0.122 |
ok | +0.113 |
biggest | +0.109 |
Neg logit contributions | |
yles | -0.206 |
outing | -0.196 |
ries | -0.187 |
outed | -0.186 |
ateful | -0.181 |
Token | rer |
Token ID | 11751 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
age | +0.010 |
est | +0.008 |
� | +0.007 |
ok | +0.007 |
ze | +0.007 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.011 |
ries | -0.010 |
outed | -0.010 |
ateful | -0.010 |
Token | by |
Token ID | 416 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
age | +0.091 |
est | +0.077 |
ok | +0.060 |
ench | +0.059 |
� | +0.059 |
Neg logit contributions | |
yles | -0.097 |
outing | -0.092 |
ries | -0.091 |
outed | -0.085 |
ateful | -0.084 |
Token | taking |
Token ID | 2263 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
age | +0.010 |
est | +0.009 |
� | +0.008 |
ok | +0.008 |
ze | +0.008 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.009 |
outed | -0.008 |
ateful | -0.008 |
ries | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
age | +0.034 |
est | +0.030 |
� | +0.025 |
ok | +0.025 |
ench | +0.024 |
Neg logit contributions | |
yles | -0.023 |
ries | -0.021 |
outing | -0.020 |
eling | -0.020 |
ateful | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | -1.88e-03 |
Pos logit contributions | |
yles | +0.020 |
outing | +0.018 |
ries | +0.018 |
outed | +0.018 |
ateful | +0.017 |
Neg logit contributions | |
age | -0.012 |
est | -0.010 |
� | -0.008 |
ok | -0.008 |
ze | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
age | +0.003 |
est | +0.002 |
� | +0.002 |
best | +0.002 |
ok | +0.002 |
Neg logit contributions | |
outing | -0.004 |
yles | -0.004 |
outed | -0.003 |
ateful | -0.003 |
ries | -0.003 |
Token | car |
Token ID | 1097 |
Feature activation | +7.17e-04 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.006 |
ateful | +0.005 |
outed | +0.005 |
ries | +0.005 |
Neg logit contributions | |
age | -0.007 |
est | -0.006 |
� | -0.005 |
ok | -0.005 |
ze | -0.005 |
Token | trips |
Token ID | 13229 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.001 |
outed | +0.001 |
ries | +0.001 |
ateful | +0.001 |
Neg logit contributions | |
age | -0.001 |
est | -0.001 |
� | -0.001 |
ok | -0.001 |
ze | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
yles | +0.045 |
outing | +0.042 |
outed | +0.040 |
ries | +0.039 |
nam | +0.039 |
Neg logit contributions | |
age | -0.039 |
est | -0.034 |
� | -0.029 |
ok | -0.028 |
ze | -0.027 |
Token | many |
Token ID | 867 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
yles | +0.050 |
outing | +0.049 |
outed | +0.047 |
ries | +0.046 |
ateful | +0.044 |
Neg logit contributions | |
age | -0.038 |
est | -0.033 |
� | -0.028 |
ok | -0.026 |
biggest | -0.026 |
Token | different |
Token ID | 1180 |
Feature activation | +2.46e-03 |
Pos logit contributions | |
yles | +0.145 |
outing | +0.140 |
outed | +0.132 |
ries | +0.128 |
ateful | +0.125 |
Neg logit contributions | |
age | -0.121 |
est | -0.113 |
� | -0.096 |
best | -0.088 |
ok | -0.086 |
Token | places |
Token ID | 4113 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
yles | +0.004 |
outing | +0.004 |
outed | +0.004 |
ries | +0.004 |
ateful | +0.004 |
Neg logit contributions | |
age | -0.004 |
est | -0.004 |
� | -0.003 |
ok | -0.003 |
best | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.19e-03 |
Pos logit contributions | |
yles | +0.038 |
outing | +0.035 |
ries | +0.034 |
outed | +0.033 |
ateful | +0.033 |
Neg logit contributions | |
age | -0.027 |
est | -0.023 |
� | -0.020 |
ok | -0.018 |
ze | -0.017 |
Token | One |
Token ID | 1881 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
yles | +0.007 |
outing | +0.006 |
outed | +0.006 |
ries | +0.006 |
ateful | +0.006 |
Neg logit contributions | |
age | -0.005 |
est | -0.004 |
� | -0.003 |
ok | -0.003 |
ze | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
age | +0.026 |
est | +0.021 |
� | +0.017 |
ok | +0.015 |
ze | +0.014 |
Neg logit contributions | |
yles | -0.052 |
outing | -0.049 |
ries | -0.047 |
outed | -0.046 |
ateful | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
yles | +0.015 |
ries | +0.013 |
outing | +0.013 |
eling | +0.012 |
outed | +0.012 |
Neg logit contributions | |
age | -0.023 |
est | -0.019 |
ok | -0.017 |
ench | -0.017 |
� | -0.016 |
Token | handles |
Token ID | 17105 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
age | +0.033 |
est | +0.029 |
ok | +0.026 |
� | +0.026 |
nob | +0.025 |
Neg logit contributions | |
yles | -0.022 |
brushes | -0.022 |
outing | -0.021 |
nam | -0.021 |
outed | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.44e-03 |
Pos logit contributions | |
age | +0.019 |
est | +0.015 |
ok | +0.013 |
� | +0.012 |
ze | +0.012 |
Neg logit contributions | |
yles | -0.024 |
outing | -0.024 |
ries | -0.022 |
outed | -0.022 |
nam | -0.022 |
Token | g |
Token ID | 308 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
outed | +0.002 |
ateful | +0.002 |
ries | +0.002 |
Neg logit contributions | |
age | -0.003 |
est | -0.002 |
� | -0.002 |
ok | -0.002 |
ze | -0.002 |
Token | iggle |
Token ID | 24082 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
yles | +0.017 |
nam | +0.016 |
outing | +0.016 |
ateful | +0.015 |
ries | +0.015 |
Neg logit contributions | |
age | -0.015 |
est | -0.013 |
ok | -0.010 |
� | -0.010 |
ze | -0.010 |
Token | as |
Token ID | 355 |
Feature activation | +6.59e-02 |
Pos logit contributions | |
age | +0.019 |
est | +0.015 |
� | +0.013 |
ok | +0.013 |
ench | +0.013 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.016 |
ries | -0.015 |
nam | -0.015 |
outed | -0.015 |
Token | she |
Token ID | 673 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
yles | +0.069 |
outing | +0.060 |
outed | +0.054 |
ries | +0.054 |
ateful | +0.053 |
Neg logit contributions | |
age | -0.168 |
est | -0.152 |
� | -0.141 |
ok | -0.136 |
ze | -0.132 |
Token | went |
Token ID | 1816 |
Feature activation | -7.08e-04 |
Pos logit contributions | |
age | +0.026 |
est | +0.023 |
� | +0.022 |
ze | +0.020 |
ok | +0.019 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.016 |
ateful | -0.015 |
ries | -0.015 |
nam | -0.015 |
Token | up |
Token ID | 510 |
Feature activation | +3.10e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
ok | +0.001 |
� | +0.001 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.001 |
ries | -0.001 |
outing | -0.001 |
brushes | -0.001 |
spill | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.005 |
ries | +0.005 |
outed | +0.005 |
nam | +0.005 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
ok | -0.004 |
� | -0.004 |
ze | -0.004 |
Token | up |
Token ID | 510 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
age | +0.005 |
est | +0.004 |
� | +0.003 |
ok | +0.003 |
ench | +0.003 |
Neg logit contributions | |
yles | -0.005 |
outing | -0.004 |
nam | -0.004 |
eling | -0.004 |
outed | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.90e-03 |
Pos logit contributions | |
yles | +0.004 |
ries | +0.003 |
outing | +0.003 |
nam | +0.003 |
brushes | +0.003 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
ench | -0.004 |
ze | -0.004 |
ok | -0.004 |
Token | tug |
Token ID | 27762 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
age | +0.007 |
� | +0.007 |
est | +0.006 |
ok | +0.006 |
right | +0.006 |
Neg logit contributions | |
outing | -0.006 |
yles | -0.006 |
ateful | -0.006 |
outed | -0.006 |
ries | -0.006 |
Token | ged |
Token ID | 2004 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
yles | +0.067 |
outing | +0.061 |
ries | +0.057 |
outed | +0.057 |
ateful | +0.056 |
Neg logit contributions | |
age | -0.098 |
est | -0.086 |
� | -0.078 |
ok | -0.075 |
ze | -0.072 |
Token | as |
Token ID | 355 |
Feature activation | +6.93e-02 |
Pos logit contributions | |
yles | +0.106 |
outing | +0.099 |
ries | +0.097 |
nam | +0.092 |
eling | +0.091 |
Neg logit contributions | |
age | -0.095 |
est | -0.075 |
ench | -0.061 |
ze | -0.060 |
entire | -0.059 |
Token | hard |
Token ID | 1327 |
Feature activation | +1.23e-03 |
Pos logit contributions | |
yles | +0.133 |
outing | +0.122 |
outed | +0.117 |
ries | +0.117 |
eling | +0.116 |
Neg logit contributions | |
age | -0.112 |
est | -0.098 |
� | -0.097 |
ok | -0.084 |
best | -0.083 |
Token | as |
Token ID | 355 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
outed | +0.002 |
ateful | +0.002 |
ries | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.002 |
� | -0.002 |
ok | -0.001 |
ze | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
yles | +0.077 |
outing | +0.069 |
outed | +0.063 |
ries | +0.061 |
ateful | +0.060 |
Neg logit contributions | |
age | -0.170 |
est | -0.155 |
� | -0.147 |
ok | -0.140 |
best | -0.134 |
Token | could |
Token ID | 714 |
Feature activation | +7.74e-03 |
Pos logit contributions | |
age | +0.025 |
est | +0.022 |
� | +0.021 |
ok | +0.019 |
best | +0.018 |
Neg logit contributions | |
yles | -0.025 |
outing | -0.023 |
ries | -0.023 |
ateful | -0.022 |
eling | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
yles | +0.016 |
outing | +0.015 |
outed | +0.014 |
ries | +0.014 |
ateful | +0.014 |
Neg logit contributions | |
age | -0.011 |
est | -0.010 |
� | -0.008 |
ok | -0.007 |
ze | -0.007 |
Token | but |
Token ID | 475 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.001 |
ok | +0.001 |
ench | +0.001 |
Neg logit contributions | |
yles | -0.002 |
outing | -0.002 |
eling | -0.002 |
nam | -0.002 |
ries | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
age | +0.062 |
est | +0.054 |
� | +0.052 |
ok | +0.049 |
ze | +0.046 |
Neg logit contributions | |
yles | -0.048 |
outing | -0.044 |
ateful | -0.041 |
ries | -0.041 |
outed | -0.041 |
Token | |
Token ID | 220 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
age | +0.035 |
est | +0.034 |
ok | +0.025 |
biggest | +0.025 |
� | +0.024 |
Neg logit contributions | |
yles | -0.044 |
outing | -0.041 |
outed | -0.040 |
ries | -0.038 |
eling | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
yles | +0.059 |
outing | +0.056 |
outed | +0.054 |
ries | +0.051 |
ateful | +0.050 |
Neg logit contributions | |
age | -0.049 |
est | -0.044 |
ze | -0.035 |
ok | -0.034 |
� | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
age | +0.023 |
est | +0.022 |
ze | +0.017 |
ok | +0.016 |
biggest | +0.016 |
Neg logit contributions | |
yles | -0.026 |
outing | -0.024 |
outed | -0.023 |
ila | -0.022 |
ateful | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
age | +0.027 |
est | +0.025 |
biggest | +0.020 |
ok | +0.020 |
best | +0.020 |
Neg logit contributions | |
yles | -0.023 |
outing | -0.021 |
ateful | -0.019 |
outed | -0.019 |
eling | -0.019 |
Token | b |
Token ID | 275 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
age | +0.021 |
est | +0.018 |
ench | +0.015 |
� | +0.015 |
nob | +0.014 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.018 |
nam | -0.017 |
outed | -0.017 |
ateful | -0.017 |
Token | unn |
Token ID | 20935 |
Feature activation | +7.20e-02 |
Pos logit contributions | |
age | +0.041 |
est | +0.036 |
� | +0.032 |
ok | +0.031 |
ze | +0.030 |
Neg logit contributions | |
yles | -0.027 |
outing | -0.025 |
ries | -0.023 |
outed | -0.023 |
ateful | -0.023 |
Token | ies |
Token ID | 444 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
yles | +0.058 |
outing | +0.049 |
ries | +0.042 |
outed | +0.042 |
ateful | +0.041 |
Neg logit contributions | |
age | -0.201 |
est | -0.182 |
� | -0.170 |
ok | -0.165 |
ze | -0.161 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.29e-04 |
Pos logit contributions | |
age | +0.024 |
est | +0.021 |
� | +0.019 |
ok | +0.018 |
ze | +0.018 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.015 |
ries | -0.014 |
ateful | -0.014 |
outed | -0.014 |
Token | at |
Token ID | 379 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
nob | +0.001 |
� | +0.001 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.001 |
outed | -0.001 |
outing | -0.001 |
nam | -0.001 |
ries | -0.001 |
Token | each |
Token ID | 1123 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
yles | +0.034 |
outing | +0.034 |
outed | +0.030 |
ateful | +0.029 |
eling | +0.028 |
Neg logit contributions | |
age | -0.033 |
est | -0.032 |
� | -0.029 |
ok | -0.027 |
best | -0.026 |
Token | other |
Token ID | 584 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
age | +0.015 |
est | +0.013 |
� | +0.012 |
ok | +0.011 |
ze | +0.011 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.014 |
ries | -0.014 |
outed | -0.014 |
ateful | -0.014 |
Token | were |
Token ID | 547 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
age | +0.001 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
best | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.000 |
ateful | -0.000 |
ries | -0.000 |
Token | burying |
Token ID | 48360 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
yles | +0.047 |
outing | +0.044 |
ries | +0.041 |
outed | +0.041 |
ateful | +0.041 |
Neg logit contributions | |
age | -0.051 |
est | -0.044 |
� | -0.038 |
ok | -0.036 |
ze | -0.035 |
Token | something |
Token ID | 1223 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
yles | +0.024 |
outing | +0.022 |
ries | +0.022 |
ateful | +0.021 |
outed | +0.021 |
Neg logit contributions | |
age | -0.030 |
est | -0.025 |
� | -0.022 |
ok | -0.020 |
ze | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | +3.74e-03 |
Pos logit contributions | |
yles | +0.058 |
outing | +0.056 |
ries | +0.053 |
outed | +0.052 |
eling | +0.051 |
Neg logit contributions | |
age | -0.067 |
est | -0.055 |
� | -0.045 |
ze | -0.045 |
ok | -0.044 |
Token | long |
Token ID | 890 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.006 |
outed | +0.006 |
ateful | +0.005 |
ries | +0.005 |
Neg logit contributions | |
age | -0.007 |
est | -0.006 |
� | -0.005 |
ok | -0.005 |
ze | -0.005 |
Token | ago |
Token ID | 2084 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.002 |
ok | +0.002 |
ze | +0.002 |
Neg logit contributions | |
yles | -0.003 |
outing | -0.003 |
ries | -0.002 |
outed | -0.002 |
ateful | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
yles | +0.169 |
outing | +0.159 |
ries | +0.156 |
outed | +0.153 |
ateful | +0.150 |
Neg logit contributions | |
age | -0.138 |
est | -0.115 |
� | -0.100 |
ok | -0.094 |
ze | -0.089 |
Token | made |
Token ID | 925 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
yles | +0.019 |
outing | +0.017 |
ries | +0.016 |
outed | +0.016 |
ateful | +0.016 |
Neg logit contributions | |
age | -0.025 |
est | -0.022 |
� | -0.019 |
ok | -0.018 |
ze | -0.018 |
Token | them |
Token ID | 606 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
age | +0.071 |
est | +0.064 |
� | +0.059 |
ok | +0.057 |
ze | +0.054 |
Neg logit contributions | |
yles | -0.051 |
outing | -0.047 |
outed | -0.044 |
ateful | -0.043 |
ries | -0.043 |
Token | feel |
Token ID | 1254 |
Feature activation | -2.12e-03 |
Pos logit contributions | |
age | +0.030 |
est | +0.026 |
� | +0.021 |
ok | +0.020 |
ze | +0.020 |
Neg logit contributions | |
yles | -0.031 |
outing | -0.029 |
nam | -0.028 |
ateful | -0.028 |
outed | -0.028 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
age | +0.004 |
est | +0.003 |
nob | +0.003 |
> | +0.002 |
ze | +0.002 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.003 |
eling | -0.003 |
ateful | -0.003 |
outed | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.007 |
ok | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.005 |
outed | -0.005 |
ries | -0.005 |
ateful | -0.005 |
Token | king |
Token ID | 5822 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
age | +0.024 |
est | +0.019 |
� | +0.018 |
ok | +0.017 |
ze | +0.016 |
Neg logit contributions | |
yles | -0.021 |
ateful | -0.020 |
outing | -0.020 |
nam | -0.020 |
eling | -0.019 |
Token | knew |
Token ID | 2993 |
Feature activation | +3.42e-03 |
Pos logit contributions | |
age | +0.015 |
est | +0.013 |
� | +0.011 |
ok | +0.011 |
ze | +0.010 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.015 |
outed | -0.014 |
ries | -0.014 |
ateful | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.006 |
outed | +0.005 |
ries | +0.005 |
ateful | +0.005 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
� | -0.005 |
ok | -0.005 |
best | -0.004 |
Token | he |
Token ID | 339 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
yles | +0.020 |
outing | +0.018 |
ries | +0.017 |
ateful | +0.017 |
outed | +0.017 |
Neg logit contributions | |
age | -0.024 |
est | -0.021 |
� | -0.019 |
ok | -0.018 |
ze | -0.017 |
Token | could |
Token ID | 714 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
yles | +0.022 |
outing | +0.020 |
outed | +0.019 |
ries | +0.019 |
ateful | +0.019 |
Neg logit contributions | |
age | -0.027 |
est | -0.023 |
� | -0.021 |
ok | -0.020 |
ze | -0.019 |
Token | always |
Token ID | 1464 |
Feature activation | -3.88e-03 |
Pos logit contributions | |
yles | +0.019 |
eling | +0.017 |
outing | +0.017 |
spill | +0.017 |
ateful | +0.017 |
Neg logit contributions | |
age | -0.023 |
est | -0.022 |
ok | -0.017 |
> | -0.017 |
ger | -0.017 |
Token | count |
Token ID | 954 |
Feature activation | -3.05e-03 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
� | +0.005 |
ok | +0.005 |
ze | +0.005 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.006 |
eling | -0.006 |
ateful | -0.006 |
nam | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -9.12e-03 |
Pos logit contributions | |
age | +0.005 |
est | +0.004 |
� | +0.004 |
ok | +0.003 |
ze | +0.003 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.006 |
outed | -0.005 |
ries | -0.005 |
ateful | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
age | +0.018 |
est | +0.016 |
� | +0.014 |
ok | +0.014 |
ze | +0.013 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.013 |
ries | -0.013 |
outed | -0.013 |
ateful | -0.013 |
Token | wizard |
Token ID | 18731 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
age | +0.021 |
est | +0.016 |
� | +0.015 |
ok | +0.014 |
ench | +0.014 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.016 |
nam | -0.016 |
ateful | -0.015 |
brushes | -0.015 |
Token | catch |
Token ID | 4929 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
yles | +0.044 |
outing | +0.042 |
outed | +0.040 |
ries | +0.040 |
ateful | +0.038 |
Neg logit contributions | |
age | -0.036 |
est | -0.030 |
� | -0.027 |
ok | -0.024 |
ze | -0.024 |
Token | fish |
Token ID | 5916 |
Feature activation | +6.12e-03 |
Pos logit contributions | |
yles | +0.033 |
ries | +0.029 |
outing | +0.029 |
ateful | +0.028 |
eling | +0.027 |
Neg logit contributions | |
age | -0.050 |
est | -0.040 |
ok | -0.036 |
� | -0.036 |
sy | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e-03 |
Pos logit contributions | |
yles | +0.011 |
outing | +0.011 |
ries | +0.010 |
ateful | +0.010 |
outed | +0.010 |
Neg logit contributions | |
age | -0.010 |
est | -0.009 |
ok | -0.008 |
� | -0.007 |
nob | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | -7.09e-03 |
Pos logit contributions | |
age | +0.002 |
est | +0.001 |
� | +0.001 |
ok | +0.001 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.003 |
outing | -0.003 |
ries | -0.002 |
outed | -0.002 |
ateful | -0.002 |
Token | liked |
Token ID | 8288 |
Feature activation | -2.64e-04 |
Pos logit contributions | |
age | +0.013 |
est | +0.011 |
� | +0.010 |
ok | +0.010 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.012 |
outing | -0.011 |
ries | -0.011 |
ateful | -0.011 |
outed | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
age | +0.000 |
est | +0.000 |
� | +0.000 |
right | +0.000 |
best | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.001 |
ateful | -0.001 |
eling | -0.001 |
Token | job |
Token ID | 1693 |
Feature activation | -9.43e-03 |
Pos logit contributions | |
yles | +0.056 |
outing | +0.052 |
ries | +0.049 |
outed | +0.048 |
ateful | +0.048 |
Neg logit contributions | |
age | -0.055 |
est | -0.048 |
� | -0.041 |
ok | -0.040 |
best | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
age | +0.015 |
est | +0.013 |
� | +0.011 |
ok | +0.010 |
ze | +0.010 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.018 |
ries | -0.017 |
outed | -0.017 |
ateful | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
outed | +0.002 |
ries | +0.002 |
ateful | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.001 |
� | -0.001 |
ok | -0.001 |
ze | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
age | +0.010 |
est | +0.008 |
� | +0.007 |
ok | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.014 |
outed | -0.013 |
ries | -0.013 |
ateful | -0.013 |
Token | One |
Token ID | 3198 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
age | +0.013 |
est | +0.012 |
ok | +0.010 |
� | +0.010 |
ze | +0.010 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.013 |
outed | -0.012 |
ateful | -0.011 |
ries | -0.011 |
Token | beach |
Token ID | 10481 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
age | +0.021 |
est | +0.018 |
ok | +0.016 |
� | +0.016 |
nob | +0.015 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.012 |
ateful | -0.011 |
outed | -0.011 |
eling | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e-04 |
Pos logit contributions | |
yles | +0.043 |
outing | +0.040 |
ries | +0.039 |
outed | +0.038 |
ateful | +0.037 |
Neg logit contributions | |
age | -0.037 |
est | -0.031 |
� | -0.027 |
ok | -0.026 |
ze | -0.025 |
Token | Jane |
Token ID | 12091 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
age | +0.000 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.000 |
outing | -0.000 |
outed | -0.000 |
ries | -0.000 |
ateful | -0.000 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.002 |
outed | +0.002 |
ries | +0.002 |
eling | +0.002 |
Neg logit contributions | |
age | -0.004 |
est | -0.003 |
� | -0.003 |
ok | -0.003 |
ze | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
yles | +0.003 |
outed | +0.003 |
outing | +0.003 |
nam | +0.003 |
eling | +0.003 |
Neg logit contributions | |
age | -0.003 |
est | -0.002 |
ze | -0.002 |
nob | -0.002 |
� | -0.002 |
Token | Joe |
Token ID | 5689 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
outing | +0.052 |
yles | +0.050 |
outed | +0.047 |
ateful | +0.046 |
ins | +0.045 |
Neg logit contributions | |
est | -0.033 |
age | -0.029 |
� | -0.028 |
biggest | -0.027 |
back | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
yles | +0.038 |
outing | +0.036 |
ries | +0.034 |
eling | +0.034 |
outed | +0.034 |
Neg logit contributions | |
age | -0.028 |
est | -0.023 |
ok | -0.019 |
� | -0.017 |
ze | -0.017 |
Token | who |
Token ID | 508 |
Feature activation | -8.88e-03 |
Pos logit contributions | |
age | +0.005 |
est | +0.005 |
� | +0.004 |
ok | +0.004 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.006 |
ateful | -0.006 |
ries | -0.006 |
outed | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +8.75e-04 |
Pos logit contributions | |
age | +0.011 |
� | +0.010 |
est | +0.009 |
ok | +0.007 |
best | +0.007 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.019 |
ries | -0.018 |
ateful | -0.018 |
nam | -0.018 |
Token | jumping |
Token ID | 14284 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
outed | +0.001 |
ateful | +0.001 |
ries | +0.001 |
Neg logit contributions | |
age | -0.002 |
est | -0.001 |
� | -0.001 |
ok | -0.001 |
ze | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | +7.98e-03 |
Pos logit contributions | |
age | +0.060 |
est | +0.044 |
ok | +0.038 |
ench | +0.037 |
house | +0.036 |
Neg logit contributions | |
outing | -0.056 |
yles | -0.054 |
outed | -0.051 |
ries | -0.049 |
they | -0.049 |
Token | shining |
Token ID | 22751 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
age | +0.016 |
est | +0.014 |
� | +0.011 |
nob | +0.011 |
ok | +0.011 |
Neg logit contributions | |
yles | -0.012 |
outing | -0.012 |
nam | -0.011 |
spill | -0.011 |
ateful | -0.010 |
Token | penny |
Token ID | 26369 |
Feature activation | -8.30e-03 |
Pos logit contributions | |
ries | +0.006 |
spill | +0.006 |
yles | +0.006 |
outing | +0.006 |
tilted | +0.005 |
Neg logit contributions | |
age | -0.010 |
ok | -0.008 |
� | -0.007 |
tted | -0.007 |
est | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
age | +0.013 |
est | +0.011 |
ok | +0.009 |
� | +0.008 |
ench | +0.008 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.015 |
ries | -0.015 |
eling | -0.015 |
outed | -0.014 |
Token | picked |
Token ID | 6497 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
ateful | +0.002 |
ries | +0.002 |
outed | +0.002 |
Neg logit contributions | |
age | -0.004 |
est | -0.003 |
� | -0.003 |
ok | -0.003 |
ze | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +1.00e-03 |
Pos logit contributions | |
yles | +0.016 |
ries | +0.013 |
outing | +0.012 |
eling | +0.011 |
inspection | +0.011 |
Neg logit contributions | |
age | -0.037 |
est | -0.031 |
ok | -0.029 |
iver | -0.028 |
sy | -0.028 |
Token | up |
Token ID | 510 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
yles | +0.001 |
outing | +0.001 |
they | +0.001 |
ries | +0.001 |
outed | +0.001 |
Neg logit contributions | |
age | -0.002 |
est | -0.001 |
tted | -0.001 |
iver | -0.001 |
virtue | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
outing | +0.017 |
yles | +0.017 |
outed | +0.016 |
ries | +0.016 |
nam | +0.016 |
Neg logit contributions | |
age | -0.019 |
est | -0.016 |
ze | -0.013 |
� | -0.013 |
ok | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
age | +0.003 |
est | +0.002 |
ze | +0.002 |
sy | +0.002 |
ok | +0.002 |
Neg logit contributions | |
yles | -0.002 |
outed | -0.002 |
outing | -0.002 |
nam | -0.002 |
brushes | -0.001 |
Token | smiled |
Token ID | 13541 |
Feature activation | +5.01e-03 |
Pos logit contributions | |
age | +0.033 |
est | +0.029 |
� | +0.027 |
ok | +0.026 |
ze | +0.025 |
Neg logit contributions | |
yles | -0.021 |
outing | -0.019 |
ries | -0.018 |
outed | -0.018 |
ateful | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -4.16e-04 |
Pos logit contributions | |
yles | +0.009 |
outing | +0.009 |
outed | +0.008 |
ateful | +0.008 |
ries | +0.008 |
Neg logit contributions | |
age | -0.009 |
est | -0.007 |
� | -0.006 |
nob | -0.006 |
ok | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | -4.97e-03 |
Pos logit contributions | |
age | +0.001 |
� | +0.001 |
est | +0.001 |
ok | +0.001 |
right | +0.001 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
ateful | -0.001 |
ries | -0.001 |
eling | -0.001 |
Token | baby |
Token ID | 5156 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
age | +0.011 |
est | +0.009 |
� | +0.008 |
ok | +0.008 |
nob | +0.008 |
Neg logit contributions | |
yles | -0.008 |
outing | -0.007 |
outed | -0.007 |
ries | -0.007 |
ateful | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
age | +0.069 |
est | +0.062 |
� | +0.056 |
ok | +0.055 |
ench | +0.052 |
Neg logit contributions | |
yles | -0.041 |
outing | -0.039 |
outed | -0.037 |
ries | -0.036 |
eling | -0.035 |
Token | tears |
Token ID | 10953 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
yles | +0.023 |
outing | +0.022 |
outed | +0.021 |
ries | +0.020 |
ateful | +0.020 |
Neg logit contributions | |
age | -0.025 |
est | -0.022 |
� | -0.020 |
nob | -0.018 |
ok | -0.018 |
Token | slowly |
Token ID | 6364 |
Feature activation | -6.22e-03 |
Pos logit contributions | |
yles | +0.057 |
outing | +0.051 |
ateful | +0.049 |
ries | +0.049 |
nam | +0.048 |
Neg logit contributions | |
age | -0.057 |
est | -0.050 |
� | -0.045 |
ok | -0.042 |
ze | -0.041 |
Token | stopped |
Token ID | 5025 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
age | +0.011 |
est | +0.009 |
� | +0.008 |
ze | +0.007 |
ok | +0.007 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.011 |
ateful | -0.011 |
nam | -0.011 |
ries | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -5.15e-05 |
Pos logit contributions | |
yles | +0.017 |
outing | +0.016 |
outed | +0.015 |
ateful | +0.015 |
ries | +0.015 |
Neg logit contributions | |
age | -0.015 |
est | -0.013 |
� | -0.012 |
ok | -0.011 |
ze | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -6.72e-03 |
Pos logit contributions | |
age | +0.000 |
� | +0.000 |
est | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.000 |
outing | -0.000 |
ateful | -0.000 |
ries | -0.000 |
outed | -0.000 |
Token | baby |
Token ID | 5156 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
age | +0.014 |
est | +0.012 |
� | +0.011 |
ok | +0.011 |
nob | +0.010 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.009 |
ries | -0.008 |
outed | -0.008 |
ateful | -0.008 |
Token | fell |
Token ID | 3214 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
age | +0.062 |
est | +0.055 |
� | +0.049 |
ok | +0.047 |
ze | +0.045 |
Neg logit contributions | |
yles | -0.046 |
outing | -0.042 |
outed | -0.040 |
ries | -0.040 |
ateful | -0.039 |
Token | asleep |
Token ID | 16039 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
age | +0.051 |
est | +0.046 |
� | +0.040 |
ok | +0.037 |
ench | +0.037 |
Neg logit contributions | |
outing | -0.051 |
yles | -0.049 |
outed | -0.048 |
ries | -0.046 |
nam | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
age | +0.020 |
est | +0.017 |
� | +0.015 |
ok | +0.014 |
biggest | +0.013 |
Neg logit contributions | |
yles | -0.022 |
outing | -0.021 |
nam | -0.020 |
outed | -0.020 |
eling | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
right | +0.020 |
back | +0.020 |
middle | +0.020 |
safe | +0.019 |
best | +0.019 |
Neg logit contributions | |
outing | -0.054 |
yles | -0.054 |
outed | -0.051 |
ateful | -0.050 |
ins | -0.048 |
Token | top |
Token ID | 1353 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
age | +0.022 |
est | +0.019 |
� | +0.017 |
ok | +0.016 |
ze | +0.015 |
Neg logit contributions | |
yles | -0.017 |
outing | -0.016 |
outed | -0.015 |
ries | -0.015 |
eling | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
age | +0.076 |
est | +0.063 |
� | +0.055 |
ok | +0.050 |
ze | +0.047 |
Neg logit contributions | |
yles | -0.106 |
outing | -0.099 |
outed | -0.095 |
ries | -0.094 |
ateful | -0.094 |
Token | They |
Token ID | 1119 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
yles | +0.004 |
outing | +0.004 |
eling | +0.004 |
ries | +0.004 |
ateful | +0.003 |
Neg logit contributions | |
age | -0.003 |
est | -0.002 |
� | -0.002 |
ok | -0.002 |
middle | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | -4.44e-02 |
Pos logit contributions | |
age | +0.009 |
� | +0.009 |
even | +0.007 |
est | +0.007 |
middle | +0.007 |
Neg logit contributions | |
yles | -0.011 |
ries | -0.009 |
outing | -0.009 |
ateful | -0.009 |
irs | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -9.12e-03 |
Pos logit contributions | |
age | +0.072 |
est | +0.060 |
� | +0.052 |
ok | +0.049 |
ze | +0.046 |
Neg logit contributions | |
yles | -0.089 |
outing | -0.083 |
ries | -0.079 |
outed | -0.079 |
ateful | -0.079 |
Token | big |
Token ID | 1263 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
age | +0.017 |
est | +0.015 |
� | +0.013 |
ok | +0.013 |
ze | +0.012 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.014 |
nam | -0.013 |
outed | -0.013 |
spill | -0.013 |
Token | bag |
Token ID | 6131 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
age | +0.044 |
est | +0.035 |
ok | +0.032 |
� | +0.032 |
ze | +0.031 |
Neg logit contributions | |
spill | -0.027 |
ries | -0.027 |
yles | -0.026 |
outing | -0.026 |
brushes | -0.026 |
Token | of |
Token ID | 286 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
age | +0.033 |
est | +0.029 |
ok | +0.024 |
� | +0.024 |
ze | +0.023 |
Neg logit contributions | |
outing | -0.034 |
yles | -0.034 |
outed | -0.032 |
ries | -0.031 |
ateful | -0.030 |
Token | flour |
Token ID | 10601 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
yles | +0.037 |
outing | +0.034 |
outed | +0.032 |
ateful | +0.032 |
ries | +0.031 |
Neg logit contributions | |
age | -0.044 |
est | -0.039 |
� | -0.034 |
ok | -0.033 |
ze | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e-04 |
Pos logit contributions | |
age | +0.070 |
est | +0.056 |
� | +0.047 |
ok | +0.043 |
ze | +0.040 |
Neg logit contributions | |
yles | -0.122 |
outing | -0.115 |
ries | -0.110 |
outed | -0.110 |
ateful | -0.109 |
Token | One |
Token ID | 3198 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
age | +0.015 |
est | +0.013 |
� | +0.011 |
ok | +0.010 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.024 |
outing | -0.022 |
ries | -0.022 |
outed | -0.022 |
ateful | -0.022 |
Token | day |
Token ID | 1110 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
age | +0.029 |
est | +0.023 |
� | +0.019 |
ok | +0.017 |
ze | +0.016 |
Neg logit contributions | |
yles | -0.054 |
outing | -0.051 |
ries | -0.049 |
outed | -0.049 |
ateful | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -9.59e-03 |
Pos logit contributions | |
age | +0.010 |
est | +0.008 |
� | +0.006 |
ok | +0.004 |
best | +0.004 |
Neg logit contributions | |
yles | -0.033 |
outing | -0.031 |
outed | -0.030 |
ateful | -0.030 |
ries | -0.030 |
Token | Sara |
Token ID | 24799 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
est | +0.017 |
best | +0.016 |
� | +0.016 |
age | +0.016 |
ok | +0.015 |
Neg logit contributions | |
yles | -0.014 |
outing | -0.013 |
eling | -0.013 |
ateful | -0.012 |
irs | -0.012 |
Token | finds |
Token ID | 7228 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
age | +0.030 |
est | +0.026 |
ok | +0.024 |
ench | +0.022 |
ze | +0.021 |
Neg logit contributions | |
yles | -0.026 |
outed | -0.023 |
ila | -0.023 |
ateful | -0.023 |
outing | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
age | +0.038 |
est | +0.031 |
� | +0.027 |
ok | +0.025 |
ze | +0.024 |
Neg logit contributions | |
yles | -0.053 |
outing | -0.050 |
outed | -0.047 |
ries | -0.047 |
ateful | -0.047 |
Token | big |
Token ID | 1263 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
age | +0.023 |
est | +0.020 |
� | +0.017 |
ok | +0.017 |
ze | +0.016 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.018 |
nam | -0.017 |
outed | -0.017 |
ateful | -0.017 |
Token | bottle |
Token ID | 9294 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
age | +0.046 |
est | +0.037 |
ok | +0.036 |
� | +0.035 |
tted | +0.034 |
Neg logit contributions | |
yles | -0.031 |
passports | -0.030 |
ries | -0.030 |
nam | -0.029 |
spill | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
age | +0.026 |
est | +0.024 |
ok | +0.023 |
ze | +0.020 |
advantage | +0.020 |
Neg logit contributions | |
outing | -0.022 |
outed | -0.020 |
yles | -0.020 |
ila | -0.019 |
ries | -0.019 |
Token | oil |
Token ID | 3056 |
Feature activation | -9.97e-03 |
Pos logit contributions | |
yles | +0.033 |
outing | +0.030 |
ries | +0.029 |
outed | +0.028 |
ateful | +0.028 |
Neg logit contributions | |
age | -0.042 |
est | -0.036 |
� | -0.032 |
ok | -0.031 |
ze | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
age | +0.015 |
est | +0.013 |
ok | +0.012 |
� | +0.011 |
ench | +0.010 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.019 |
ries | -0.018 |
outed | -0.018 |
ateful | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -8.71e-03 |
Pos logit contributions | |
age | +0.087 |
est | +0.075 |
� | +0.067 |
ok | +0.064 |
ze | +0.062 |
Neg logit contributions | |
yles | -0.064 |
outing | -0.057 |
ries | -0.055 |
outed | -0.054 |
ateful | -0.053 |
Token | fork |
Token ID | 15563 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
age | +0.020 |
est | +0.017 |
� | +0.015 |
nob | +0.014 |
tted | +0.014 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.010 |
nam | -0.009 |
spill | -0.009 |
frowned | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | -9.17e-03 |
Pos logit contributions | |
age | +0.018 |
est | +0.015 |
ok | +0.012 |
ench | +0.012 |
� | +0.012 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.020 |
ries | -0.018 |
spill | -0.018 |
outed | -0.017 |
Token | From |
Token ID | 3574 |
Feature activation | +6.62e-03 |
Pos logit contributions | |
age | +0.017 |
est | +0.015 |
ze | +0.013 |
ok | +0.013 |
� | +0.012 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.014 |
outed | -0.014 |
ries | -0.014 |
ateful | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
yles | +0.012 |
outing | +0.012 |
outed | +0.011 |
ateful | +0.011 |
ries | +0.011 |
Neg logit contributions | |
age | -0.011 |
est | -0.010 |
� | -0.009 |
ok | -0.008 |
ze | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | -5.79e-03 |
Pos logit contributions | |
yles | +0.014 |
they | +0.014 |
outing | +0.013 |
nam | +0.013 |
frowned | +0.013 |
Neg logit contributions | |
age | -0.022 |
est | -0.016 |
ze | -0.016 |
tted | -0.016 |
ench | -0.016 |
Token | Bob |
Token ID | 5811 |
Feature activation | +8.49e-03 |
Pos logit contributions | |
age | +0.009 |
est | +0.008 |
ze | +0.006 |
ench | +0.006 |
nob | +0.006 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.010 |
outed | -0.010 |
ries | -0.010 |
nam | -0.010 |
Token | knew |
Token ID | 2993 |
Feature activation | +4.47e-03 |
Pos logit contributions | |
yles | +0.013 |
outing | +0.012 |
outed | +0.012 |
ries | +0.012 |
eling | +0.012 |
Neg logit contributions | |
age | -0.016 |
est | -0.015 |
ok | -0.013 |
� | -0.012 |
biggest | -0.012 |
Token | what |
Token ID | 644 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
yles | +0.008 |
outing | +0.007 |
outed | +0.007 |
ateful | +0.006 |
ries | +0.006 |
Neg logit contributions | |
age | -0.009 |
est | -0.008 |
� | -0.007 |
ok | -0.007 |
best | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -8.74e-03 |
Pos logit contributions | |
yles | +0.022 |
outing | +0.020 |
ries | +0.019 |
outed | +0.019 |
ateful | +0.019 |
Neg logit contributions | |
age | -0.028 |
est | -0.025 |
� | -0.022 |
ok | -0.021 |
ze | -0.020 |
Token | fork |
Token ID | 15563 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
age | +0.024 |
est | +0.020 |
tted | +0.018 |
house | +0.018 |
mates | +0.018 |
Neg logit contributions | |
yles | -0.007 |
outing | -0.006 |
spill | -0.006 |
eling | -0.005 |
frowned | -0.005 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
yles | +0.048 |
outing | +0.044 |
ries | +0.040 |
nam | +0.040 |
ateful | +0.039 |
Neg logit contributions | |
age | -0.064 |
est | -0.059 |
� | -0.057 |
ok | -0.051 |
middle | -0.050 |
Token | asks |
Token ID | 7893 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
yles | +0.016 |
outing | +0.013 |
outed | +0.011 |
ries | +0.011 |
ateful | +0.011 |
Neg logit contributions | |
age | -0.054 |
est | -0.049 |
� | -0.045 |
ok | -0.044 |
ze | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
yles | +0.058 |
outing | +0.054 |
ries | +0.052 |
outed | +0.051 |
ateful | +0.051 |
Neg logit contributions | |
age | -0.054 |
est | -0.045 |
� | -0.039 |
ok | -0.037 |
ze | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
yles | +0.023 |
outing | +0.022 |
eling | +0.021 |
ateful | +0.021 |
ries | +0.021 |
Neg logit contributions | |
age | -0.013 |
est | -0.011 |
� | -0.010 |
ok | -0.009 |
right | -0.008 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.59e-03 |
Pos logit contributions | |
age | +0.026 |
est | +0.024 |
� | +0.022 |
ok | +0.021 |
ze | +0.020 |
Neg logit contributions | |
yles | -0.019 |
outing | -0.017 |
ateful | -0.016 |
nam | -0.016 |
ries | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.003 |
ries | +0.003 |
outed | +0.003 |
ateful | +0.003 |
Neg logit contributions | |
age | -0.003 |
est | -0.002 |
� | -0.002 |
ok | -0.002 |
ze | -0.002 |
Token | shovel |
Token ID | 33677 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
age | +0.020 |
est | +0.017 |
� | +0.015 |
ok | +0.014 |
ze | +0.014 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.015 |
outed | -0.014 |
ries | -0.014 |
ateful | -0.013 |
Token | from |
Token ID | 422 |
Feature activation | -3.28e-04 |
Pos logit contributions | |
yles | +0.037 |
outing | +0.034 |
eling | +0.033 |
ateful | +0.032 |
outed | +0.032 |
Neg logit contributions | |
age | -0.022 |
est | -0.018 |
� | -0.016 |
ok | -0.014 |
best | -0.012 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
right | +0.000 |
� | +0.000 |
back | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.000 |
ateful | -0.000 |
nam | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
yles | +0.053 |
outing | +0.051 |
ries | +0.049 |
nam | +0.047 |
outed | +0.047 |
Neg logit contributions | |
age | -0.045 |
est | -0.039 |
ok | -0.032 |
biggest | -0.029 |
ze | -0.029 |
Token | fills |
Token ID | 23816 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
outing | +0.002 |
yles | +0.002 |
ateful | +0.002 |
outed | +0.002 |
nam | +0.001 |
Neg logit contributions | |
� | -0.002 |
est | -0.002 |
age | -0.002 |
right | -0.002 |
back | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -7.55e-03 |
Pos logit contributions | |
yles | +0.009 |
outing | +0.008 |
outed | +0.008 |
ries | +0.008 |
ateful | +0.008 |
Neg logit contributions | |
age | -0.009 |
est | -0.008 |
� | -0.007 |
ok | -0.007 |
ze | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -8.92e-03 |
Pos logit contributions | |
age | +0.012 |
est | +0.011 |
ok | +0.009 |
� | +0.008 |
biggest | +0.008 |
Neg logit contributions | |
yles | -0.015 |
outing | -0.014 |
outed | -0.013 |
ateful | -0.013 |
ries | -0.013 |
Token | L |
Token ID | 43 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
age | +0.018 |
est | +0.017 |
ok | +0.014 |
biggest | +0.013 |
best | +0.013 |
Neg logit contributions | |
yles | -0.013 |
outing | -0.013 |
outed | -0.012 |
ateful | -0.012 |
nam | -0.011 |
Token | ily |
Token ID | 813 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
yles | +0.092 |
outing | +0.087 |
outed | +0.084 |
ries | +0.083 |
ateful | +0.083 |
Neg logit contributions | |
age | -0.073 |
est | -0.060 |
� | -0.052 |
ok | -0.049 |
ze | -0.047 |
Token | 's |
Token ID | 338 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
outed | +0.024 |
yles | +0.024 |
frowned | +0.023 |
outing | +0.022 |
eling | +0.021 |
Neg logit contributions | |
age | -0.049 |
est | -0.044 |
ok | -0.040 |
biggest | -0.039 |
advantage | -0.038 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
yles | +0.020 |
outing | +0.019 |
outed | +0.019 |
ateful | +0.018 |
nam | +0.017 |
Neg logit contributions | |
age | -0.029 |
est | -0.025 |
� | -0.022 |
sy | -0.021 |
ok | -0.021 |
Token | my |
Token ID | 1820 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
age | +0.007 |
est | +0.006 |
� | +0.005 |
ok | +0.005 |
ze | +0.004 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.009 |
outed | -0.009 |
ries | -0.009 |
ateful | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +3.70e-03 |
Pos logit contributions | |
age | +0.019 |
est | +0.017 |
� | +0.015 |
ok | +0.015 |
ze | +0.014 |
Neg logit contributions | |
yles | -0.009 |
outing | -0.008 |
outed | -0.008 |
ries | -0.008 |
ateful | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
yles | +0.007 |
outing | +0.007 |
outed | +0.007 |
ateful | +0.007 |
nam | +0.007 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
� | -0.004 |
nob | -0.004 |
ze | -0.004 |
Token | touched |
Token ID | 12615 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
yles | +0.032 |
ries | +0.030 |
outing | +0.028 |
eling | +0.027 |
irs | +0.027 |
Neg logit contributions | |
age | -0.018 |
� | -0.014 |
est | -0.014 |
ok | -0.013 |
best | -0.012 |
Token | by |
Token ID | 416 |
Feature activation | -1.26e-03 |
Pos logit contributions | |
age | +0.025 |
est | +0.022 |
� | +0.020 |
ok | +0.019 |
ze | +0.019 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.015 |
ries | -0.014 |
outed | -0.014 |
ateful | -0.014 |
Token | put |
Token ID | 1234 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
yles | +0.007 |
outing | +0.007 |
ateful | +0.006 |
ries | +0.006 |
outed | +0.006 |
Neg logit contributions | |
age | -0.008 |
est | -0.007 |
� | -0.006 |
ze | -0.006 |
ok | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | -8.67e-03 |
Pos logit contributions | |
age | +0.032 |
est | +0.029 |
� | +0.026 |
ok | +0.025 |
ze | +0.024 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.018 |
outed | -0.017 |
ateful | -0.017 |
ries | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +1.21e-03 |
Pos logit contributions | |
age | +0.020 |
est | +0.018 |
� | +0.016 |
ok | +0.016 |
ze | +0.015 |
Neg logit contributions | |
yles | -0.011 |
outing | -0.010 |
outed | -0.010 |
ateful | -0.010 |
ries | -0.009 |
Token | p |
Token ID | 279 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
yles | +0.002 |
nam | +0.002 |
ries | +0.002 |
outing | +0.002 |
outed | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.002 |
� | -0.002 |
ok | -0.002 |
ench | -0.002 |
Token | aj |
Token ID | 1228 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
yles | +0.054 |
ateful | +0.048 |
nam | +0.047 |
eling | +0.047 |
outing | +0.046 |
Neg logit contributions | |
age | -0.060 |
est | -0.050 |
� | -0.041 |
ze | -0.039 |
sy | -0.039 |
Token | amas |
Token ID | 17485 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
age | +0.012 |
est | +0.010 |
� | +0.008 |
ok | +0.008 |
biggest | +0.006 |
Neg logit contributions | |
yles | -0.025 |
outing | -0.024 |
ries | -0.023 |
outed | -0.023 |
ateful | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-03 |
Pos logit contributions | |
age | +0.136 |
est | +0.120 |
� | +0.100 |
ok | +0.098 |
ze | +0.091 |
Neg logit contributions | |
yles | -0.148 |
outing | -0.142 |
outed | -0.131 |
nam | -0.129 |
ateful | -0.128 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.002 |
ok | +0.002 |
ze | +0.002 |
Neg logit contributions | |
yles | -0.002 |
outing | -0.002 |
outed | -0.002 |
ries | -0.002 |
ateful | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.003 |
outed | +0.003 |
ries | +0.003 |
ateful | +0.003 |
Neg logit contributions | |
age | -0.003 |
est | -0.003 |
� | -0.002 |
ok | -0.002 |
ze | -0.002 |
Token | read |
Token ID | 1100 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
age | +0.033 |
est | +0.030 |
� | +0.026 |
ok | +0.026 |
ze | +0.025 |
Neg logit contributions | |
yles | -0.021 |
outing | -0.019 |
outed | -0.018 |
ries | -0.018 |
ateful | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +5.91e-04 |
Pos logit contributions | |
yles | +0.025 |
outing | +0.023 |
outed | +0.021 |
ateful | +0.021 |
ries | +0.021 |
Neg logit contributions | |
age | -0.042 |
est | -0.038 |
� | -0.034 |
ok | -0.033 |
ze | -0.032 |
Token | share |
Token ID | 2648 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
yles | +0.033 |
outing | +0.029 |
ries | +0.028 |
eling | +0.028 |
ateful | +0.028 |
Neg logit contributions | |
age | -0.040 |
est | -0.037 |
ok | -0.031 |
� | -0.030 |
sy | -0.029 |
Token | your |
Token ID | 534 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
age | +0.040 |
est | +0.034 |
� | +0.029 |
ok | +0.028 |
sy | +0.027 |
Neg logit contributions | |
yles | -0.039 |
outing | -0.035 |
ries | -0.035 |
ateful | -0.034 |
nam | -0.033 |
Token | food |
Token ID | 2057 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
age | +0.022 |
est | +0.018 |
� | +0.018 |
ok | +0.017 |
sy | +0.017 |
Neg logit contributions | |
yles | -0.014 |
ries | -0.013 |
outing | -0.012 |
eling | -0.012 |
outed | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
age | +0.054 |
est | +0.043 |
� | +0.038 |
ok | +0.038 |
nob | +0.037 |
Neg logit contributions | |
yles | -0.053 |
outing | -0.051 |
ries | -0.050 |
ateful | -0.049 |
nam | -0.047 |
Token | make |
Token ID | 787 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
yles | +0.011 |
outing | +0.010 |
outed | +0.010 |
ries | +0.010 |
ateful | +0.010 |
Neg logit contributions | |
age | -0.011 |
est | -0.009 |
� | -0.008 |
ok | -0.008 |
ze | -0.008 |
Token | us |
Token ID | 514 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
age | +0.023 |
est | +0.020 |
� | +0.017 |
ok | +0.016 |
sy | +0.016 |
Neg logit contributions | |
yles | -0.018 |
outing | -0.016 |
ries | -0.016 |
ateful | -0.015 |
eling | -0.015 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
age | +0.152 |
est | +0.129 |
nob | +0.116 |
� | +0.114 |
antly | +0.112 |
Neg logit contributions | |
yles | -0.102 |
nam | -0.096 |
outing | -0.094 |
ateful | -0.093 |
ries | -0.092 |
Token | ." |
Token ID | 526 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
yles | +0.057 |
ries | +0.052 |
ateful | +0.051 |
outing | +0.048 |
ins | +0.047 |
Neg logit contributions | |
age | -0.050 |
sy | -0.037 |
est | -0.036 |
� | -0.036 |
tted | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
yles | +0.026 |
outing | +0.024 |
outed | +0.023 |
ateful | +0.023 |
ries | +0.023 |
Neg logit contributions | |
age | -0.020 |
est | -0.017 |
� | -0.014 |
ok | -0.014 |
ze | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -3.21e-04 |
Pos logit contributions | |
yles | +0.002 |
outing | +0.002 |
ateful | +0.002 |
outed | +0.002 |
ries | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.002 |
ok | -0.001 |
� | -0.001 |
ze | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.001 |
ok | +0.000 |
� | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
ateful | -0.000 |
outed | -0.000 |
ila | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +9.93e-03 |
Pos logit contributions | |
yles | +0.069 |
outing | +0.065 |
ries | +0.062 |
outed | +0.061 |
ateful | +0.061 |
Neg logit contributions | |
age | -0.060 |
est | -0.049 |
� | -0.042 |
ok | -0.040 |
ze | -0.039 |
Token | " |
Token ID | 366 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
yles | +0.022 |
outing | +0.021 |
ries | +0.020 |
outed | +0.020 |
ateful | +0.020 |
Neg logit contributions | |
age | -0.014 |
est | -0.011 |
� | -0.009 |
ok | -0.009 |
ze | -0.008 |
Token | He |
Token ID | 1544 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
yles | +0.023 |
outing | +0.022 |
ries | +0.021 |
outed | +0.021 |
eling | +0.020 |
Neg logit contributions | |
age | -0.021 |
� | -0.017 |
est | -0.017 |
ok | -0.014 |
ze | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
yles | +0.013 |
outing | +0.012 |
ries | +0.012 |
outed | +0.012 |
eling | +0.011 |
Neg logit contributions | |
age | -0.012 |
est | -0.010 |
� | -0.008 |
ok | -0.008 |
ze | -0.008 |
Token | making |
Token ID | 1642 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
yles | +0.043 |
outing | +0.040 |
outed | +0.038 |
nam | +0.038 |
ries | +0.037 |
Neg logit contributions | |
age | -0.046 |
est | -0.040 |
� | -0.034 |
ok | -0.031 |
ze | -0.031 |
Token | us |
Token ID | 514 |
Feature activation | -7.63e-02 |
Pos logit contributions | |
age | +0.068 |
est | +0.058 |
sy | +0.048 |
ench | +0.048 |
nob | +0.047 |
Neg logit contributions | |
yles | -0.054 |
ries | -0.049 |
outing | -0.049 |
eling | -0.047 |
ateful | -0.047 |
Token | scared |
Token ID | 12008 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
age | +0.137 |
est | +0.118 |
� | +0.097 |
ok | +0.096 |
nob | +0.096 |
Neg logit contributions | |
yles | -0.124 |
outing | -0.120 |
ries | -0.115 |
ateful | -0.114 |
nam | -0.114 |
Token | ." |
Token ID | 526 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
yles | +0.011 |
ries | +0.011 |
outing | +0.011 |
ateful | +0.010 |
ila | +0.010 |
Neg logit contributions | |
age | -0.014 |
est | -0.011 |
sy | -0.010 |
ench | -0.010 |
nob | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -3.41e-04 |
Pos logit contributions | |
yles | +0.027 |
outing | +0.026 |
outed | +0.025 |
ateful | +0.024 |
ries | +0.024 |
Neg logit contributions | |
age | -0.026 |
est | -0.022 |
� | -0.018 |
ze | -0.018 |
ok | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
age | +0.001 |
est | +0.000 |
� | +0.000 |
ok | +0.000 |
ze | +0.000 |
Neg logit contributions | |
yles | -0.001 |
outing | -0.001 |
outed | -0.001 |
ateful | -0.001 |
ries | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -9.63e-03 |
Pos logit contributions | |
age | +0.003 |
est | +0.003 |
ok | +0.002 |
� | +0.002 |
ze | +0.002 |
Neg logit contributions | |
yles | -0.003 |
outing | -0.003 |
ateful | -0.003 |
outed | -0.003 |
ries | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +3.13e-03 |
Pos logit contributions | |
yles | +0.034 |
outing | +0.033 |
outed | +0.031 |
ateful | +0.030 |
ries | +0.028 |
Neg logit contributions | |
age | -0.029 |
� | -0.026 |
back | -0.025 |
right | -0.025 |
est | -0.024 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
yles | +0.004 |
ries | +0.004 |
outing | +0.004 |
outed | +0.004 |
nam | +0.004 |
Neg logit contributions | |
age | -0.007 |
est | -0.006 |
ok | -0.005 |
� | -0.005 |
tted | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -3.76e-03 |
Pos logit contributions | |
age | +0.015 |
est | +0.013 |
� | +0.010 |
ok | +0.010 |
ze | +0.009 |
Neg logit contributions | |
yles | -0.023 |
outing | -0.022 |
ries | -0.021 |
outed | -0.021 |
ateful | -0.020 |
Token | who |
Token ID | 508 |
Feature activation | -6.19e-03 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.006 |
ok | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.006 |
outing | -0.005 |
ateful | -0.005 |
ries | -0.005 |
outed | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
age | +0.005 |
� | +0.005 |
est | +0.004 |
right | +0.003 |
, | +0.003 |
Neg logit contributions | |
yles | -0.016 |
outing | -0.016 |
ateful | -0.015 |
nam | -0.015 |
outed | -0.015 |
Token | sitting |
Token ID | 5586 |
Feature activation | -8.70e-02 |
Pos logit contributions | |
yles | +0.006 |
outing | +0.005 |
outed | +0.005 |
ateful | +0.005 |
ries | +0.005 |
Neg logit contributions | |
age | -0.006 |
est | -0.005 |
� | -0.005 |
ok | -0.005 |
ze | -0.004 |
Token | on |
Token ID | 319 |
Feature activation | -4.87e-03 |
Pos logit contributions | |
age | +0.126 |
est | +0.103 |
� | +0.090 |
ok | +0.081 |
ze | +0.076 |
Neg logit contributions | |
yles | -0.187 |
outing | -0.180 |
ries | -0.173 |
outed | -0.172 |
ateful | -0.170 |
Token | a |
Token ID | 257 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
age | +0.008 |
est | +0.007 |
� | +0.006 |
ze | +0.006 |
right | +0.006 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.010 |
outed | -0.009 |
ateful | -0.009 |
eling | -0.008 |
Token | bench |
Token ID | 7624 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
age | +0.015 |
est | +0.013 |
� | +0.012 |
ok | +0.011 |
ze | +0.011 |
Neg logit contributions | |
yles | -0.010 |
outing | -0.009 |
outed | -0.009 |
ries | -0.009 |
ateful | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.60e-03 |
Pos logit contributions | |
yles | +0.090 |
ateful | +0.080 |
outing | +0.080 |
ries | +0.078 |
outed | +0.078 |
Neg logit contributions | |
age | -0.045 |
est | -0.034 |
� | -0.029 |
right | -0.025 |
ze | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
age | +0.004 |
� | +0.003 |
est | +0.003 |
ok | +0.003 |
Just | +0.003 |
Neg logit contributions | |
yles | -0.006 |
eling | -0.005 |
outing | -0.005 |
ries | -0.005 |
ateful | -0.005 |
Token | front |
Token ID | 2166 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
age | +0.014 |
est | +0.013 |
� | +0.012 |
right | +0.011 |
middle | +0.011 |
Neg logit contributions | |
yles | -0.020 |
outing | -0.020 |
outed | -0.019 |
eling | -0.017 |
ours | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
yles | +0.010 |
outing | +0.009 |
outed | +0.009 |
ries | +0.009 |
ateful | +0.009 |
Neg logit contributions | |
age | -0.008 |
est | -0.006 |
� | -0.006 |
ok | -0.005 |
ze | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
yles | +0.043 |
outing | +0.041 |
outed | +0.039 |
eling | +0.036 |
ateful | +0.036 |
Neg logit contributions | |
age | -0.036 |
est | -0.033 |
right | -0.031 |
back | -0.030 |
ok | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
age | +0.024 |
est | +0.020 |
� | +0.017 |
ok | +0.015 |
ze | +0.015 |
Neg logit contributions | |
yles | -0.038 |
outing | -0.035 |
outed | -0.034 |
ries | -0.034 |
ateful | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | -5.57e-03 |
Pos logit contributions | |
yles | +0.003 |
outing | +0.003 |
outed | +0.002 |
ateful | +0.002 |
ries | +0.002 |
Neg logit contributions | |
age | -0.002 |
est | -0.002 |
� | -0.001 |
ok | -0.001 |
ze | -0.001 |
Token | tri |
Token ID | 1333 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
age | +0.010 |
� | +0.008 |
est | +0.008 |
ze | +0.007 |
right | +0.007 |
Neg logit contributions | |
yles | -0.011 |
irs | -0.010 |
ries | -0.010 |
outing | -0.009 |
ateful | -0.009 |
Token | pped |
Token ID | 1496 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
age | +0.147 |
est | +0.135 |
� | +0.118 |
ok | +0.115 |
biggest | +0.113 |
Neg logit contributions | |
yles | -0.101 |
outing | -0.093 |
outed | -0.088 |
ateful | -0.085 |
ries | -0.085 |
Token | and |
Token ID | 290 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
age | +0.009 |
est | +0.007 |
ok | +0.006 |
� | +0.006 |
ze | +0.006 |
Neg logit contributions | |
yles | -0.012 |
outing | -0.011 |
ries | -0.011 |
outed | -0.010 |
ateful | -0.010 |
Token | fell |
Token ID | 3214 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
age | +0.004 |
� | +0.003 |
est | +0.003 |
ze | +0.003 |
middle | +0.002 |
Neg logit contributions | |
yles | -0.005 |
outing | -0.005 |
ries | -0.004 |
ateful | -0.004 |
passports | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
age | +0.058 |
est | +0.049 |
� | +0.042 |
ok | +0.040 |
ze | +0.038 |
Neg logit contributions | |
yles | -0.073 |
outing | -0.070 |
outed | -0.067 |
ries | -0.067 |
ateful | -0.065 |
Token | He |
Token ID | 679 |
Feature activation | -9.35e-03 |
Pos logit contributions | |
age | +0.002 |
est | +0.002 |
� | +0.002 |
ok | +0.002 |
ze | +0.001 |
Neg logit contributions | |
yles | -0.004 |
outing | -0.004 |
ries | -0.004 |
outed | -0.004 |
ateful | -0.004 |