Token | and |
Token ID | 290 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
nail | +0.016 |
run | +0.016 |
block | +0.016 |
inter | +0.015 |
ooter | +0.014 |
Neg logit contributions | |
Amen | -0.021 |
cle | -0.018 |
Merry | -0.017 |
Say | -0.017 |
MacDonald | -0.017 |
Token | stay |
Token ID | 2652 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
run | +0.014 |
nail | +0.013 |
block | +0.013 |
igsaw | +0.012 |
pad | +0.012 |
Neg logit contributions | |
Amen | -0.015 |
cle | -0.014 |
ting | -0.014 |
Miss | -0.013 |
Mr | -0.013 |
Token | well |
Token ID | 880 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
sets | +0.075 |
Amen | +0.074 |
ting | +0.074 |
cle | +0.074 |
Merry | +0.074 |
Neg logit contributions | |
run | -0.050 |
block | -0.046 |
nail | -0.045 |
igsaw | -0.041 |
foot | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
cle | +0.028 |
Amen | +0.027 |
Merry | +0.027 |
ting | +0.027 |
MacDonald | +0.026 |
Neg logit contributions | |
run | -0.035 |
block | -0.034 |
nail | -0.033 |
pad | -0.033 |
igsaw | -0.033 |
Token | Bro |
Token ID | 2806 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
cle | +0.021 |
sets | +0.021 |
ting | +0.021 |
glers | +0.020 |
pa | +0.020 |
Neg logit contributions | |
run | -0.023 |
Half | -0.021 |
block | -0.020 |
igsaw | -0.020 |
inter | -0.020 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
Amen | +0.082 |
Say | +0.078 |
ting | +0.078 |
Mr | +0.076 |
Merry | +0.076 |
Neg logit contributions | |
run | -0.066 |
block | -0.065 |
fault | -0.065 |
pad | -0.064 |
inter | -0.063 |
Token | is |
Token ID | 318 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
cle | +0.173 |
Amen | +0.170 |
Miss | +0.162 |
Merry | +0.161 |
Mr | +0.154 |
Neg logit contributions | |
block | -0.161 |
nail | -0.146 |
run | -0.134 |
inter | -0.133 |
pattern | -0.133 |
Token | your |
Token ID | 534 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.018 |
ting | +0.018 |
Mr | +0.017 |
Merry | +0.017 |
Neg logit contributions | |
run | -0.017 |
igsaw | -0.017 |
block | -0.016 |
nail | -0.016 |
ooter | -0.015 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Amen | +0.083 |
cle | +0.083 |
ting | +0.081 |
Mr | +0.080 |
ourselves | +0.079 |
Neg logit contributions | |
run | -0.043 |
igsaw | -0.041 |
block | -0.036 |
nail | -0.036 |
Half | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +7.98e-01 |
Pos logit contributions | |
Amen | +0.033 |
cle | +0.033 |
ting | +0.032 |
Say | +0.032 |
adays | +0.032 |
Neg logit contributions | |
run | -0.046 |
block | -0.046 |
nail | -0.042 |
pad | -0.042 |
foot | -0.040 |
Token | not |
Token ID | 407 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
Amen | +0.021 |
cle | +0.021 |
ting | +0.020 |
Mr | +0.019 |
123 | +0.019 |
Neg logit contributions | |
run | -0.022 |
igsaw | -0.021 |
block | -0.021 |
nail | -0.020 |
pad | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -8.41e-01 |
Pos logit contributions | |
run | +0.035 |
igsaw | +0.034 |
block | +0.031 |
ooter | +0.031 |
nail | +0.031 |
Neg logit contributions | |
Amen | -0.034 |
ting | -0.033 |
cle | -0.033 |
Mr | -0.032 |
Merry | -0.032 |
Token | eat |
Token ID | 4483 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
run | +0.021 |
block | +0.020 |
nail | +0.020 |
igsaw | +0.020 |
stack | +0.018 |
Neg logit contributions | |
ting | -0.024 |
Amen | -0.024 |
cle | -0.023 |
sets | -0.023 |
123 | -0.022 |
Token | broccoli |
Token ID | 44653 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Amen | +0.025 |
cle | +0.024 |
ting | +0.022 |
Miss | +0.022 |
123 | +0.022 |
Neg logit contributions | |
run | -0.021 |
block | -0.021 |
nail | -0.020 |
igsaw | -0.020 |
pad | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
Amen | +0.061 |
cle | +0.058 |
Mr | +0.051 |
Merry | +0.051 |
Miss | +0.051 |
Neg logit contributions | |
block | -0.062 |
run | -0.061 |
nail | -0.059 |
pad | -0.059 |
igsaw | -0.059 |
Token | Bro |
Token ID | 2806 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.018 |
ting | +0.018 |
Mr | +0.018 |
Merry | +0.017 |
Neg logit contributions | |
run | -0.021 |
igsaw | -0.021 |
nail | -0.019 |
block | -0.019 |
ooter | -0.019 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
Amen | +0.084 |
ting | +0.079 |
Miss | +0.076 |
Say | +0.075 |
adays | +0.073 |
Neg logit contributions | |
block | -0.069 |
run | -0.068 |
pad | -0.067 |
favorite | -0.064 |
fault | -0.064 |
Token | was |
Token ID | 373 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Amen | +0.182 |
cle | +0.176 |
Miss | +0.165 |
Santa | +0.161 |
Merry | +0.161 |
Neg logit contributions | |
block | -0.141 |
nail | -0.130 |
run | -0.123 |
pad | -0.121 |
pattern | -0.121 |
Token | green |
Token ID | 4077 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Amen | +0.011 |
Mr | +0.010 |
They | +0.010 |
ting | +0.010 |
cle | +0.010 |
Neg logit contributions | |
igsaw | -0.011 |
run | -0.010 |
ooter | -0.010 |
inter | -0.009 |
nail | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
block | +0.044 |
run | +0.041 |
nail | +0.040 |
pad | +0.039 |
igsaw | +0.038 |
Neg logit contributions | |
Amen | -0.055 |
cle | -0.055 |
Merry | -0.051 |
Miss | -0.050 |
Mr | -0.050 |
Token | bitter |
Token ID | 12922 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
run | +0.004 |
igsaw | +0.004 |
block | +0.004 |
nail | +0.004 |
pad | +0.004 |
Neg logit contributions | |
Amen | -0.007 |
ting | -0.007 |
cle | -0.007 |
123 | -0.007 |
Miss | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
run | +0.001 |
block | +0.001 |
nail | +0.001 |
pad | +0.001 |
inter | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
cle | -0.001 |
Santa | -0.001 |
Miss | -0.001 |
Mr | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
run | +0.013 |
igsaw | +0.012 |
block | +0.012 |
nail | +0.012 |
Half | +0.011 |
Neg logit contributions | |
Amen | -0.017 |
cle | -0.015 |
ting | -0.015 |
bless | -0.015 |
123 | -0.015 |
Token | famous |
Token ID | 5863 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.018 |
ting | +0.018 |
Mr | +0.018 |
Merry | +0.017 |
Neg logit contributions | |
run | -0.015 |
igsaw | -0.014 |
block | -0.013 |
nail | -0.013 |
pad | -0.013 |
Token | chef |
Token ID | 21221 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
igsaw | +0.037 |
block | +0.035 |
nail | +0.035 |
run | +0.035 |
pad | +0.032 |
Neg logit contributions | |
Amen | -0.049 |
cle | -0.047 |
ting | -0.047 |
They | -0.046 |
Mr | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
Amen | +0.053 |
ourselves | +0.050 |
cle | +0.050 |
ting | +0.049 |
Mr | +0.049 |
Neg logit contributions | |
block | -0.039 |
nail | -0.037 |
run | -0.037 |
pad | -0.036 |
stack | -0.033 |
Token | making |
Token ID | 1642 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
run | +0.011 |
igsaw | +0.011 |
nail | +0.010 |
block | +0.010 |
pad | +0.010 |
Neg logit contributions | |
Amen | -0.011 |
cle | -0.010 |
ting | -0.010 |
Mr | -0.010 |
Merry | -0.010 |
Token | las |
Token ID | 39990 |
Feature activation | +5.55e+00 |
Pos logit contributions | |
Amen | +0.032 |
cle | +0.032 |
ting | +0.031 |
Mr | +0.030 |
Merry | +0.030 |
Neg logit contributions | |
run | -0.028 |
igsaw | -0.026 |
block | -0.025 |
nail | -0.025 |
pad | -0.024 |
Token | agna |
Token ID | 48669 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Amen | +0.144 |
ting | +0.135 |
cle | +0.135 |
Mr | +0.130 |
Merry | +0.130 |
Neg logit contributions | |
run | -0.155 |
igsaw | -0.154 |
block | -0.146 |
ooter | -0.141 |
nail | -0.140 |
Token | . |
Token ID | 13 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
Amen | +0.078 |
cle | +0.075 |
Merry | +0.071 |
Miss | +0.071 |
Mr | +0.071 |
Neg logit contributions | |
run | -0.089 |
block | -0.087 |
igsaw | -0.085 |
nail | -0.083 |
stack | -0.079 |
Token | That |
Token ID | 1320 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
Amen | +0.011 |
ting | +0.011 |
cle | +0.011 |
Mr | +0.011 |
Merry | +0.010 |
Neg logit contributions | |
run | -0.011 |
igsaw | -0.011 |
nail | -0.011 |
block | -0.010 |
pad | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
Amen | +0.001 |
ting | +0.001 |
cle | +0.001 |
ourselves | +0.001 |
Miss | +0.001 |
Neg logit contributions | |
block | -0.001 |
nail | -0.001 |
igsaw | -0.001 |
run | -0.001 |
pad | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Amen | +0.007 |
cle | +0.007 |
ting | +0.007 |
Mr | +0.006 |
sets | +0.006 |
Neg logit contributions | |
run | -0.005 |
igsaw | -0.005 |
block | -0.005 |
nail | -0.005 |
Half | -0.005 |
Token | honey |
Token ID | 12498 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Amen | +0.007 |
cle | +0.006 |
ting | +0.006 |
123 | +0.006 |
Miss | +0.006 |
Neg logit contributions | |
run | -0.005 |
block | -0.004 |
nail | -0.004 |
igsaw | -0.004 |
Half | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Amen | +0.083 |
cle | +0.075 |
Miss | +0.074 |
Say | +0.073 |
Merry | +0.072 |
Neg logit contributions | |
run | -0.073 |
pad | -0.071 |
block | -0.070 |
nail | -0.069 |
inter | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
Amen | +0.015 |
cle | +0.015 |
ting | +0.015 |
Mr | +0.015 |
Merry | +0.014 |
Neg logit contributions | |
run | -0.013 |
igsaw | -0.012 |
block | -0.011 |
nail | -0.011 |
pad | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
Amen | +0.010 |
cle | +0.010 |
They | +0.009 |
Mr | +0.009 |
Miss | +0.009 |
Neg logit contributions | |
run | -0.012 |
igsaw | -0.012 |
nail | -0.012 |
inter | -0.011 |
pad | -0.011 |
Token | " |
Token ID | 1 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Amen | +0.017 |
cle | +0.017 |
ting | +0.017 |
Merry | +0.016 |
sets | +0.016 |
Neg logit contributions | |
run | -0.019 |
igsaw | -0.019 |
block | -0.018 |
nail | -0.018 |
pad | -0.017 |
Token | Dr |
Token ID | 6187 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
Amen | +0.004 |
ourselves | +0.004 |
ting | +0.004 |
adays | +0.004 |
cle | +0.004 |
Neg logit contributions | |
block | -0.007 |
run | -0.007 |
nail | -0.007 |
igsaw | -0.007 |
pad | -0.007 |
Token | ink |
Token ID | 676 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
ting | +0.145 |
Amen | +0.144 |
Say | +0.134 |
Merry | +0.133 |
Miss | +0.131 |
Neg logit contributions | |
block | -0.144 |
nail | -0.142 |
igsaw | -0.137 |
atter | -0.135 |
une | -0.134 |
Token | this |
Token ID | 428 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
block | +0.028 |
inter | +0.028 |
nail | +0.028 |
ooter | +0.028 |
run | +0.028 |
Neg logit contributions | |
Say | -0.019 |
Miss | -0.019 |
Mr | -0.019 |
Amen | -0.019 |
Merry | -0.018 |
Token | James |
Token ID | 3700 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
block | +0.004 |
nail | +0.004 |
run | +0.004 |
inter | +0.004 |
igsaw | +0.004 |
Neg logit contributions | |
Amen | -0.006 |
cle | -0.006 |
ting | -0.006 |
Mr | -0.006 |
Miss | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
ting | +0.050 |
Say | +0.049 |
Miss | +0.049 |
Amen | +0.048 |
Mr | +0.047 |
Neg logit contributions | |
block | -0.056 |
run | -0.055 |
pad | -0.052 |
nail | -0.050 |
atter | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
run | +0.015 |
igsaw | +0.014 |
block | +0.014 |
nail | +0.014 |
ooter | +0.013 |
Neg logit contributions | |
Amen | -0.012 |
cle | -0.012 |
ting | -0.011 |
sets | -0.011 |
123 | -0.011 |
Token | try |
Token ID | 1949 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
block | +0.019 |
nail | +0.018 |
igsaw | +0.018 |
run | +0.018 |
stack | +0.017 |
Neg logit contributions | |
ting | -0.027 |
sets | -0.026 |
Amen | -0.025 |
cle | -0.025 |
we | -0.024 |
Token | new |
Token ID | 649 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Amen | +0.022 |
cle | +0.021 |
ting | +0.020 |
Dear | +0.019 |
MacDonald | +0.019 |
Neg logit contributions | |
run | -0.019 |
igsaw | -0.018 |
block | -0.018 |
nail | -0.018 |
pad | -0.017 |
Token | things |
Token ID | 1243 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
run | +0.006 |
block | +0.006 |
nail | +0.006 |
igsaw | +0.006 |
favorite | +0.005 |
Neg logit contributions | |
Amen | -0.008 |
cle | -0.008 |
ting | -0.008 |
Claus | -0.008 |
Miss | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Amen | +0.053 |
cle | +0.049 |
ting | +0.045 |
sets | +0.044 |
Say | +0.044 |
Neg logit contributions | |
run | -0.058 |
block | -0.055 |
igsaw | -0.055 |
nail | -0.054 |
pad | -0.052 |
Token | Bro |
Token ID | 2806 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
cle | +0.027 |
ting | +0.027 |
Amen | +0.026 |
sets | +0.026 |
pa | +0.025 |
Neg logit contributions | |
run | -0.031 |
igsaw | -0.029 |
block | -0.028 |
Half | -0.028 |
nail | -0.028 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.52e+00 |
Pos logit contributions | |
Amen | +0.082 |
ting | +0.079 |
Say | +0.079 |
Miss | +0.077 |
Mr | +0.077 |
Neg logit contributions | |
run | -0.068 |
block | -0.067 |
pad | -0.066 |
igsaw | -0.064 |
inter | -0.063 |
Token | is |
Token ID | 318 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
Amen | +0.162 |
cle | +0.160 |
Miss | +0.144 |
Santa | +0.142 |
Mr | +0.141 |
Neg logit contributions | |
block | -0.153 |
nail | -0.138 |
run | -0.134 |
pad | -0.132 |
pattern | -0.127 |
Token | not |
Token ID | 407 |
Feature activation | +7.22e-01 |
Pos logit contributions | |
Amen | +0.024 |
cle | +0.024 |
ting | +0.023 |
Mr | +0.023 |
Merry | +0.022 |
Neg logit contributions | |
run | -0.022 |
igsaw | -0.021 |
block | -0.020 |
nail | -0.020 |
ooter | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Amen | +0.020 |
cle | +0.019 |
ting | +0.019 |
Mr | +0.019 |
They | +0.018 |
Neg logit contributions | |
run | -0.019 |
igsaw | -0.018 |
block | -0.017 |
nail | -0.017 |
ooter | -0.017 |
Token | bad |
Token ID | 2089 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
run | +0.045 |
block | +0.043 |
igsaw | +0.043 |
nail | +0.043 |
pad | +0.040 |
Neg logit contributions | |
cle | -0.041 |
Amen | -0.041 |
ting | -0.038 |
Santa | -0.037 |
Mr | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
run | +0.017 |
block | +0.016 |
pad | +0.016 |
nail | +0.016 |
foot | +0.015 |
Neg logit contributions | |
cle | -0.019 |
Amen | -0.019 |
Mr | -0.017 |
Santa | -0.017 |
Ho | -0.016 |
Token | water |
Token ID | 1660 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
block | +0.012 |
nail | +0.011 |
run | +0.011 |
pattern | +0.011 |
igsaw | +0.011 |
Neg logit contributions | |
cle | -0.023 |
ting | -0.022 |
Amen | -0.022 |
yer | -0.022 |
Claus | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +6.64e-01 |
Pos logit contributions | |
Amen | +0.030 |
cle | +0.029 |
Mr | +0.026 |
ting | +0.026 |
Merry | +0.026 |
Neg logit contributions | |
run | -0.035 |
block | -0.034 |
nail | -0.032 |
igsaw | -0.032 |
pad | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
Amen | +0.017 |
cle | +0.017 |
ting | +0.017 |
Mr | +0.016 |
Merry | +0.016 |
Neg logit contributions | |
run | -0.018 |
igsaw | -0.018 |
nail | -0.017 |
block | -0.017 |
ooter | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +9.23e-01 |
Pos logit contributions | |
Amen | +0.021 |
cle | +0.021 |
ting | +0.020 |
Mr | +0.019 |
Merry | +0.019 |
Neg logit contributions | |
run | -0.019 |
igsaw | -0.018 |
block | -0.017 |
nail | -0.017 |
pad | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
Amen | +0.023 |
sets | +0.022 |
ting | +0.022 |
amen | +0.021 |
pa | +0.021 |
Neg logit contributions | |
run | -0.027 |
block | -0.026 |
igsaw | -0.026 |
nail | -0.026 |
Half | -0.025 |
Token | Dr |
Token ID | 6187 |
Feature activation | +5.50e+00 |
Pos logit contributions | |
Amen | +0.006 |
ting | +0.006 |
cle | +0.006 |
123 | +0.006 |
adays | +0.006 |
Neg logit contributions | |
block | -0.008 |
run | -0.008 |
igsaw | -0.008 |
nail | -0.008 |
Half | -0.007 |
Token | ink |
Token ID | 676 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
ting | +0.158 |
Amen | +0.150 |
sets | +0.146 |
Merry | +0.145 |
Jesus | +0.137 |
Neg logit contributions | |
block | -0.137 |
nail | -0.128 |
foot | -0.121 |
circle | -0.117 |
atter | -0.117 |
Token | some |
Token ID | 617 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
block | +0.025 |
run | +0.025 |
inter | +0.025 |
ooter | +0.024 |
pad | +0.024 |
Neg logit contributions | |
Amen | -0.019 |
Say | -0.018 |
Miss | -0.018 |
Mr | -0.018 |
Merry | -0.018 |
Token | water |
Token ID | 1660 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
cle | +0.024 |
Amen | +0.024 |
ting | +0.023 |
sets | +0.023 |
Miss | +0.023 |
Neg logit contributions | |
block | -0.014 |
run | -0.014 |
nail | -0.013 |
igsaw | -0.012 |
bucket | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
Amen | +0.025 |
cle | +0.024 |
Miss | +0.023 |
ting | +0.022 |
Mr | +0.022 |
Neg logit contributions | |
block | -0.027 |
run | -0.027 |
nail | -0.025 |
igsaw | -0.025 |
inter | -0.024 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
run | +0.005 |
igsaw | +0.005 |
ooter | +0.004 |
block | +0.004 |
nail | +0.004 |
Neg logit contributions | |
Amen | -0.004 |
Mr | -0.004 |
cle | -0.004 |
ting | -0.004 |
Merry | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
run | +0.038 |
block | +0.035 |
nail | +0.035 |
pad | +0.034 |
igsaw | +0.034 |
Neg logit contributions | |
Amen | -0.031 |
cle | -0.028 |
ting | -0.026 |
Mr | -0.026 |
Miss | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.019 |
ting | +0.018 |
Mr | +0.018 |
They | +0.018 |
Neg logit contributions | |
run | -0.020 |
igsaw | -0.020 |
block | -0.019 |
nail | -0.018 |
ooter | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
Amen | +0.013 |
cle | +0.012 |
ting | +0.012 |
Mr | +0.012 |
They | +0.012 |
Neg logit contributions | |
run | -0.013 |
igsaw | -0.012 |
block | -0.012 |
nail | -0.012 |
pad | -0.011 |
Token | " |
Token ID | 1 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
Amen | +0.015 |
ting | +0.015 |
sets | +0.014 |
cle | +0.014 |
Merry | +0.013 |
Neg logit contributions | |
run | -0.021 |
igsaw | -0.021 |
nail | -0.020 |
block | -0.020 |
pad | -0.020 |
Token | Bro |
Token ID | 15783 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
run | +0.001 |
igsaw | +0.001 |
block | +0.001 |
nail | +0.001 |
Half | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
ting | -0.001 |
cle | -0.001 |
Merry | -0.001 |
sets | -0.001 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Amen | +0.040 |
cle | +0.038 |
ting | +0.038 |
Mr | +0.037 |
Merry | +0.036 |
Neg logit contributions | |
run | -0.042 |
igsaw | -0.040 |
block | -0.038 |
nail | -0.038 |
pad | -0.037 |
Token | is |
Token ID | 318 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
Amen | +0.158 |
cle | +0.150 |
Miss | +0.149 |
ting | +0.145 |
Santa | +0.144 |
Neg logit contributions | |
block | -0.153 |
nail | -0.140 |
run | -0.134 |
stack | -0.129 |
igsaw | -0.127 |
Token | not |
Token ID | 407 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
Amen | +0.023 |
cle | +0.022 |
Mr | +0.022 |
ting | +0.022 |
They | +0.021 |
Neg logit contributions | |
run | -0.023 |
igsaw | -0.023 |
ooter | -0.021 |
block | -0.020 |
nail | -0.020 |
Token | y |
Token ID | 331 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.019 |
ting | +0.018 |
Mr | +0.018 |
Merry | +0.017 |
Neg logit contributions | |
run | -0.017 |
igsaw | -0.017 |
block | -0.016 |
nail | -0.016 |
ooter | -0.015 |
Token | ucky |
Token ID | 5309 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
run | +0.025 |
igsaw | +0.024 |
block | +0.023 |
nail | +0.022 |
inter | +0.021 |
Neg logit contributions | |
Amen | -0.027 |
cle | -0.026 |
ting | -0.026 |
Mr | -0.025 |
Merry | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
run | +0.036 |
block | +0.036 |
nail | +0.035 |
pad | +0.035 |
igsaw | +0.034 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.031 |
Santa | -0.028 |
Miss | -0.028 |
Merry | -0.028 |
Token | bunny |
Token ID | 44915 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Amen | +0.024 |
cle | +0.024 |
Mr | +0.022 |
Merry | +0.022 |
adays | +0.022 |
Neg logit contributions | |
block | -0.016 |
nail | -0.016 |
run | -0.015 |
igsaw | -0.014 |
ooter | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +7.93e-01 |
Pos logit contributions | |
cle | +0.033 |
Amen | +0.032 |
adays | +0.030 |
Merry | +0.030 |
123 | +0.029 |
Neg logit contributions | |
block | -0.038 |
nail | -0.037 |
run | -0.037 |
pad | -0.036 |
igsaw | -0.034 |
Token | She |
Token ID | 1375 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Amen | +0.020 |
cle | +0.019 |
ting | +0.019 |
Merry | +0.019 |
Mr | +0.019 |
Neg logit contributions | |
run | -0.023 |
igsaw | -0.022 |
nail | -0.021 |
block | -0.021 |
ooter | -0.020 |
Token | called |
Token ID | 1444 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Amen | +0.031 |
ting | +0.031 |
cle | +0.030 |
sets | +0.030 |
ourselves | +0.029 |
Neg logit contributions | |
block | -0.028 |
run | -0.027 |
nail | -0.026 |
pad | -0.025 |
pattern | -0.024 |
Token | him |
Token ID | 683 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
cle | +0.005 |
Amen | +0.004 |
They | +0.004 |
Miss | +0.004 |
ting | +0.004 |
Neg logit contributions | |
run | -0.005 |
igsaw | -0.005 |
block | -0.005 |
nail | -0.005 |
Half | -0.005 |
Token | Ho |
Token ID | 9544 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
Amen | +0.047 |
cle | +0.045 |
adays | +0.042 |
ting | +0.042 |
narrative | +0.041 |
Neg logit contributions | |
run | -0.043 |
block | -0.041 |
pad | -0.039 |
favorite | -0.038 |
Half | -0.038 |
Token | ppy |
Token ID | 14097 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Amen | +0.157 |
Merry | +0.144 |
ting | +0.144 |
Say | +0.144 |
adays | +0.144 |
Neg logit contributions | |
run | -0.146 |
pad | -0.145 |
block | -0.134 |
igsaw | -0.126 |
inter | -0.123 |
Token | and |
Token ID | 290 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Amen | +0.060 |
cle | +0.057 |
Mr | +0.053 |
ting | +0.052 |
Say | +0.052 |
Neg logit contributions | |
run | -0.057 |
pad | -0.056 |
block | -0.055 |
igsaw | -0.051 |
nail | -0.050 |
Token | he |
Token ID | 339 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
ting | +0.008 |
cle | +0.008 |
ourselves | +0.008 |
Amen | +0.008 |
sets | +0.008 |
Neg logit contributions | |
run | -0.007 |
block | -0.006 |
nail | -0.006 |
favorite | -0.006 |
Half | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +5.84e-02 |
Pos logit contributions | |
Amen | +0.070 |
cle | +0.069 |
ting | +0.068 |
ourselves | +0.066 |
sets | +0.065 |
Neg logit contributions | |
run | -0.060 |
block | -0.059 |
nail | -0.054 |
pad | -0.054 |
favorite | -0.052 |
Token | very |
Token ID | 845 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
cle | +0.002 |
Amen | +0.002 |
ting | +0.002 |
adays | +0.002 |
sets | +0.002 |
Neg logit contributions | |
run | -0.001 |
block | -0.001 |
nail | -0.001 |
Half | -0.001 |
igsaw | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
run | +0.051 |
block | +0.046 |
pad | +0.045 |
igsaw | +0.045 |
ooter | +0.044 |
Neg logit contributions | |
Amen | -0.041 |
cle | -0.037 |
ting | -0.035 |
Mr | -0.035 |
sets | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Amen | +0.016 |
cle | +0.015 |
ting | +0.015 |
Mr | +0.014 |
sets | +0.014 |
Neg logit contributions | |
run | -0.018 |
igsaw | -0.017 |
block | -0.016 |
nail | -0.016 |
pad | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
Amen | +0.010 |
cle | +0.010 |
Mr | +0.010 |
They | +0.010 |
ting | +0.009 |
Neg logit contributions | |
run | -0.011 |
igsaw | -0.011 |
nail | -0.010 |
block | -0.010 |
pad | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
ting | +0.015 |
sets | +0.014 |
Amen | +0.014 |
amen | +0.013 |
Merry | +0.013 |
Neg logit contributions | |
run | -0.020 |
block | -0.020 |
igsaw | -0.020 |
nail | -0.020 |
pad | -0.019 |
Token | Bro |
Token ID | 15783 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
run | +0.003 |
block | +0.003 |
nail | +0.003 |
igsaw | +0.003 |
Half | +0.003 |
Neg logit contributions | |
Amen | -0.002 |
ting | -0.001 |
cle | -0.001 |
sets | -0.001 |
adays | -0.001 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Amen | +0.037 |
ting | +0.037 |
cle | +0.035 |
Mr | +0.035 |
sets | +0.035 |
Neg logit contributions | |
run | -0.033 |
igsaw | -0.031 |
block | -0.031 |
nail | -0.030 |
pad | -0.030 |
Token | is |
Token ID | 318 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
Amen | +0.155 |
Miss | +0.150 |
ting | +0.150 |
cle | +0.150 |
Say | +0.145 |
Neg logit contributions | |
block | -0.150 |
nail | -0.134 |
run | -0.128 |
stack | -0.125 |
pad | -0.121 |
Token | what |
Token ID | 644 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.019 |
Mr | +0.018 |
ting | +0.018 |
Merry | +0.018 |
Neg logit contributions | |
run | -0.019 |
igsaw | -0.019 |
block | -0.017 |
nail | -0.017 |
ooter | -0.017 |
Token | we |
Token ID | 356 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
Amen | +0.044 |
cle | +0.043 |
ting | +0.043 |
Mr | +0.039 |
Santa | +0.038 |
Neg logit contributions | |
run | -0.080 |
block | -0.077 |
nail | -0.076 |
igsaw | -0.075 |
pad | -0.071 |
Token | have |
Token ID | 423 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
run | +0.027 |
igsaw | +0.025 |
block | +0.024 |
nail | +0.024 |
pad | +0.023 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.033 |
ting | -0.033 |
Mr | -0.031 |
123 | -0.031 |
Token | for |
Token ID | 329 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
run | +0.003 |
block | +0.003 |
pad | +0.003 |
favorite | +0.003 |
nail | +0.003 |
Neg logit contributions | |
Amen | -0.003 |
ting | -0.003 |
cle | -0.003 |
Mr | -0.003 |
sets | -0.003 |
Token | bunny |
Token ID | 44915 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.018 |
Merry | +0.017 |
Mr | +0.017 |
adays | +0.017 |
Neg logit contributions | |
nail | -0.014 |
block | -0.014 |
run | -0.014 |
pad | -0.013 |
ooter | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
cle | +0.027 |
Amen | +0.027 |
adays | +0.025 |
Merry | +0.025 |
Mr | +0.024 |
Neg logit contributions | |
block | -0.030 |
nail | -0.030 |
run | -0.030 |
pad | -0.029 |
igsaw | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Amen | +0.016 |
God | +0.016 |
Merry | +0.015 |
Mr | +0.015 |
They | +0.015 |
Neg logit contributions | |
run | -0.026 |
ooter | -0.024 |
igsaw | -0.023 |
chie | -0.023 |
nail | -0.022 |
Token | named |
Token ID | 3706 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
Amen | +0.027 |
ting | +0.026 |
cle | +0.026 |
sets | +0.025 |
ourselves | +0.025 |
Neg logit contributions | |
run | -0.028 |
block | -0.027 |
nail | -0.027 |
pad | -0.026 |
igsaw | -0.026 |
Token | him |
Token ID | 683 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
run | +0.020 |
igsaw | +0.019 |
block | +0.019 |
nail | +0.018 |
Half | +0.018 |
Neg logit contributions | |
cle | -0.020 |
Amen | -0.018 |
They | -0.017 |
Miss | -0.017 |
Dear | -0.017 |
Token | Ho |
Token ID | 9544 |
Feature activation | +5.33e+00 |
Pos logit contributions | |
Amen | +0.043 |
cle | +0.040 |
ting | +0.038 |
ourselves | +0.037 |
adays | +0.037 |
Neg logit contributions | |
run | -0.048 |
block | -0.045 |
nail | -0.043 |
igsaw | -0.042 |
pad | -0.042 |
Token | ppy |
Token ID | 14097 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Amen | +0.138 |
Merry | +0.130 |
ting | +0.129 |
Say | +0.126 |
adays | +0.125 |
Neg logit contributions | |
run | -0.159 |
pad | -0.148 |
block | -0.144 |
igsaw | -0.142 |
nail | -0.139 |
Token | and |
Token ID | 290 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
Amen | +0.059 |
cle | +0.056 |
ourselves | +0.051 |
Say | +0.051 |
Merry | +0.051 |
Neg logit contributions | |
run | -0.056 |
block | -0.055 |
pad | -0.055 |
nail | -0.051 |
igsaw | -0.051 |
Token | took |
Token ID | 1718 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
run | +0.001 |
nail | +0.001 |
block | +0.001 |
favorite | +0.001 |
pad | +0.001 |
Neg logit contributions | |
cle | -0.002 |
Amen | -0.002 |
ourselves | -0.002 |
ting | -0.002 |
yer | -0.002 |
Token | him |
Token ID | 683 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
cle | +0.064 |
Amen | +0.061 |
sets | +0.055 |
works | +0.055 |
yer | +0.054 |
Neg logit contributions | |
run | -0.071 |
igsaw | -0.066 |
Half | -0.064 |
block | -0.063 |
favorite | -0.061 |
Token | everywhere |
Token ID | 8347 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
ting | +0.012 |
boys | +0.011 |
cle | +0.011 |
123 | +0.011 |
ourselves | +0.011 |
Neg logit contributions | |
igsaw | -0.012 |
run | -0.012 |
nail | -0.011 |
block | -0.011 |
inter | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
run | +0.015 |
igsaw | +0.014 |
nail | +0.014 |
block | +0.014 |
pad | +0.014 |
Neg logit contributions | |
Amen | -0.017 |
cle | -0.016 |
ting | -0.016 |
Mr | -0.015 |
sets | -0.015 |
Token | your |
Token ID | 534 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
igsaw | +0.031 |
block | +0.030 |
nail | +0.030 |
run | +0.029 |
Half | +0.027 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.032 |
ting | -0.031 |
MacDonald | -0.030 |
Miss | -0.030 |
Token | plate |
Token ID | 7480 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Amen | +0.008 |
cle | +0.008 |
ting | +0.007 |
Mr | +0.007 |
Merry | +0.007 |
Neg logit contributions | |
run | -0.006 |
igsaw | -0.005 |
block | -0.005 |
nail | -0.005 |
ooter | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
run | +0.043 |
block | +0.042 |
igsaw | +0.040 |
nail | +0.040 |
pad | +0.039 |
Neg logit contributions | |
Amen | -0.028 |
cle | -0.027 |
ting | -0.026 |
Mr | -0.025 |
Merry | -0.024 |
Token | Bro |
Token ID | 2806 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Amen | +0.025 |
cle | +0.025 |
ting | +0.024 |
sets | +0.024 |
Mr | +0.023 |
Neg logit contributions | |
run | -0.014 |
igsaw | -0.013 |
block | -0.013 |
nail | -0.012 |
Half | -0.012 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Amen | +0.075 |
ting | +0.075 |
Miss | +0.072 |
Say | +0.072 |
adays | +0.071 |
Neg logit contributions | |
block | -0.067 |
run | -0.067 |
inter | -0.063 |
pad | -0.063 |
igsaw | -0.062 |
Token | is |
Token ID | 318 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
Amen | +0.146 |
cle | +0.144 |
Miss | +0.136 |
Mr | +0.131 |
Santa | +0.131 |
Neg logit contributions | |
block | -0.156 |
nail | -0.143 |
run | -0.141 |
inter | -0.134 |
pad | -0.133 |
Token | not |
Token ID | 407 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
Amen | +0.020 |
cle | +0.020 |
ting | +0.019 |
Mr | +0.019 |
Merry | +0.019 |
Neg logit contributions | |
run | -0.018 |
igsaw | -0.017 |
block | -0.016 |
nail | -0.016 |
ooter | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Amen | +0.016 |
cle | +0.016 |
ting | +0.015 |
Mr | +0.015 |
Merry | +0.015 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.015 |
block | -0.014 |
nail | -0.014 |
ooter | -0.014 |
Token | bad |
Token ID | 2089 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
run | +0.046 |
block | +0.046 |
nail | +0.045 |
igsaw | +0.043 |
inter | +0.041 |
Neg logit contributions | |
cle | -0.043 |
Amen | -0.043 |
ting | -0.039 |
Miss | -0.039 |
Santa | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
run | +0.023 |
block | +0.023 |
nail | +0.022 |
pad | +0.022 |
fault | +0.021 |
Neg logit contributions | |
cle | -0.024 |
Amen | -0.024 |
Mr | -0.022 |
Miss | -0.022 |
Santa | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
run | +0.001 |
nail | +0.001 |
block | +0.001 |
igsaw | +0.001 |
pad | +0.001 |
Neg logit contributions | |
cle | -0.001 |
Amen | -0.001 |
ting | -0.001 |
Mr | -0.001 |
Miss | -0.001 |
Token | corn |
Token ID | 11676 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
cle | +0.019 |
Amen | +0.019 |
adays | +0.019 |
es | +0.017 |
fed | +0.017 |
Neg logit contributions | |
pad | -0.019 |
favorite | -0.018 |
nail | -0.017 |
block | -0.017 |
rake | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Amen | +0.050 |
cle | +0.048 |
Miss | +0.047 |
Mr | +0.046 |
Santa | +0.044 |
Neg logit contributions | |
block | -0.052 |
run | -0.051 |
nail | -0.050 |
pad | -0.049 |
stack | -0.048 |
Token | She |
Token ID | 1375 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
ting | +0.022 |
Merry | +0.021 |
Mr | +0.021 |
Amen | +0.021 |
They | +0.020 |
Neg logit contributions | |
igsaw | -0.034 |
run | -0.033 |
block | -0.031 |
nail | -0.031 |
ooter | -0.030 |
Token | brought |
Token ID | 3181 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
cle | +0.019 |
Amen | +0.019 |
Mr | +0.018 |
ting | +0.018 |
They | +0.018 |
Neg logit contributions | |
igsaw | -0.026 |
run | -0.025 |
nail | -0.023 |
ooter | -0.023 |
inter | -0.023 |
Token | Ho |
Token ID | 9544 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
Amen | +0.023 |
cle | +0.023 |
ting | +0.021 |
Mr | +0.020 |
123 | +0.020 |
Neg logit contributions | |
run | -0.030 |
igsaw | -0.029 |
block | -0.028 |
nail | -0.028 |
pad | -0.027 |
Token | ppy |
Token ID | 14097 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Amen | +0.148 |
Merry | +0.136 |
Say | +0.135 |
narrative | +0.135 |
adays | +0.134 |
Neg logit contributions | |
run | -0.154 |
pad | -0.140 |
inter | -0.129 |
block | -0.129 |
igsaw | -0.128 |
Token | with |
Token ID | 351 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
They | +0.032 |
ting | +0.032 |
Amen | +0.031 |
cle | +0.031 |
ourselves | +0.031 |
Neg logit contributions | |
igsaw | -0.041 |
run | -0.040 |
nail | -0.037 |
inter | -0.037 |
ooter | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
Amen | +0.021 |
cle | +0.021 |
ting | +0.019 |
Miss | +0.019 |
123 | +0.019 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.023 |
block | -0.022 |
nail | -0.022 |
pad | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
igsaw | +0.009 |
run | +0.009 |
nail | +0.008 |
Half | +0.008 |
ooter | +0.008 |
Neg logit contributions | |
Amen | -0.011 |
cle | -0.011 |
ting | -0.011 |
Mr | -0.010 |
bless | -0.010 |
Token | held |
Token ID | 2714 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Amen | +0.013 |
cle | +0.013 |
ourselves | +0.012 |
ting | +0.012 |
Miss | +0.012 |
Neg logit contributions | |
run | -0.012 |
block | -0.010 |
nail | -0.010 |
favorite | -0.010 |
Half | -0.010 |
Token | says |
Token ID | 1139 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
cle | +0.007 |
Amen | +0.007 |
ting | +0.006 |
Mr | +0.006 |
Miss | +0.006 |
Neg logit contributions | |
run | -0.006 |
block | -0.005 |
igsaw | -0.005 |
nail | -0.005 |
Half | -0.005 |
Token | : |
Token ID | 25 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
run | +0.009 |
block | +0.008 |
nail | +0.008 |
igsaw | +0.008 |
Half | +0.008 |
Neg logit contributions | |
cle | -0.009 |
ting | -0.009 |
Amen | -0.009 |
Mr | -0.009 |
sets | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +7.68e-02 |
Pos logit contributions | |
run | +0.024 |
igsaw | +0.023 |
block | +0.022 |
nail | +0.021 |
pad | +0.021 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.034 |
ting | -0.033 |
Mr | -0.032 |
Merry | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
ting | +0.002 |
Amen | +0.002 |
cle | +0.002 |
sets | +0.002 |
Merry | +0.002 |
Neg logit contributions | |
run | -0.002 |
igsaw | -0.002 |
block | -0.002 |
nail | -0.002 |
Half | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ting | +0.007 |
Amen | +0.007 |
sets | +0.006 |
cle | +0.006 |
amen | +0.006 |
Neg logit contributions | |
run | -0.010 |
igsaw | -0.010 |
block | -0.010 |
nail | -0.009 |
Half | -0.009 |
Token | Dr |
Token ID | 6187 |
Feature activation | +5.32e+00 |
Pos logit contributions | |
block | +0.010 |
run | +0.010 |
igsaw | +0.010 |
nail | +0.010 |
Half | +0.010 |
Neg logit contributions | |
Amen | -0.007 |
cle | -0.007 |
ting | -0.007 |
sets | -0.007 |
adays | -0.007 |
Token | ink |
Token ID | 676 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Amen | +0.146 |
ting | +0.144 |
sets | +0.133 |
Rudolph | +0.130 |
Merry | +0.129 |
Neg logit contributions | |
block | -0.138 |
nail | -0.128 |
igsaw | -0.126 |
foot | -0.125 |
circle | -0.125 |
Token | some |
Token ID | 617 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
block | +0.032 |
run | +0.032 |
igsaw | +0.031 |
inter | +0.031 |
ooter | +0.031 |
Neg logit contributions | |
Amen | -0.032 |
Mr | -0.031 |
Say | -0.030 |
ting | -0.029 |
cle | -0.029 |
Token | water |
Token ID | 1660 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Amen | +0.018 |
cle | +0.018 |
ting | +0.017 |
sets | +0.016 |
Mr | +0.016 |
Neg logit contributions | |
run | -0.011 |
block | -0.011 |
nail | -0.011 |
igsaw | -0.010 |
inter | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Amen | +0.016 |
cle | +0.015 |
Mr | +0.014 |
Miss | +0.014 |
ting | +0.014 |
Neg logit contributions | |
run | -0.013 |
block | -0.013 |
igsaw | -0.012 |
nail | -0.012 |
inter | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
run | +0.004 |
block | +0.004 |
igsaw | +0.004 |
Half | +0.004 |
nail | +0.004 |
Neg logit contributions | |
cle | -0.007 |
Amen | -0.006 |
ting | -0.006 |
sets | -0.006 |
Mr | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
Amen | +0.071 |
cle | +0.065 |
adays | +0.060 |
Mr | +0.060 |
Say | +0.059 |
Neg logit contributions | |
block | -0.068 |
pad | -0.064 |
run | -0.063 |
favorite | -0.060 |
nail | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Amen | +0.018 |
cle | +0.018 |
ting | +0.018 |
Mr | +0.017 |
Merry | +0.017 |
Neg logit contributions | |
run | -0.023 |
igsaw | -0.022 |
block | -0.021 |
nail | -0.021 |
pad | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Amen | +0.011 |
ting | +0.011 |
cle | +0.011 |
Mr | +0.011 |
sets | +0.011 |
Neg logit contributions | |
run | -0.010 |
igsaw | -0.009 |
block | -0.009 |
nail | -0.009 |
pad | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
ting | +0.015 |
sets | +0.015 |
Amen | +0.014 |
pa | +0.013 |
Merry | +0.013 |
Neg logit contributions | |
block | -0.020 |
run | -0.019 |
nail | -0.019 |
Half | -0.019 |
pad | -0.019 |
Token | Bro |
Token ID | 15783 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
run | +0.002 |
igsaw | +0.001 |
block | +0.001 |
nail | +0.001 |
Half | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
ting | -0.001 |
cle | -0.001 |
sets | -0.001 |
Merry | -0.001 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
Amen | +0.032 |
cle | +0.031 |
ting | +0.031 |
Mr | +0.030 |
Merry | +0.029 |
Neg logit contributions | |
run | -0.041 |
igsaw | -0.039 |
block | -0.038 |
nail | -0.038 |
pad | -0.037 |
Token | is |
Token ID | 318 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
Amen | +0.157 |
cle | +0.156 |
Miss | +0.153 |
ting | +0.151 |
Santa | +0.148 |
Neg logit contributions | |
block | -0.147 |
nail | -0.131 |
stack | -0.124 |
run | -0.124 |
pattern | -0.121 |
Token | not |
Token ID | 407 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
Amen | +0.025 |
cle | +0.024 |
ting | +0.024 |
Mr | +0.023 |
Merry | +0.023 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.023 |
block | -0.021 |
nail | -0.021 |
ooter | -0.021 |
Token | our |
Token ID | 674 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
Amen | +0.016 |
cle | +0.016 |
ting | +0.015 |
Mr | +0.015 |
Merry | +0.015 |
Neg logit contributions | |
run | -0.013 |
igsaw | -0.013 |
block | -0.012 |
nail | -0.012 |
pad | -0.011 |
Token | friend |
Token ID | 1545 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
Amen | +0.025 |
cle | +0.024 |
ting | +0.024 |
Mr | +0.023 |
Merry | +0.023 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.015 |
block | -0.015 |
nail | -0.015 |
pad | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
run | +0.033 |
block | +0.031 |
pad | +0.030 |
nail | +0.030 |
igsaw | +0.029 |
Neg logit contributions | |
Amen | -0.019 |
cle | -0.018 |
ting | -0.018 |
Santa | -0.017 |
Mr | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
Amen | +0.105 |
ting | +0.104 |
cle | +0.103 |
Miss | +0.102 |
Mr | +0.098 |
Neg logit contributions | |
block | -0.121 |
run | -0.118 |
igsaw | -0.113 |
pad | -0.113 |
favorite | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
cle | +0.012 |
ting | +0.011 |
Amen | +0.011 |
sets | +0.011 |
123 | +0.011 |
Neg logit contributions | |
run | -0.010 |
igsaw | -0.010 |
block | -0.009 |
pad | -0.009 |
nail | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Amen | +0.005 |
cle | +0.005 |
They | +0.005 |
Mr | +0.005 |
Santa | +0.004 |
Neg logit contributions | |
run | -0.005 |
igsaw | -0.005 |
nail | -0.005 |
ooter | -0.005 |
inter | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
Amen | +0.011 |
cle | +0.011 |
ting | +0.011 |
Mr | +0.010 |
They | +0.010 |
Neg logit contributions | |
run | -0.020 |
igsaw | -0.020 |
block | -0.019 |
nail | -0.019 |
pad | -0.018 |
Token | Bro |
Token ID | 15783 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Amen | +0.001 |
ting | +0.001 |
cle | +0.001 |
123 | +0.001 |
sets | +0.001 |
Neg logit contributions | |
run | -0.002 |
igsaw | -0.002 |
block | -0.002 |
nail | -0.002 |
pad | -0.002 |
Token | ccoli |
Token ID | 34544 |
Feature activation | +5.26e+00 |
Pos logit contributions | |
Amen | +0.028 |
ting | +0.028 |
cle | +0.027 |
Mr | +0.026 |
Miss | +0.026 |
Neg logit contributions | |
run | -0.030 |
igsaw | -0.029 |
block | -0.028 |
nail | -0.028 |
pad | -0.027 |
Token | is |
Token ID | 318 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
cle | +0.145 |
Miss | +0.144 |
ting | +0.142 |
Amen | +0.140 |
Merry | +0.135 |
Neg logit contributions | |
block | -0.151 |
nail | -0.133 |
run | -0.130 |
stack | -0.127 |
pad | -0.124 |
Token | y |
Token ID | 331 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Amen | +0.016 |
cle | +0.015 |
ting | +0.015 |
Mr | +0.015 |
Merry | +0.015 |
Neg logit contributions | |
run | -0.012 |
igsaw | -0.011 |
block | -0.011 |
nail | -0.011 |
pad | -0.010 |
Token | ucky |
Token ID | 5309 |
Feature activation | +9.16e-02 |
Pos logit contributions | |
igsaw | +0.008 |
run | +0.007 |
block | +0.007 |
nail | +0.007 |
inter | +0.007 |
Neg logit contributions | |
Amen | -0.008 |
cle | -0.008 |
ting | -0.007 |
Santa | -0.007 |
amen | -0.007 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
cle | +0.002 |
Amen | +0.002 |
Miss | +0.002 |
Say | +0.002 |
123 | +0.002 |
Neg logit contributions | |
block | -0.003 |
nail | -0.003 |
igsaw | -0.003 |
run | -0.003 |
pad | -0.003 |
Token | Ben |
Token ID | 3932 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
run | +0.028 |
block | +0.025 |
igsaw | +0.025 |
nail | +0.025 |
Half | +0.024 |
Neg logit contributions | |
Amen | -0.033 |
cle | -0.032 |
ting | -0.032 |
sets | -0.031 |
123 | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
Amen | +0.031 |
cle | +0.030 |
ting | +0.027 |
Merry | +0.027 |
Mr | +0.027 |
Neg logit contributions | |
run | -0.055 |
block | -0.051 |
igsaw | -0.050 |
nail | -0.050 |
pad | -0.050 |
Token | started |
Token ID | 2067 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
run | +0.008 |
nail | +0.008 |
block | +0.007 |
pad | +0.007 |
foot | +0.007 |
Neg logit contributions | |
Amen | -0.010 |
cle | -0.009 |
Merry | -0.009 |
sets | -0.009 |
123 | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
igsaw | +0.020 |
run | +0.017 |
pad | +0.017 |
block | +0.017 |
ooter | +0.017 |
Neg logit contributions | |
ting | -0.020 |
Amen | -0.020 |
They | -0.019 |
Mr | -0.019 |
cle | -0.019 |
Token | cry |
Token ID | 3960 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
run | +0.003 |
nail | +0.003 |
igsaw | +0.003 |
block | +0.003 |
ooter | +0.002 |
Neg logit contributions | |
cle | -0.004 |
Amen | -0.004 |
ting | -0.004 |
Merry | -0.004 |
Mr | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +9.24e-01 |
Pos logit contributions | |
cle | +0.060 |
Amen | +0.057 |
rob | +0.054 |
Mr | +0.054 |
Say | +0.054 |
Neg logit contributions | |
run | -0.059 |
nail | -0.052 |
block | -0.051 |
foot | -0.051 |
pad | -0.049 |
Token | Ho |
Token ID | 9544 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
Amen | +0.026 |
cle | +0.025 |
ting | +0.025 |
Mr | +0.024 |
Merry | +0.024 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.024 |
block | -0.022 |
nail | -0.022 |
ooter | -0.021 |
Token | ppy |
Token ID | 14097 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Amen | +0.143 |
Merry | +0.132 |
cle | +0.131 |
ting | +0.130 |
123 | +0.128 |
Neg logit contributions | |
run | -0.154 |
pad | -0.141 |
igsaw | -0.139 |
block | -0.136 |
nail | -0.135 |
Token | flew |
Token ID | 13112 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
cle | +0.038 |
Amen | +0.037 |
ourselves | +0.036 |
sets | +0.036 |
ting | +0.036 |
Neg logit contributions | |
block | -0.026 |
run | -0.026 |
pad | -0.025 |
nail | -0.025 |
foot | -0.023 |
Token | out |
Token ID | 503 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
igsaw | +0.008 |
run | +0.008 |
nail | +0.007 |
block | +0.007 |
ooter | +0.007 |
Neg logit contributions | |
ting | -0.006 |
Amen | -0.006 |
cle | -0.006 |
Mr | -0.006 |
They | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
Amen | +0.015 |
ting | +0.015 |
cle | +0.015 |
Mr | +0.014 |
They | +0.014 |
Neg logit contributions | |
run | -0.014 |
igsaw | -0.014 |
nail | -0.013 |
pad | -0.013 |
block | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
ting | +0.016 |
Mr | +0.016 |
Amen | +0.016 |
cle | +0.015 |
123 | +0.015 |
Neg logit contributions | |
run | -0.035 |
ooter | -0.035 |
inter | -0.034 |
igsaw | -0.034 |
pad | -0.034 |
Token | away |
Token ID | 1497 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
Amen | +0.011 |
cle | +0.011 |
Mr | +0.011 |
ting | +0.010 |
Merry | +0.010 |
Neg logit contributions | |
run | -0.011 |
igsaw | -0.010 |
block | -0.010 |
nail | -0.009 |
ooter | -0.009 |
Token | from |
Token ID | 422 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Amen | +0.028 |
cle | +0.026 |
Mr | +0.024 |
Say | +0.023 |
Dear | +0.023 |
Neg logit contributions | |
run | -0.025 |
igsaw | -0.024 |
block | -0.023 |
nail | -0.023 |
foot | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
Amen | +0.042 |
ting | +0.041 |
cle | +0.040 |
Merry | +0.038 |
Mr | +0.038 |
Neg logit contributions | |
run | -0.063 |
igsaw | -0.061 |
block | -0.057 |
nail | -0.057 |
ooter | -0.057 |
Token | traffic |
Token ID | 4979 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
Amen | +0.008 |
ting | +0.007 |
cle | +0.007 |
Mr | +0.007 |
123 | +0.007 |
Neg logit contributions | |
run | -0.006 |
igsaw | -0.006 |
nail | -0.005 |
pad | -0.005 |
block | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
run | +0.012 |
igsaw | +0.012 |
block | +0.012 |
nail | +0.012 |
pad | +0.011 |
Neg logit contributions | |
Amen | -0.008 |
cle | -0.008 |
Mr | -0.007 |
Merry | -0.007 |
ting | -0.007 |
Token | Ref |
Token ID | 6524 |
Feature activation | +5.25e+00 |
Pos logit contributions | |
Amen | +0.009 |
ting | +0.009 |
Merry | +0.009 |
cle | +0.009 |
adays | +0.009 |
Neg logit contributions | |
run | -0.014 |
block | -0.013 |
igsaw | -0.013 |
nail | -0.013 |
ooter | -0.012 |
Token | using |
Token ID | 3500 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
Amen | +0.134 |
cle | +0.126 |
Merry | +0.120 |
Mr | +0.119 |
ting | +0.119 |
Neg logit contributions | |
run | -0.155 |
igsaw | -0.146 |
block | -0.140 |
nail | -0.138 |
ooter | -0.138 |
Token | to |
Token ID | 284 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Amen | +0.022 |
cle | +0.021 |
Mr | +0.020 |
ting | +0.020 |
Santa | +0.019 |
Neg logit contributions | |
run | -0.022 |
igsaw | -0.021 |
nail | -0.020 |
block | -0.020 |
pad | -0.019 |
Token | go |
Token ID | 467 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
run | +0.020 |
igsaw | +0.019 |
block | +0.018 |
nail | +0.018 |
pad | +0.017 |
Neg logit contributions | |
Amen | -0.021 |
cle | -0.020 |
ting | -0.020 |
Mr | -0.019 |
Merry | -0.019 |
Token | near |
Token ID | 1474 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
Amen | +0.026 |
cle | +0.025 |
Mr | +0.024 |
ting | +0.023 |
amen | +0.023 |
Neg logit contributions | |
run | -0.015 |
igsaw | -0.014 |
block | -0.014 |
ooter | -0.014 |
nail | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
Amen | +0.010 |
cle | +0.009 |
ting | +0.009 |
Mr | +0.009 |
Santa | +0.008 |
Neg logit contributions | |
run | -0.010 |
nail | -0.010 |
igsaw | -0.010 |
block | -0.009 |
pad | -0.009 |
Token | L |
Token ID | 43 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
pa | +0.023 |
Amen | +0.023 |
sets | +0.023 |
works | +0.022 |
cle | +0.022 |
Neg logit contributions | |
nail | -0.019 |
run | -0.019 |
block | -0.018 |
Half | -0.018 |
pad | -0.018 |
Token | ily |
Token ID | 813 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
run | +0.009 |
igsaw | +0.009 |
nail | +0.009 |
block | +0.009 |
ooter | +0.008 |
Neg logit contributions | |
Amen | -0.010 |
ting | -0.010 |
cle | -0.009 |
Mr | -0.009 |
They | -0.009 |
Token | started |
Token ID | 2067 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
block | +0.016 |
run | +0.015 |
pad | +0.015 |
nail | +0.014 |
stack | +0.014 |
Neg logit contributions | |
Amen | -0.022 |
cle | -0.021 |
ourselves | -0.021 |
ting | -0.020 |
Merry | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
igsaw | +0.025 |
run | +0.023 |
ooter | +0.022 |
pad | +0.022 |
inter | +0.022 |
Neg logit contributions | |
Amen | -0.025 |
ting | -0.024 |
123 | -0.024 |
bless | -0.024 |
Mr | -0.023 |
Token | examine |
Token ID | 10716 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
nail | +0.005 |
block | +0.004 |
run | +0.004 |
igsaw | +0.004 |
pattern | +0.004 |
Neg logit contributions | |
cle | -0.007 |
ting | -0.007 |
Amen | -0.007 |
Merry | -0.007 |
Miss | -0.007 |
Token | Ho |
Token ID | 9544 |
Feature activation | +5.24e+00 |
Pos logit contributions | |
Amen | +0.049 |
cle | +0.047 |
Claus | +0.042 |
adays | +0.042 |
works | +0.041 |
Neg logit contributions | |
run | -0.043 |
nail | -0.037 |
block | -0.037 |
pad | -0.036 |
foot | -0.035 |
Token | ppy |
Token ID | 14097 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Amen | +0.141 |
Merry | +0.131 |
ting | +0.129 |
cle | +0.129 |
Say | +0.128 |
Neg logit contributions | |
run | -0.149 |
pad | -0.137 |
igsaw | -0.136 |
block | -0.131 |
nail | -0.131 |
Token | . |
Token ID | 13 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
Amen | +0.020 |
ting | +0.020 |
cle | +0.019 |
Mr | +0.018 |
They | +0.018 |
Neg logit contributions | |
run | -0.041 |
igsaw | -0.040 |
block | -0.038 |
nail | -0.038 |
ooter | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
cle | +0.027 |
Amen | +0.026 |
ting | +0.025 |
Mr | +0.024 |
Miss | +0.024 |
Neg logit contributions | |
run | -0.028 |
igsaw | -0.026 |
nail | -0.025 |
block | -0.025 |
pad | -0.025 |
Token | looked |
Token ID | 3114 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
Amen | +0.021 |
cle | +0.020 |
ting | +0.020 |
Mr | +0.019 |
They | +0.019 |
Neg logit contributions | |
run | -0.023 |
igsaw | -0.023 |
nail | -0.021 |
block | -0.021 |
ooter | -0.021 |
Token | at |
Token ID | 379 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
cle | +0.015 |
Amen | +0.015 |
ting | +0.015 |
Mr | +0.014 |
123 | +0.014 |
Neg logit contributions | |
run | -0.012 |
igsaw | -0.011 |
block | -0.011 |
nail | -0.011 |
pad | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
cle | +0.015 |
Amen | +0.014 |
Mr | +0.013 |
Santa | +0.013 |
adays | +0.013 |
Neg logit contributions | |
run | -0.014 |
pad | -0.013 |
block | -0.012 |
igsaw | -0.012 |
fault | -0.011 |
Token | They |
Token ID | 1119 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
cle | +0.017 |
Amen | +0.016 |
ting | +0.016 |
sets | +0.015 |
bless | +0.015 |
Neg logit contributions | |
run | -0.014 |
igsaw | -0.013 |
block | -0.012 |
Half | -0.012 |
pad | -0.012 |
Token | took |
Token ID | 1718 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
cle | +0.031 |
Amen | +0.031 |
ting | +0.029 |
ourselves | +0.029 |
123 | +0.028 |
Neg logit contributions | |
block | -0.027 |
run | -0.026 |
nail | -0.026 |
pad | -0.026 |
pattern | -0.024 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
Amen | +0.050 |
cle | +0.049 |
sets | +0.043 |
amen | +0.043 |
Santa | +0.043 |
Neg logit contributions | |
run | -0.044 |
igsaw | -0.042 |
block | -0.040 |
nail | -0.039 |
Half | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
run | +0.017 |
igsaw | +0.017 |
nail | +0.016 |
block | +0.016 |
ooter | +0.015 |
Neg logit contributions | |
Amen | -0.015 |
cle | -0.014 |
ting | -0.014 |
Mr | -0.014 |
123 | -0.013 |
Token | Ho |
Token ID | 9544 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
Amen | +0.004 |
cle | +0.004 |
ting | +0.004 |
Mr | +0.003 |
They | +0.003 |
Neg logit contributions | |
run | -0.004 |
igsaw | -0.004 |
block | -0.004 |
nail | -0.004 |
ooter | -0.004 |
Token | ppy |
Token ID | 14097 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Amen | +0.138 |
Merry | +0.128 |
ting | +0.126 |
Say | +0.124 |
adays | +0.122 |
Neg logit contributions | |
run | -0.160 |
pad | -0.144 |
block | -0.142 |
igsaw | -0.139 |
ooter | -0.136 |
Token | and |
Token ID | 290 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Amen | +0.031 |
cle | +0.030 |
ting | +0.028 |
Mr | +0.028 |
Merry | +0.027 |
Neg logit contributions | |
run | -0.039 |
igsaw | -0.037 |
block | -0.036 |
nail | -0.035 |
pad | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
run | +0.010 |
block | +0.009 |
nail | +0.009 |
igsaw | +0.009 |
pad | +0.009 |
Neg logit contributions | |
Amen | -0.009 |
cle | -0.009 |
ourselves | -0.009 |
ting | -0.008 |
sets | -0.008 |
Token | dog |
Token ID | 3290 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
Amen | +0.023 |
cle | +0.023 |
ting | +0.022 |
Mr | +0.022 |
They | +0.021 |
Neg logit contributions | |
run | -0.019 |
igsaw | -0.018 |
block | -0.018 |
nail | -0.018 |
pad | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
Amen | +0.006 |
cle | +0.006 |
Mr | +0.005 |
ting | +0.005 |
Merry | +0.005 |
Neg logit contributions | |
run | -0.007 |
block | -0.007 |
pad | -0.006 |
nail | -0.006 |
igsaw | -0.006 |
Token | away |
Token ID | 1497 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
Amen | +0.009 |
cle | +0.009 |
Mr | +0.009 |
ting | +0.008 |
Say | +0.008 |
Neg logit contributions | |
run | -0.008 |
igsaw | -0.008 |
block | -0.007 |
nail | -0.007 |
ooter | -0.007 |
Token | from |
Token ID | 422 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
Amen | +0.026 |
cle | +0.024 |
Mr | +0.023 |
Say | +0.022 |
Dear | +0.021 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.023 |
block | -0.022 |
nail | -0.022 |
foot | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +3.86e-01 |
Pos logit contributions | |
Amen | +0.047 |
cle | +0.046 |
ting | +0.045 |
Mr | +0.044 |
Merry | +0.043 |
Neg logit contributions | |
run | -0.060 |
igsaw | -0.058 |
block | -0.056 |
nail | -0.056 |
pad | -0.054 |
Token | traffic |
Token ID | 4979 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
Amen | +0.012 |
cle | +0.012 |
ting | +0.012 |
Mr | +0.011 |
Merry | +0.011 |
Neg logit contributions | |
run | -0.009 |
igsaw | -0.009 |
nail | -0.008 |
pad | -0.008 |
block | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
run | +0.010 |
igsaw | +0.009 |
block | +0.009 |
nail | +0.009 |
pad | +0.009 |
Neg logit contributions | |
Amen | -0.007 |
cle | -0.007 |
Mr | -0.007 |
Merry | -0.006 |
ting | -0.006 |
Token | Ref |
Token ID | 6524 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
Merry | +0.008 |
Amen | +0.008 |
They | +0.008 |
ting | +0.008 |
cle | +0.008 |
Neg logit contributions | |
run | -0.013 |
block | -0.013 |
nail | -0.013 |
igsaw | -0.012 |
ooter | -0.012 |
Token | using |
Token ID | 3500 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
Amen | +0.137 |
cle | +0.128 |
Merry | +0.122 |
God | +0.121 |
Mr | +0.121 |
Neg logit contributions | |
run | -0.150 |
igsaw | -0.140 |
block | -0.133 |
ooter | -0.132 |
nail | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
Amen | +0.026 |
cle | +0.025 |
Mr | +0.024 |
ting | +0.023 |
Santa | +0.023 |
Neg logit contributions | |
run | -0.025 |
igsaw | -0.023 |
nail | -0.022 |
block | -0.022 |
pad | -0.021 |
Token | go |
Token ID | 467 |
Feature activation | +6.52e-01 |
Pos logit contributions | |
run | +0.024 |
igsaw | +0.023 |
block | +0.022 |
nail | +0.022 |
ooter | +0.020 |
Neg logit contributions | |
Amen | -0.027 |
cle | -0.027 |
ting | -0.027 |
Mr | -0.025 |
sets | -0.025 |
Token | near |
Token ID | 1474 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Amen | +0.023 |
cle | +0.022 |
Mr | +0.022 |
amen | +0.021 |
ting | +0.021 |
Neg logit contributions | |
run | -0.013 |
igsaw | -0.012 |
block | -0.012 |
ooter | -0.012 |
nail | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
Amen | +0.007 |
cle | +0.006 |
Mr | +0.006 |
ting | +0.006 |
amen | +0.006 |
Neg logit contributions | |
run | -0.007 |
nail | -0.006 |
igsaw | -0.006 |
block | -0.006 |
pad | -0.006 |
Token | twenty |
Token ID | 8208 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
igsaw | +0.071 |
run | +0.070 |
ooter | +0.067 |
inter | +0.066 |
block | +0.065 |
Neg logit contributions | |
Amen | -0.060 |
Mr | -0.058 |
They | -0.058 |
cle | -0.056 |
Merry | -0.056 |
Token | - |
Token ID | 12 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
run | +0.072 |
igsaw | +0.072 |
nail | +0.068 |
ooter | +0.067 |
inter | +0.067 |
Neg logit contributions | |
cle | -0.046 |
Amen | -0.045 |
They | -0.043 |
ting | -0.043 |
Mr | -0.043 |
Token | eight |
Token ID | 26022 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
igsaw | +0.221 |
run | +0.206 |
inter | +0.204 |
nail | +0.200 |
bucket | +0.199 |
Neg logit contributions | |
Miss | -0.176 |
Amen | -0.175 |
Mr | -0.174 |
cle | -0.173 |
They | -0.171 |
Token | , |
Token ID | 11 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
run | +0.027 |
igsaw | +0.026 |
block | +0.025 |
nail | +0.025 |
pad | +0.024 |
Neg logit contributions | |
Amen | -0.017 |
cle | -0.016 |
ting | -0.016 |
Mr | -0.015 |
Merry | -0.015 |
Token | twenty |
Token ID | 8208 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
run | +0.052 |
igsaw | +0.050 |
ooter | +0.047 |
inter | +0.047 |
block | +0.045 |
Neg logit contributions | |
Amen | -0.081 |
cle | -0.078 |
Mr | -0.078 |
ting | -0.077 |
They | -0.076 |
Token | - |
Token ID | 12 |
Feature activation | -7.32e+00 |
Pos logit contributions | |
igsaw | +0.084 |
run | +0.084 |
nail | +0.080 |
inter | +0.079 |
ooter | +0.079 |
Neg logit contributions | |
cle | -0.057 |
Amen | -0.056 |
They | -0.054 |
ting | -0.053 |
Mr | -0.053 |
Token | nine |
Token ID | 30888 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
igsaw | +0.214 |
run | +0.201 |
inter | +0.200 |
nail | +0.197 |
bucket | +0.195 |
Neg logit contributions | |
Amen | -0.179 |
Mr | -0.176 |
cle | -0.176 |
Miss | -0.175 |
ting | -0.173 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Amen | +0.004 |
cle | +0.003 |
ting | +0.003 |
Santa | +0.003 |
Mr | +0.003 |
Neg logit contributions | |
run | -0.004 |
igsaw | -0.004 |
block | -0.004 |
pad | -0.004 |
nail | -0.004 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
run | +0.039 |
igsaw | +0.037 |
block | +0.034 |
ooter | +0.034 |
nail | +0.033 |
Neg logit contributions | |
Amen | -0.070 |
cle | -0.068 |
ting | -0.067 |
Mr | -0.067 |
They | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
run | +0.050 |
igsaw | +0.050 |
nail | +0.047 |
block | +0.046 |
inter | +0.046 |
Neg logit contributions | |
cle | -0.044 |
Amen | -0.044 |
ting | -0.042 |
They | -0.041 |
Mr | -0.041 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
run | +0.034 |
igsaw | +0.032 |
block | +0.029 |
nail | +0.029 |
ooter | +0.028 |
Neg logit contributions | |
Amen | -0.066 |
cle | -0.065 |
ting | -0.064 |
Mr | -0.063 |
Merry | -0.062 |
Token | nine |
Token ID | 30888 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
igsaw | +0.214 |
run | +0.201 |
inter | +0.200 |
nail | +0.197 |
bucket | +0.195 |
Neg logit contributions | |
Amen | -0.179 |
Mr | -0.176 |
cle | -0.176 |
Miss | -0.175 |
ting | -0.173 |
Token | , |
Token ID | 11 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Amen | +0.004 |
cle | +0.003 |
ting | +0.003 |
Santa | +0.003 |
Mr | +0.003 |
Neg logit contributions | |
run | -0.004 |
igsaw | -0.004 |
block | -0.004 |
pad | -0.004 |
nail | -0.004 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
run | +0.039 |
igsaw | +0.037 |
block | +0.034 |
ooter | +0.034 |
nail | +0.033 |
Neg logit contributions | |
Amen | -0.070 |
cle | -0.068 |
ting | -0.067 |
Mr | -0.067 |
They | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
run | +0.050 |
igsaw | +0.050 |
nail | +0.047 |
block | +0.046 |
inter | +0.046 |
Neg logit contributions | |
cle | -0.044 |
Amen | -0.044 |
ting | -0.042 |
They | -0.041 |
Mr | -0.041 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
run | +0.034 |
igsaw | +0.032 |
block | +0.029 |
nail | +0.029 |
ooter | +0.028 |
Neg logit contributions | |
Amen | -0.066 |
cle | -0.065 |
ting | -0.064 |
Mr | -0.063 |
Merry | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
run | +0.044 |
igsaw | +0.044 |
nail | +0.041 |
block | +0.041 |
inter | +0.040 |
Neg logit contributions | |
Amen | -0.041 |
cle | -0.041 |
ting | -0.039 |
Mr | -0.038 |
They | -0.038 |
Token | one |
Token ID | 505 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
igsaw | +0.184 |
run | +0.178 |
inter | +0.172 |
nail | +0.171 |
ooter | +0.168 |
Neg logit contributions | |
Amen | -0.168 |
ting | -0.165 |
cle | -0.164 |
Mr | -0.163 |
Miss | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
igsaw | +0.057 |
run | +0.053 |
inter | +0.053 |
nail | +0.053 |
Half | +0.052 |
Neg logit contributions | |
Amen | -0.039 |
cle | -0.039 |
They | -0.037 |
pa | -0.036 |
123 | -0.036 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
run | +0.031 |
igsaw | +0.029 |
block | +0.027 |
nail | +0.027 |
ooter | +0.025 |
Neg logit contributions | |
Amen | -0.066 |
cle | -0.065 |
ting | -0.064 |
Mr | -0.063 |
Merry | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
run | +0.040 |
igsaw | +0.039 |
nail | +0.037 |
block | +0.036 |
pad | +0.035 |
Neg logit contributions | |
Amen | -0.038 |
cle | -0.038 |
ting | -0.036 |
Mr | -0.035 |
They | -0.035 |
Token | two |
Token ID | 11545 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
igsaw | +0.171 |
run | +0.167 |
nail | +0.159 |
inter | +0.158 |
ooter | +0.155 |
Neg logit contributions | |
Amen | -0.162 |
ting | -0.159 |
cle | -0.159 |
Mr | -0.157 |
Miss | -0.154 |
Token | back |
Token ID | 736 |
Feature activation | +5.35e-02 |
Pos logit contributions | |
ting | +0.004 |
Amen | +0.004 |
cle | +0.004 |
Merry | +0.004 |
Mr | +0.004 |
Neg logit contributions | |
run | -0.006 |
igsaw | -0.006 |
nail | -0.006 |
block | -0.006 |
ooter | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
ting | +0.001 |
Amen | +0.001 |
cle | +0.001 |
123 | +0.001 |
sets | +0.001 |
Neg logit contributions | |
run | -0.002 |
igsaw | -0.001 |
nail | -0.001 |
block | -0.001 |
inter | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Amen | +0.003 |
cle | +0.003 |
ting | +0.003 |
Mr | +0.002 |
Merry | +0.002 |
Neg logit contributions | |
run | -0.003 |
igsaw | -0.003 |
block | -0.003 |
nail | -0.003 |
pad | -0.003 |
Token | zip |
Token ID | 19974 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
igsaw | +0.002 |
nail | +0.002 |
block | +0.002 |
run | +0.002 |
pad | +0.002 |
Neg logit contributions | |
Amen | -0.004 |
cle | -0.003 |
ting | -0.003 |
They | -0.003 |
Mr | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
run | +0.089 |
igsaw | +0.087 |
block | +0.083 |
nail | +0.083 |
pad | +0.081 |
Neg logit contributions | |
Amen | -0.055 |
cle | -0.053 |
ting | -0.051 |
Mr | -0.049 |
Merry | -0.048 |
Token | line |
Token ID | 1370 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
run | +0.087 |
igsaw | +0.083 |
block | +0.079 |
nail | +0.078 |
pad | +0.075 |
Neg logit contributions | |
Amen | -0.107 |
cle | -0.105 |
ting | -0.103 |
Mr | -0.100 |
Merry | -0.099 |
Token | , |
Token ID | 11 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
run | +0.221 |
igsaw | +0.213 |
block | +0.207 |
nail | +0.205 |
pad | +0.200 |
Neg logit contributions | |
Amen | -0.135 |
cle | -0.130 |
ting | -0.126 |
Mr | -0.123 |
Merry | -0.119 |
Token | z |
Token ID | 1976 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
Amen | +0.001 |
ting | +0.001 |
cle | +0.001 |
Mr | +0.001 |
They | +0.001 |
Neg logit contributions | |
run | -0.001 |
igsaw | -0.001 |
nail | -0.001 |
block | -0.001 |
ooter | -0.001 |
Token | ipping |
Token ID | 4501 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
run | +0.002 |
igsaw | +0.002 |
block | +0.002 |
nail | +0.002 |
pad | +0.001 |
Neg logit contributions | |
cle | -0.002 |
Amen | -0.002 |
ting | -0.002 |
Mr | -0.002 |
Merry | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Amen | +0.006 |
cle | +0.006 |
ting | +0.006 |
Mr | +0.006 |
123 | +0.005 |
Neg logit contributions | |
run | -0.007 |
igsaw | -0.006 |
block | -0.006 |
nail | -0.006 |
pad | -0.006 |
Token | around |
Token ID | 1088 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
run | +0.047 |
igsaw | +0.046 |
nail | +0.044 |
ooter | +0.044 |
inter | +0.043 |
Neg logit contributions | |
ting | -0.033 |
Amen | -0.032 |
cle | -0.031 |
They | -0.030 |
Merry | -0.030 |
Token | robe |
Token ID | 25481 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
run | +0.009 |
igsaw | +0.009 |
block | +0.009 |
nail | +0.008 |
inter | +0.008 |
Neg logit contributions | |
Amen | -0.014 |
cle | -0.014 |
Mr | -0.013 |
ting | -0.013 |
Merry | -0.012 |
Token | back |
Token ID | 736 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
run | +0.003 |
igsaw | +0.003 |
nail | +0.003 |
inter | +0.003 |
block | +0.003 |
Neg logit contributions | |
ting | -0.002 |
They | -0.001 |
123 | -0.001 |
Amen | -0.001 |
Miss | -0.001 |
Token | onto |
Token ID | 4291 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
igsaw | +0.022 |
run | +0.021 |
inter | +0.020 |
nail | +0.020 |
ooter | +0.019 |
Neg logit contributions | |
ting | -0.012 |
They | -0.011 |
123 | -0.011 |
ourselves | -0.011 |
sets | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
run | +0.021 |
igsaw | +0.020 |
ooter | +0.020 |
pad | +0.019 |
inter | +0.019 |
Neg logit contributions | |
ting | -0.011 |
Mr | -0.011 |
cle | -0.011 |
Amen | -0.011 |
They | -0.010 |
Token | clothes |
Token ID | 8242 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
block | +0.007 |
nail | +0.007 |
run | +0.007 |
igsaw | +0.007 |
pad | +0.007 |
Neg logit contributions | |
Amen | -0.015 |
cle | -0.015 |
sets | -0.014 |
Him | -0.014 |
ting | -0.014 |
Token | line |
Token ID | 1370 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
run | +0.027 |
igsaw | +0.027 |
block | +0.025 |
nail | +0.025 |
ooter | +0.025 |
Neg logit contributions | |
Amen | -0.013 |
ting | -0.013 |
cle | -0.013 |
Mr | -0.012 |
They | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
run | +0.244 |
igsaw | +0.241 |
nail | +0.228 |
block | +0.227 |
pad | +0.222 |
Neg logit contributions | |
Amen | -0.102 |
cle | -0.099 |
ting | -0.099 |
They | -0.091 |
Mr | -0.090 |
Token | He |
Token ID | 679 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
igsaw | +0.001 |
run | +0.000 |
nail | +0.000 |
ooter | +0.000 |
pad | +0.000 |
Neg logit contributions | |
Mr | -0.000 |
Amen | -0.000 |
Merry | -0.000 |
They | -0.000 |
ting | -0.000 |
Token | used |
Token ID | 973 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
ting | +0.017 |
Amen | +0.017 |
They | +0.017 |
cle | +0.017 |
Mr | +0.016 |
Neg logit contributions | |
igsaw | -0.024 |
run | -0.024 |
nail | -0.021 |
ooter | -0.021 |
inter | -0.021 |
Token | all |
Token ID | 477 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
They | +0.007 |
ting | +0.006 |
from | +0.006 |
Rudolph | +0.006 |
sometimes | +0.006 |
Neg logit contributions | |
igsaw | -0.027 |
ooter | -0.027 |
inter | -0.026 |
appy | -0.024 |
orry | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
ooter | +0.079 |
pad | +0.076 |
igsaw | +0.075 |
sing | +0.073 |
une | +0.073 |
Neg logit contributions | |
They | -0.026 |
ting | -0.023 |
thanks | -0.022 |
kisses | -0.021 |
pa | -0.020 |
Token | jumped |
Token ID | 11687 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
igsaw | +0.008 |
run | +0.008 |
nail | +0.007 |
inter | +0.007 |
ooter | +0.007 |
Neg logit contributions | |
cle | -0.005 |
Amen | -0.005 |
ting | -0.005 |
Mr | -0.005 |
They | -0.005 |
Token | onto |
Token ID | 4291 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
run | +0.004 |
igsaw | +0.004 |
nail | +0.004 |
inter | +0.004 |
ooter | +0.004 |
Neg logit contributions | |
ting | -0.002 |
They | -0.002 |
Merry | -0.002 |
Amen | -0.002 |
123 | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
run | +0.005 |
ooter | +0.005 |
inter | +0.005 |
igsaw | +0.005 |
pad | +0.005 |
Neg logit contributions | |
ting | -0.001 |
Santa | -0.001 |
ourselves | -0.001 |
123 | -0.001 |
God | -0.001 |
Token | zip |
Token ID | 19974 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
run | +0.002 |
igsaw | +0.002 |
inter | +0.002 |
pad | +0.002 |
fault | +0.002 |
Neg logit contributions | |
ting | -0.003 |
Mr | -0.003 |
Miss | -0.003 |
Merry | -0.003 |
123 | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
run | +0.094 |
igsaw | +0.090 |
Half | +0.083 |
inter | +0.082 |
nail | +0.082 |
Neg logit contributions | |
ting | -0.043 |
123 | -0.038 |
cle | -0.037 |
sets | -0.036 |
adays | -0.036 |
Token | line |
Token ID | 1370 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
run | +0.092 |
igsaw | +0.087 |
nail | +0.083 |
fault | +0.081 |
pad | +0.080 |
Neg logit contributions | |
ting | -0.083 |
cle | -0.083 |
Mr | -0.081 |
Miss | -0.080 |
They | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
run | +0.236 |
igsaw | +0.233 |
nail | +0.215 |
inter | +0.213 |
block | +0.211 |
Neg logit contributions | |
ting | -0.108 |
cle | -0.105 |
Amen | -0.102 |
They | -0.100 |
sets | -0.099 |
Token | z |
Token ID | 1976 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
run | +0.001 |
block | +0.001 |
igsaw | +0.001 |
nail | +0.001 |
pad | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
cle | -0.001 |
Mr | -0.001 |
ting | -0.001 |
Santa | -0.001 |
Token | ipped |
Token ID | 3949 |
Feature activation | +8.52e-02 |
Pos logit contributions | |
igsaw | +0.009 |
pad | +0.009 |
nail | +0.009 |
run | +0.009 |
Half | +0.009 |
Neg logit contributions | |
cle | -0.005 |
ting | -0.005 |
es | -0.005 |
bless | -0.005 |
ises | -0.005 |
Token | around |
Token ID | 1088 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
ting | +0.002 |
Amen | +0.002 |
cle | +0.002 |
Merry | +0.002 |
They | +0.002 |
Neg logit contributions | |
run | -0.003 |
igsaw | -0.003 |
nail | -0.002 |
block | -0.002 |
inter | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
run | +0.030 |
igsaw | +0.029 |
block | +0.027 |
nail | +0.027 |
ooter | +0.027 |
Neg logit contributions | |
Amen | -0.016 |
ting | -0.015 |
cle | -0.015 |
Mr | -0.014 |
Merry | -0.014 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
run | +0.034 |
igsaw | +0.032 |
block | +0.029 |
nail | +0.029 |
ooter | +0.028 |
Neg logit contributions | |
Amen | -0.066 |
cle | -0.065 |
ting | -0.064 |
Mr | -0.063 |
Merry | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
run | +0.044 |
igsaw | +0.044 |
nail | +0.041 |
block | +0.041 |
inter | +0.040 |
Neg logit contributions | |
Amen | -0.041 |
cle | -0.041 |
ting | -0.039 |
Mr | -0.038 |
They | -0.038 |
Token | one |
Token ID | 505 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
igsaw | +0.184 |
run | +0.178 |
inter | +0.172 |
nail | +0.171 |
ooter | +0.168 |
Neg logit contributions | |
Amen | -0.168 |
ting | -0.165 |
cle | -0.164 |
Mr | -0.163 |
Miss | -0.161 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
igsaw | +0.057 |
run | +0.053 |
inter | +0.053 |
nail | +0.053 |
Half | +0.052 |
Neg logit contributions | |
Amen | -0.039 |
cle | -0.039 |
They | -0.037 |
pa | -0.036 |
123 | -0.036 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
run | +0.031 |
igsaw | +0.029 |
block | +0.027 |
nail | +0.027 |
ooter | +0.025 |
Neg logit contributions | |
Amen | -0.066 |
cle | -0.065 |
ting | -0.064 |
Mr | -0.063 |
Merry | -0.062 |
Token | - |
Token ID | 12 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
run | +0.040 |
igsaw | +0.039 |
nail | +0.037 |
block | +0.036 |
pad | +0.035 |
Neg logit contributions | |
Amen | -0.038 |
cle | -0.038 |
ting | -0.036 |
Mr | -0.035 |
They | -0.035 |
Token | two |
Token ID | 11545 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
igsaw | +0.171 |
run | +0.167 |
nail | +0.159 |
inter | +0.158 |
ooter | +0.155 |
Neg logit contributions | |
Amen | -0.162 |
ting | -0.159 |
cle | -0.159 |
Mr | -0.157 |
Miss | -0.154 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
run | +0.021 |
igsaw | +0.021 |
nail | +0.020 |
block | +0.019 |
ooter | +0.019 |
Neg logit contributions | |
Amen | -0.012 |
cle | -0.012 |
ting | -0.011 |
Mr | -0.011 |
They | -0.011 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
run | +0.027 |
igsaw | +0.025 |
block | +0.023 |
nail | +0.023 |
pad | +0.021 |
Neg logit contributions | |
Amen | -0.059 |
cle | -0.058 |
ting | -0.057 |
Mr | -0.056 |
Merry | -0.055 |
Token | - |
Token ID | 12 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
run | +0.033 |
igsaw | +0.032 |
nail | +0.030 |
block | +0.030 |
pad | +0.029 |
Neg logit contributions | |
Amen | -0.033 |
cle | -0.033 |
ting | -0.032 |
Mr | -0.031 |
Merry | -0.030 |
Token | three |
Token ID | 15542 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
run | +0.147 |
igsaw | +0.146 |
nail | +0.137 |
block | +0.134 |
inter | +0.134 |
Neg logit contributions | |
Amen | -0.139 |
cle | -0.139 |
ting | -0.138 |
Mr | -0.135 |
Miss | -0.132 |
Token | as |
Token ID | 355 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Amen | +0.010 |
cle | +0.010 |
ting | +0.009 |
Mr | +0.009 |
Merry | +0.009 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.016 |
block | -0.015 |
nail | -0.015 |
pad | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +5.51e-02 |
Pos logit contributions | |
run | +0.005 |
block | +0.005 |
nail | +0.005 |
igsaw | +0.005 |
Half | +0.005 |
Neg logit contributions | |
Amen | -0.006 |
ting | -0.006 |
cle | -0.005 |
MacDonald | -0.005 |
Mr | -0.005 |
Token | explored |
Token ID | 18782 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
cle | +0.001 |
ting | +0.001 |
Amen | +0.001 |
They | +0.001 |
Mr | +0.001 |
Neg logit contributions | |
igsaw | -0.002 |
run | -0.002 |
nail | -0.002 |
ooter | -0.002 |
block | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.55e-01 |
Pos logit contributions | |
block | +0.002 |
run | +0.002 |
igsaw | +0.001 |
nail | +0.001 |
pattern | +0.001 |
Neg logit contributions | |
Amen | -0.002 |
cle | -0.002 |
Claus | -0.002 |
Mr | -0.002 |
Dear | -0.001 |
Token | shore |
Token ID | 15191 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
Amen | +0.006 |
cle | +0.006 |
ting | +0.006 |
amen | +0.005 |
Mr | +0.005 |
Neg logit contributions | |
block | -0.003 |
nail | -0.002 |
igsaw | -0.002 |
pattern | -0.002 |
run | -0.002 |
Token | line |
Token ID | 1370 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
block | +0.053 |
run | +0.053 |
pad | +0.050 |
igsaw | +0.049 |
nail | +0.049 |
Neg logit contributions | |
Amen | -0.043 |
cle | -0.039 |
Mr | -0.038 |
amen | -0.035 |
Merry | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
run | +0.219 |
igsaw | +0.208 |
block | +0.207 |
nail | +0.203 |
pad | +0.199 |
Neg logit contributions | |
Amen | -0.120 |
cle | -0.115 |
ting | -0.109 |
Mr | -0.109 |
Merry | -0.106 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Amen | +0.001 |
They | +0.001 |
Merry | +0.001 |
Mr | +0.001 |
cle | +0.001 |
Neg logit contributions | |
run | -0.002 |
nail | -0.002 |
chie | -0.002 |
ooter | -0.002 |
igsaw | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
They | +0.002 |
Amen | +0.002 |
Mr | +0.002 |
cle | +0.002 |
Miss | +0.002 |
Neg logit contributions | |
igsaw | -0.004 |
run | -0.004 |
nail | -0.003 |
ooter | -0.003 |
pad | -0.003 |
Token | One |
Token ID | 3198 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
They | +0.009 |
Mr | +0.009 |
Say | +0.008 |
Amen | +0.008 |
Miss | +0.008 |
Neg logit contributions | |
run | -0.017 |
igsaw | -0.015 |
ooter | -0.015 |
inter | -0.015 |
nail | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
run | +0.006 |
igsaw | +0.005 |
nail | +0.005 |
pad | +0.005 |
ooter | +0.005 |
Neg logit contributions | |
cle | -0.005 |
Amen | -0.005 |
Merry | -0.005 |
ting | -0.005 |
They | -0.005 |
Token | I |
Token ID | 40 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
Amen | +0.001 |
cle | +0.000 |
ting | +0.000 |
Mr | +0.000 |
Merry | +0.000 |
Neg logit contributions | |
run | -0.001 |
igsaw | -0.001 |
block | -0.001 |
nail | -0.001 |
pad | -0.001 |
Token | fell |
Token ID | 3214 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
run | +0.019 |
igsaw | +0.019 |
nail | +0.017 |
block | +0.017 |
ooter | +0.017 |
Neg logit contributions | |
Amen | -0.021 |
cle | -0.021 |
ting | -0.020 |
They | -0.020 |
Merry | -0.020 |
Token | off |
Token ID | 572 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
cle | +0.005 |
Amen | +0.005 |
Mr | +0.004 |
amen | +0.004 |
Say | +0.004 |
Neg logit contributions | |
run | -0.005 |
block | -0.004 |
nail | -0.004 |
ooter | -0.004 |
inter | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
cle | +0.043 |
Amen | +0.043 |
sets | +0.039 |
boys | +0.038 |
Claus | +0.038 |
Neg logit contributions | |
run | -0.039 |
block | -0.037 |
igsaw | -0.035 |
nail | -0.034 |
foot | -0.032 |
Token | clothes |
Token ID | 8242 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
cle | +0.012 |
Amen | +0.012 |
Him | +0.011 |
ting | +0.011 |
sets | +0.011 |
Neg logit contributions | |
block | -0.005 |
nail | -0.005 |
igsaw | -0.005 |
pattern | -0.004 |
inter | -0.004 |
Token | line |
Token ID | 1370 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
run | +0.007 |
block | +0.007 |
igsaw | +0.007 |
nail | +0.007 |
pad | +0.007 |
Neg logit contributions | |
Amen | -0.006 |
cle | -0.006 |
Mr | -0.006 |
Merry | -0.006 |
Say | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
run | +0.184 |
block | +0.178 |
igsaw | +0.172 |
ooter | +0.169 |
nail | +0.168 |
Neg logit contributions | |
Amen | -0.154 |
cle | -0.149 |
Mr | -0.143 |
ting | -0.141 |
Merry | -0.139 |
Token | I |
Token ID | 314 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
cle | +0.004 |
Amen | +0.004 |
ting | +0.004 |
Mr | +0.004 |
Miss | +0.004 |
Neg logit contributions | |
run | -0.004 |
block | -0.004 |
nail | -0.004 |
igsaw | -0.004 |
Half | -0.004 |
Token | can |
Token ID | 460 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
igsaw | +0.021 |
run | +0.020 |
nail | +0.018 |
block | +0.018 |
ooter | +0.018 |
Neg logit contributions | |
Amen | -0.019 |
cle | -0.018 |
bless | -0.018 |
They | -0.018 |
ting | -0.018 |
Token | 't |
Token ID | 470 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
Amen | +0.044 |
cle | +0.043 |
ting | +0.042 |
Mr | +0.041 |
Merry | +0.040 |
Neg logit contributions | |
run | -0.043 |
igsaw | -0.041 |
block | -0.040 |
nail | -0.040 |
ooter | -0.038 |
Token | get |
Token ID | 651 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
Amen | +0.001 |
cle | +0.001 |
ting | +0.001 |
Mr | +0.001 |
They | +0.001 |
Neg logit contributions | |
run | -0.001 |
igsaw | -0.001 |
block | -0.001 |
nail | -0.001 |
pad | -0.001 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
run | +0.016 |
igsaw | +0.015 |
block | +0.014 |
nail | +0.014 |
pad | +0.014 |
Neg logit contributions | |
Amen | -0.016 |
cle | -0.015 |
ting | -0.015 |
Mr | -0.015 |
Merry | -0.014 |
Token | going |
Token ID | 1016 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
ting | +0.059 |
Amen | +0.057 |
cle | +0.055 |
sets | +0.054 |
123 | +0.053 |
Neg logit contributions | |
igsaw | -0.087 |
run | -0.086 |
inter | -0.081 |
pad | -0.079 |
ooter | -0.078 |
Token | beyond |
Token ID | 3675 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Amen | +0.005 |
cle | +0.005 |
Mr | +0.005 |
Merry | +0.005 |
amen | +0.005 |
Neg logit contributions | |
run | -0.004 |
block | -0.004 |
ooter | -0.004 |
igsaw | -0.004 |
nail | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
run | +0.017 |
igsaw | +0.016 |
block | +0.015 |
nail | +0.015 |
pad | +0.015 |
Neg logit contributions | |
Amen | -0.013 |
cle | -0.013 |
ting | -0.013 |
Mr | -0.012 |
Merry | -0.012 |
Token | shore |
Token ID | 15191 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Amen | +0.020 |
cle | +0.019 |
ting | +0.019 |
Mr | +0.019 |
Merry | +0.018 |
Neg logit contributions | |
run | -0.014 |
igsaw | -0.013 |
block | -0.013 |
nail | -0.013 |
pad | -0.012 |
Token | line |
Token ID | 1370 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
run | +0.057 |
block | +0.056 |
pad | +0.053 |
nail | +0.053 |
igsaw | +0.053 |
Neg logit contributions | |
Amen | -0.044 |
cle | -0.040 |
Mr | -0.039 |
Merry | -0.037 |
Miss | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
run | +0.207 |
igsaw | +0.197 |
block | +0.194 |
nail | +0.191 |
ooter | +0.188 |
Neg logit contributions | |
Amen | -0.127 |
cle | -0.122 |
ting | -0.118 |
Mr | -0.116 |
Merry | -0.113 |
Token | swim |
Token ID | 9422 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Amen | +0.005 |
cle | +0.005 |
ting | +0.005 |
Mr | +0.004 |
Merry | +0.004 |
Neg logit contributions | |
run | -0.004 |
igsaw | -0.004 |
block | -0.004 |
nail | -0.004 |
ooter | -0.004 |
Token | out |
Token ID | 503 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Amen | +0.046 |
cle | +0.043 |
bless | +0.040 |
Mr | +0.039 |
amen | +0.039 |
Neg logit contributions | |
run | -0.033 |
block | -0.031 |
favorite | -0.030 |
Half | -0.029 |
pad | -0.029 |
Token | further |
Token ID | 2252 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
Amen | +0.018 |
cle | +0.018 |
Mr | +0.017 |
ting | +0.016 |
Miss | +0.016 |
Neg logit contributions | |
run | -0.016 |
block | -0.014 |
igsaw | -0.014 |
nail | -0.013 |
Half | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Amen | +0.024 |
cle | +0.022 |
Mr | +0.022 |
Merry | +0.022 |
bless | +0.021 |
Neg logit contributions | |
run | -0.022 |
block | -0.021 |
pad | -0.020 |
nail | -0.019 |
igsaw | -0.019 |
Token | when |
Token ID | 618 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
run | +0.012 |
igsaw | +0.011 |
nail | +0.011 |
block | +0.011 |
Half | +0.010 |
Neg logit contributions | |
Amen | -0.012 |
cle | -0.012 |
ting | -0.011 |
Mr | -0.011 |
123 | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
cle | +0.054 |
Amen | +0.054 |
ting | +0.053 |
Miss | +0.052 |
Mr | +0.052 |
Neg logit contributions | |
nail | -0.041 |
block | -0.039 |
Half | -0.038 |
igsaw | -0.037 |
run | -0.036 |
Token | hugged |
Token ID | 41130 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
igsaw | +0.008 |
run | +0.008 |
ooter | +0.008 |
nail | +0.008 |
pad | +0.008 |
Neg logit contributions | |
Amen | -0.004 |
ting | -0.004 |
cle | -0.004 |
123 | -0.004 |
Merry | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
Amen | +0.029 |
cle | +0.028 |
Say | +0.027 |
Mr | +0.026 |
Claus | +0.026 |
Neg logit contributions | |
block | -0.017 |
nail | -0.017 |
run | -0.016 |
foot | -0.016 |
pad | -0.015 |
Token | shore |
Token ID | 15191 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Amen | +0.001 |
cle | +0.001 |
ting | +0.001 |
Mr | +0.001 |
Merry | +0.001 |
Neg logit contributions | |
run | -0.001 |
igsaw | -0.001 |
block | -0.001 |
nail | -0.001 |
pad | -0.001 |
Token | line |
Token ID | 1370 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
run | +0.054 |
block | +0.052 |
nail | +0.050 |
igsaw | +0.049 |
ooter | +0.048 |
Neg logit contributions | |
Amen | -0.056 |
Say | -0.051 |
cle | -0.051 |
Mr | -0.051 |
Miss | -0.051 |
Token | again |
Token ID | 757 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
run | +0.178 |
block | +0.171 |
nail | +0.167 |
igsaw | +0.164 |
ooter | +0.161 |
Neg logit contributions | |
Amen | -0.149 |
cle | -0.143 |
Mr | -0.141 |
ting | -0.141 |
Miss | -0.136 |
Token | , |
Token ID | 11 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
Amen | +0.062 |
Mr | +0.057 |
Miss | +0.056 |
Say | +0.055 |
carriers | +0.055 |
Neg logit contributions | |
run | -0.042 |
block | -0.041 |
nail | -0.040 |
pad | -0.038 |
Half | -0.038 |
Token | it |
Token ID | 340 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
nail | +0.009 |
run | +0.009 |
block | +0.009 |
igsaw | +0.009 |
Half | +0.009 |
Neg logit contributions | |
cle | -0.013 |
Amen | -0.013 |
Mr | -0.012 |
Miss | -0.012 |
ting | -0.012 |
Token | noticed |
Token ID | 6810 |
Feature activation | -6.53e-01 |
Pos logit contributions | |
Amen | +0.011 |
cle | +0.010 |
ting | +0.010 |
Merry | +0.010 |
ourselves | +0.010 |
Neg logit contributions | |
run | -0.010 |
block | -0.010 |
nail | -0.010 |
pad | -0.009 |
igsaw | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
run | +0.014 |
block | +0.013 |
nail | +0.013 |
igsaw | +0.012 |
Half | +0.012 |
Neg logit contributions | |
Amen | -0.022 |
cle | -0.022 |
Mr | -0.020 |
Merry | -0.020 |
Claus | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
run | +0.071 |
igsaw | +0.068 |
block | +0.064 |
nail | +0.063 |
pad | +0.061 |
Neg logit contributions | |
Amen | -0.084 |
cle | -0.082 |
ting | -0.081 |
Mr | -0.079 |
Merry | -0.078 |
Token | laundry |
Token ID | 25724 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
run | +0.015 |
igsaw | +0.014 |
block | +0.013 |
nail | +0.013 |
ooter | +0.013 |
Neg logit contributions | |
Amen | -0.020 |
ting | -0.020 |
cle | -0.020 |
Mr | -0.019 |
Merry | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Amen | +0.034 |
cle | +0.033 |
Merry | +0.032 |
Mr | +0.031 |
ting | +0.031 |
Neg logit contributions | |
run | -0.035 |
block | -0.034 |
igsaw | -0.034 |
nail | -0.033 |
pad | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
run | +0.030 |
igsaw | +0.029 |
block | +0.028 |
nail | +0.028 |
pad | +0.027 |
Neg logit contributions | |
Amen | -0.025 |
cle | -0.024 |
ting | -0.023 |
Mr | -0.022 |
Merry | -0.022 |
Token | clothes |
Token ID | 8242 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
nail | +0.019 |
block | +0.019 |
igsaw | +0.018 |
pad | +0.018 |
run | +0.018 |
Neg logit contributions | |
Amen | -0.036 |
cle | -0.034 |
ting | -0.033 |
amen | -0.033 |
sets | -0.033 |
Token | line |
Token ID | 1370 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
run | +0.027 |
igsaw | +0.026 |
block | +0.026 |
nail | +0.026 |
pad | +0.025 |
Neg logit contributions | |
Amen | -0.017 |
cle | -0.016 |
Merry | -0.015 |
Mr | -0.014 |
ting | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
run | +0.207 |
block | +0.196 |
igsaw | +0.194 |
nail | +0.191 |
ooter | +0.188 |
Neg logit contributions | |
Amen | -0.123 |
cle | -0.117 |
ting | -0.112 |
Merry | -0.111 |
Mr | -0.110 |
Token | " |
Token ID | 366 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
igsaw | +0.010 |
pad | +0.009 |
ooter | +0.009 |
nail | +0.009 |
wn | +0.009 |
Neg logit contributions | |
They | -0.006 |
Mr | -0.006 |
Santa | -0.005 |
Merry | -0.005 |
Santa | -0.005 |
Token | He |
Token ID | 1544 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
They | +0.007 |
Mr | +0.007 |
Amen | +0.007 |
cle | +0.007 |
Say | +0.007 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.016 |
ooter | -0.015 |
pad | -0.015 |
fault | -0.015 |
Token | wants |
Token ID | 3382 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Amen | +0.047 |
cle | +0.044 |
ting | +0.043 |
Mr | +0.043 |
Miss | +0.042 |
Neg logit contributions | |
run | -0.045 |
block | -0.044 |
nail | -0.043 |
igsaw | -0.041 |
inter | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
run | +0.032 |
block | +0.029 |
nail | +0.027 |
igsaw | +0.026 |
ooter | +0.024 |
Neg logit contributions | |
Amen | -0.069 |
cle | -0.066 |
ting | -0.064 |
sets | -0.063 |
adays | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
Amen | +0.074 |
cle | +0.072 |
ting | +0.071 |
Mr | +0.069 |
They | +0.067 |
Neg logit contributions | |
run | -0.061 |
igsaw | -0.059 |
block | -0.055 |
nail | -0.055 |
pad | -0.053 |
Token | walk |
Token ID | 2513 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Amen | +0.009 |
Rudolph | +0.008 |
Santa | +0.008 |
bless | +0.008 |
Merry | +0.008 |
Neg logit contributions | |
run | -0.010 |
igsaw | -0.009 |
fault | -0.009 |
une | -0.009 |
Half | -0.009 |
Token | along |
Token ID | 1863 |
Feature activation | -9.37e-02 |
Pos logit contributions | |
run | +0.009 |
block | +0.008 |
igsaw | +0.008 |
ooter | +0.008 |
nail | +0.008 |
Neg logit contributions | |
Amen | -0.009 |
cle | -0.009 |
amen | -0.009 |
bless | -0.009 |
Mr | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
run | +0.003 |
igsaw | +0.003 |
block | +0.003 |
nail | +0.003 |
Half | +0.002 |
Neg logit contributions | |
cle | -0.002 |
Amen | -0.002 |
amen | -0.002 |
Claus | -0.002 |
sets | -0.002 |
Token | shore |
Token ID | 15191 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
block | +0.000 |
pattern | +0.000 |
nail | +0.000 |
igsaw | +0.000 |
ooter | +0.000 |
Neg logit contributions | |
Amen | -0.000 |
cle | -0.000 |
es | -0.000 |
bless | -0.000 |
Dear | -0.000 |
Token | line |
Token ID | 1370 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
run | +0.061 |
block | +0.059 |
pad | +0.057 |
igsaw | +0.056 |
nail | +0.056 |
Neg logit contributions | |
Amen | -0.044 |
cle | -0.041 |
Mr | -0.040 |
Merry | -0.038 |
amen | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
run | +0.205 |
block | +0.194 |
igsaw | +0.192 |
nail | +0.188 |
ooter | +0.188 |
Neg logit contributions | |
Amen | -0.124 |
cle | -0.119 |
Mr | -0.114 |
ting | -0.112 |
Merry | -0.111 |
Token |
|
Token ID | 198 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
Merry | +0.010 |
They | +0.010 |
Amen | +0.009 |
Mr | +0.008 |
God | +0.008 |
Neg logit contributions | |
run | -0.020 |
nail | -0.020 |
tant | -0.019 |
chie | -0.019 |
igsaw | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
Amen | +0.012 |
They | +0.012 |
cle | +0.012 |
Mr | +0.011 |
Miss | +0.011 |
Neg logit contributions | |
run | -0.017 |
igsaw | -0.017 |
nail | -0.016 |
inter | -0.015 |
ooter | -0.015 |
Token | But |
Token ID | 1537 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
They | +0.019 |
Mr | +0.018 |
Amen | +0.018 |
Miss | +0.017 |
cle | +0.017 |
Neg logit contributions | |
run | -0.026 |
igsaw | -0.025 |
nail | -0.024 |
inter | -0.024 |
ooter | -0.024 |
Token | something |
Token ID | 1223 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
ting | +0.020 |
cle | +0.020 |
Amen | +0.020 |
Merry | +0.019 |
Mr | +0.018 |
Neg logit contributions | |
run | -0.047 |
igsaw | -0.046 |
ooter | -0.043 |
inter | -0.043 |
block | -0.043 |
Token | taught |
Token ID | 7817 |
Feature activation | +7.92e-03 |
Pos logit contributions | |
run | +0.019 |
igsaw | +0.018 |
block | +0.017 |
nail | +0.017 |
pad | +0.017 |
Neg logit contributions | |
Amen | -0.015 |
cle | -0.015 |
ting | -0.014 |
Mr | -0.014 |
Merry | -0.014 |
Token | him |
Token ID | 683 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
Amen | +0.000 |
cle | +0.000 |
ting | +0.000 |
Mr | +0.000 |
Santa | +0.000 |
Neg logit contributions | |
run | -0.000 |
igsaw | -0.000 |
block | -0.000 |
nail | -0.000 |
pad | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
run | +0.051 |
igsaw | +0.048 |
block | +0.046 |
nail | +0.046 |
ooter | +0.044 |
Neg logit contributions | |
Amen | -0.056 |
cle | -0.055 |
ting | -0.053 |
Mr | -0.052 |
Merry | -0.050 |
Token | valuable |
Token ID | 8119 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
run | +0.054 |
igsaw | +0.052 |
ption | +0.052 |
pad | +0.050 |
block | +0.050 |
Neg logit contributions | |
Amen | -0.035 |
They | -0.034 |
Merry | -0.032 |
cle | -0.032 |
Mr | -0.031 |
Token | lesson |
Token ID | 11483 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
run | +0.080 |
pad | +0.073 |
igsaw | +0.073 |
block | +0.070 |
ption | +0.069 |
Neg logit contributions | |
Amen | -0.045 |
cle | -0.041 |
God | -0.038 |
123 | -0.038 |
men | -0.037 |
Token | - |
Token ID | 12 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
Amen | +0.000 |
Mr | +0.000 |
cle | +0.000 |
bless | +0.000 |
sets | +0.000 |
Neg logit contributions | |
run | -0.000 |
igsaw | -0.000 |
block | -0.000 |
ooter | -0.000 |
nail | -0.000 |
Token | never |
Token ID | 1239 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
run | +0.155 |
igsaw | +0.149 |
nail | +0.140 |
block | +0.140 |
ooter | +0.137 |
Neg logit contributions | |
Amen | -0.167 |
ting | -0.161 |
cle | -0.160 |
Mr | -0.155 |
sets | -0.153 |
Token | trust |
Token ID | 3774 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
run | +0.023 |
igsaw | +0.021 |
nail | +0.021 |
block | +0.020 |
pad | +0.020 |
Neg logit contributions | |
Amen | -0.027 |
cle | -0.026 |
Mr | -0.025 |
ting | -0.024 |
Santa | -0.024 |
Token | anything |
Token ID | 1997 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
Amen | +0.003 |
cle | +0.003 |
Mr | +0.003 |
Say | +0.003 |
Dear | +0.003 |
Neg logit contributions | |
run | -0.003 |
nail | -0.003 |
block | -0.003 |
pad | -0.003 |
igsaw | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Amen | +0.022 |
cle | +0.021 |
ting | +0.020 |
Mr | +0.020 |
sets | +0.019 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.022 |
nail | -0.021 |
block | -0.021 |
pad | -0.020 |
Token | looks |
Token ID | 3073 |
Feature activation | -9.41e-01 |
Pos logit contributions | |
run | +0.073 |
igsaw | +0.070 |
block | +0.067 |
nail | +0.067 |
pad | +0.065 |
Neg logit contributions | |
Amen | -0.057 |
cle | -0.055 |
ting | -0.053 |
Mr | -0.052 |
They | -0.051 |
Token | started |
Token ID | 2067 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
run | +0.005 |
block | +0.005 |
nail | +0.005 |
igsaw | +0.004 |
pad | +0.004 |
Neg logit contributions | |
Amen | -0.005 |
cle | -0.005 |
ting | -0.004 |
123 | -0.004 |
Mr | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
igsaw | +0.034 |
run | +0.031 |
inter | +0.030 |
block | +0.030 |
nail | +0.029 |
Neg logit contributions | |
ting | -0.038 |
Amen | -0.036 |
cle | -0.035 |
They | -0.035 |
123 | -0.035 |
Token | chase |
Token ID | 15505 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
run | +0.028 |
igsaw | +0.027 |
ooter | +0.024 |
block | +0.024 |
inter | +0.024 |
Neg logit contributions | |
Amen | -0.033 |
ting | -0.033 |
cle | -0.032 |
Mr | -0.031 |
They | -0.031 |
Token | after |
Token ID | 706 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Amen | +0.015 |
cle | +0.014 |
ting | +0.013 |
Mr | +0.013 |
123 | +0.013 |
Neg logit contributions | |
run | -0.017 |
igsaw | -0.016 |
nail | -0.016 |
block | -0.016 |
pad | -0.015 |
Token | Kay |
Token ID | 17356 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
run | +0.006 |
igsaw | +0.005 |
nail | +0.005 |
block | +0.005 |
pad | +0.005 |
Neg logit contributions | |
Amen | -0.005 |
cle | -0.005 |
ting | -0.005 |
Mr | -0.005 |
123 | -0.004 |
Token | lee |
Token ID | 7197 |
Feature activation | -5.92e+00 |
Pos logit contributions | |
run | +0.093 |
igsaw | +0.088 |
block | +0.084 |
nail | +0.084 |
pad | +0.083 |
Neg logit contributions | |
Amen | -0.082 |
cle | -0.076 |
Mr | -0.073 |
ting | -0.072 |
amen | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
run | +0.189 |
pad | +0.178 |
igsaw | +0.169 |
ooter | +0.168 |
block | +0.166 |
Neg logit contributions | |
Amen | -0.153 |
cle | -0.136 |
Mr | -0.126 |
bless | -0.126 |
Santa | -0.125 |
Token | She |
Token ID | 1375 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
run | +0.010 |
igsaw | +0.010 |
nail | +0.009 |
block | +0.009 |
inter | +0.009 |
Neg logit contributions | |
ting | -0.008 |
Merry | -0.008 |
They | -0.008 |
Miss | -0.008 |
123 | -0.008 |
Token | screamed |
Token ID | 25421 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
igsaw | +0.015 |
run | +0.015 |
nail | +0.014 |
block | +0.014 |
ooter | +0.013 |
Neg logit contributions | |
Amen | -0.011 |
cle | -0.011 |
ting | -0.011 |
Mr | -0.010 |
They | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Amen | +0.015 |
cle | +0.015 |
Mr | +0.013 |
ting | +0.013 |
123 | +0.013 |
Neg logit contributions | |
run | -0.017 |
igsaw | -0.016 |
block | -0.015 |
nail | -0.015 |
pad | -0.015 |
Token | ran |
Token ID | 4966 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
run | +0.004 |
igsaw | +0.004 |
nail | +0.004 |
block | +0.004 |
pad | +0.004 |
Neg logit contributions | |
Amen | -0.004 |
cle | -0.004 |
ting | -0.004 |
Mr | -0.004 |
sets | -0.003 |
Token | thirty |
Token ID | 12277 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
run | +0.018 |
block | +0.017 |
igsaw | +0.016 |
nail | +0.016 |
pad | +0.015 |
Neg logit contributions | |
cle | -0.030 |
Amen | -0.030 |
ting | -0.029 |
sets | -0.028 |
Mr | -0.028 |
Token | - |
Token ID | 12 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
run | +0.014 |
igsaw | +0.013 |
block | +0.013 |
nail | +0.012 |
pad | +0.012 |
Neg logit contributions | |
Amen | -0.016 |
ting | -0.016 |
cle | -0.016 |
Mr | -0.015 |
Merry | -0.015 |
Token | seven |
Token ID | 26548 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
run | +0.124 |
igsaw | +0.121 |
nail | +0.115 |
block | +0.113 |
inter | +0.111 |
Neg logit contributions | |
Amen | -0.109 |
cle | -0.109 |
ting | -0.107 |
Mr | -0.104 |
Miss | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
run | +0.044 |
igsaw | +0.043 |
block | +0.041 |
nail | +0.041 |
pad | +0.040 |
Neg logit contributions | |
Amen | -0.030 |
cle | -0.029 |
ting | -0.028 |
Mr | -0.027 |
Merry | -0.026 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
run | +0.039 |
igsaw | +0.037 |
nail | +0.034 |
block | +0.034 |
inter | +0.034 |
Neg logit contributions | |
Amen | -0.056 |
cle | -0.054 |
ting | -0.053 |
Mr | -0.052 |
Merry | -0.052 |
Token | - |
Token ID | 12 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
run | +0.041 |
igsaw | +0.039 |
block | +0.037 |
nail | +0.037 |
pad | +0.036 |
Neg logit contributions | |
Amen | -0.043 |
cle | -0.042 |
ting | -0.041 |
Mr | -0.040 |
Merry | -0.040 |
Token | eight |
Token ID | 26022 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
run | +0.160 |
igsaw | +0.160 |
nail | +0.151 |
inter | +0.149 |
block | +0.146 |
Neg logit contributions | |
Amen | -0.153 |
cle | -0.151 |
ting | -0.149 |
Mr | -0.148 |
Miss | -0.145 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
run | +0.018 |
igsaw | +0.017 |
block | +0.017 |
nail | +0.016 |
pad | +0.016 |
Neg logit contributions | |
Amen | -0.014 |
cle | -0.012 |
ting | -0.012 |
Mr | -0.012 |
Say | -0.012 |
Token | thirty |
Token ID | 12277 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
run | +0.033 |
igsaw | +0.031 |
block | +0.029 |
nail | +0.029 |
pad | +0.027 |
Neg logit contributions | |
Amen | -0.050 |
cle | -0.049 |
ting | -0.049 |
Mr | -0.047 |
Merry | -0.047 |
Token | - |
Token ID | 12 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
run | +0.033 |
igsaw | +0.031 |
block | +0.030 |
nail | +0.030 |
pad | +0.028 |
Neg logit contributions | |
Amen | -0.035 |
cle | -0.034 |
ting | -0.033 |
Mr | -0.032 |
Merry | -0.032 |
Token | nine |
Token ID | 30888 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
run | +0.147 |
igsaw | +0.145 |
nail | +0.137 |
inter | +0.135 |
block | +0.133 |
Neg logit contributions | |
Amen | -0.128 |
cle | -0.128 |
ting | -0.126 |
Mr | -0.124 |
Miss | -0.121 |
Token | it |
Token ID | 340 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
nail | +0.002 |
block | +0.002 |
run | +0.002 |
Half | +0.002 |
igsaw | +0.002 |
Neg logit contributions | |
cle | -0.003 |
Amen | -0.003 |
Mr | -0.002 |
Miss | -0.002 |
Dear | -0.002 |
Token | would |
Token ID | 561 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Amen | +0.012 |
cle | +0.012 |
ting | +0.011 |
Mr | +0.011 |
Merry | +0.011 |
Neg logit contributions | |
run | -0.018 |
block | -0.018 |
nail | -0.017 |
pad | -0.017 |
igsaw | -0.017 |
Token | hug |
Token ID | 16225 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
cle | +0.057 |
Amen | +0.056 |
ting | +0.056 |
Mr | +0.054 |
Merry | +0.053 |
Neg logit contributions | |
run | -0.048 |
block | -0.045 |
igsaw | -0.045 |
nail | -0.044 |
pad | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
Amen | +0.064 |
glers | +0.063 |
cle | +0.061 |
Say | +0.060 |
mun | +0.060 |
Neg logit contributions | |
pad | -0.036 |
block | -0.036 |
favorite | -0.034 |
run | -0.034 |
foot | -0.033 |
Token | shore |
Token ID | 15191 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
Amen | +0.001 |
cle | +0.001 |
ting | +0.001 |
Merry | +0.001 |
Mr | +0.001 |
Neg logit contributions | |
block | -0.001 |
nail | -0.001 |
run | -0.001 |
igsaw | -0.001 |
pad | -0.001 |
Token | line |
Token ID | 1370 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
run | +0.049 |
block | +0.048 |
pad | +0.045 |
igsaw | +0.045 |
ooter | +0.044 |
Neg logit contributions | |
Amen | -0.049 |
cle | -0.048 |
Mr | -0.047 |
Miss | -0.046 |
Say | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
run | +0.156 |
block | +0.150 |
ooter | +0.141 |
igsaw | +0.140 |
nail | +0.139 |
Neg logit contributions | |
Amen | -0.159 |
cle | -0.159 |
Mr | -0.157 |
Miss | -0.150 |
Merry | -0.149 |
Token | admire |
Token ID | 21099 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
block | +0.008 |
run | +0.008 |
nail | +0.007 |
pattern | +0.007 |
pad | +0.007 |
Neg logit contributions | |
cle | -0.011 |
Mr | -0.011 |
ting | -0.011 |
Miss | -0.011 |
Amen | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
cle | +0.024 |
Amen | +0.024 |
Mr | +0.023 |
Claus | +0.022 |
ting | +0.021 |
Neg logit contributions | |
run | -0.019 |
block | -0.017 |
nail | -0.017 |
igsaw | -0.017 |
Half | -0.015 |
Token | wrecked |
Token ID | 44770 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
block | +0.006 |
nail | +0.006 |
run | +0.006 |
pattern | +0.006 |
igsaw | +0.006 |
Neg logit contributions | |
cle | -0.010 |
Amen | -0.010 |
ting | -0.010 |
Mr | -0.009 |
es | -0.009 |
Token | boats |
Token ID | 16659 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
block | +0.021 |
nail | +0.020 |
run | +0.020 |
igsaw | +0.018 |
pad | +0.018 |
Neg logit contributions | |
Amen | -0.037 |
cle | -0.036 |
Mr | -0.035 |
Merry | -0.034 |
Miss | -0.034 |
Token | amazed |
Token ID | 24562 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
igsaw | +0.038 |
run | +0.034 |
inter | +0.034 |
nail | +0.033 |
ooter | +0.032 |
Neg logit contributions | |
Amen | -0.043 |
They | -0.040 |
cle | -0.040 |
ting | -0.039 |
Mr | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
run | +0.047 |
igsaw | +0.044 |
block | +0.042 |
nail | +0.042 |
pad | +0.041 |
Neg logit contributions | |
Amen | -0.044 |
cle | -0.042 |
ting | -0.039 |
Mr | -0.039 |
Merry | -0.039 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
run | +0.016 |
nail | +0.015 |
igsaw | +0.015 |
block | +0.015 |
Half | +0.015 |
Neg logit contributions | |
Amen | -0.013 |
cle | -0.013 |
ting | -0.012 |
Mr | -0.012 |
123 | -0.012 |
Token | if |
Token ID | 611 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
run | +0.032 |
nail | +0.027 |
block | +0.026 |
Half | +0.025 |
igsaw | +0.025 |
Neg logit contributions | |
cle | -0.029 |
Amen | -0.028 |
Say | -0.027 |
Mr | -0.026 |
adays | -0.025 |
Token | Bun |
Token ID | 28515 |
Feature activation | -9.31e-01 |
Pos logit contributions | |
Amen | +0.073 |
cle | +0.072 |
'." | +0.067 |
yer | +0.067 |
Say | +0.066 |
Neg logit contributions | |
run | -0.063 |
nail | -0.058 |
Half | -0.053 |
igsaw | -0.051 |
block | -0.050 |
Token | - |
Token ID | 12 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
run | +0.028 |
igsaw | +0.024 |
block | +0.023 |
nail | +0.023 |
pad | +0.023 |
Neg logit contributions | |
Amen | -0.025 |
cle | -0.024 |
ourselves | -0.023 |
ting | -0.023 |
123 | -0.022 |
Token | B |
Token ID | 33 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
run | +0.163 |
igsaw | +0.151 |
nail | +0.147 |
block | +0.147 |
pad | +0.141 |
Neg logit contributions | |
Amen | -0.154 |
cle | -0.150 |
ting | -0.148 |
Merry | -0.144 |
Mr | -0.143 |
Token | un |
Token ID | 403 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
igsaw | +0.042 |
run | +0.041 |
block | +0.040 |
nail | +0.039 |
Half | +0.037 |
Neg logit contributions | |
Amen | -0.060 |
cle | -0.060 |
ting | -0.059 |
Mr | -0.057 |
They | -0.056 |
Token | could |
Token ID | 714 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
run | +0.054 |
igsaw | +0.049 |
nail | +0.047 |
block | +0.047 |
ooter | +0.046 |
Neg logit contributions | |
Amen | -0.047 |
cle | -0.045 |
ting | -0.043 |
Mr | -0.042 |
Merry | -0.042 |
Token | teach |
Token ID | 4545 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
run | +0.032 |
nail | +0.030 |
block | +0.028 |
ooter | +0.027 |
igsaw | +0.026 |
Neg logit contributions | |
ting | -0.046 |
Mr | -0.046 |
cle | -0.045 |
Amen | -0.045 |
sets | -0.044 |
Token | it |
Token ID | 340 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
cle | +0.005 |
Amen | +0.005 |
Mr | +0.004 |
Santa | +0.004 |
Claus | +0.004 |
Neg logit contributions | |
run | -0.005 |
igsaw | -0.005 |
nail | -0.005 |
block | -0.005 |
pattern | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
run | +0.010 |
block | +0.009 |
igsaw | +0.009 |
nail | +0.009 |
pad | +0.009 |
Neg logit contributions | |
Amen | -0.009 |
cle | -0.009 |
Mr | -0.008 |
ting | -0.008 |
123 | -0.008 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
igsaw | +0.022 |
run | +0.021 |
nail | +0.020 |
ooter | +0.020 |
inter | +0.020 |
Neg logit contributions | |
They | -0.020 |
ourselves | -0.019 |
Mr | -0.018 |
cle | -0.018 |
Santa | -0.018 |
Token | an |
Token ID | 281 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
run | +0.013 |
igsaw | +0.012 |
block | +0.011 |
nail | +0.011 |
Half | +0.011 |
Neg logit contributions | |
Amen | -0.017 |
cle | -0.017 |
ting | -0.016 |
Mr | -0.016 |
Merry | -0.015 |
Token | important |
Token ID | 1593 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
run | +0.052 |
igsaw | +0.050 |
block | +0.049 |
nail | +0.047 |
pad | +0.047 |
Neg logit contributions | |
Amen | -0.039 |
ting | -0.038 |
cle | -0.038 |
123 | -0.036 |
God | -0.036 |
Token | lesson |
Token ID | 11483 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
run | +0.073 |
pad | +0.071 |
igsaw | +0.067 |
block | +0.067 |
ption | +0.065 |
Neg logit contributions | |
cle | -0.033 |
Amen | -0.033 |
They | -0.032 |
123 | -0.031 |
Miss | -0.029 |
Token | - |
Token ID | 12 |
Feature activation | -5.74e+00 |
Pos logit contributions | |
run | +0.006 |
igsaw | +0.005 |
ooter | +0.005 |
block | +0.004 |
pad | +0.004 |
Neg logit contributions | |
Amen | -0.006 |
Mr | -0.006 |
bless | -0.005 |
cle | -0.005 |
Claus | -0.005 |
Token | with |
Token ID | 4480 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
run | +0.126 |
igsaw | +0.123 |
ooter | +0.113 |
nail | +0.112 |
inter | +0.111 |
Neg logit contributions | |
Amen | -0.189 |
ting | -0.176 |
cle | -0.174 |
amen | -0.173 |
Mr | -0.173 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
run | +0.027 |
igsaw | +0.025 |
nail | +0.024 |
block | +0.023 |
pad | +0.023 |
Neg logit contributions | |
Amen | -0.030 |
cle | -0.028 |
Mr | -0.027 |
ting | -0.026 |
sets | -0.026 |
Token | work |
Token ID | 670 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
run | +0.045 |
igsaw | +0.043 |
block | +0.041 |
nail | +0.041 |
pad | +0.039 |
Neg logit contributions | |
Amen | -0.055 |
cle | -0.055 |
ting | -0.054 |
Mr | -0.052 |
123 | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
run | +0.028 |
igsaw | +0.027 |
block | +0.025 |
nail | +0.025 |
ooter | +0.024 |
Neg logit contributions | |
Amen | -0.025 |
cle | -0.023 |
Mr | -0.022 |
ting | -0.021 |
Merry | -0.021 |
Token | determination |
Token ID | 12123 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
run | +0.033 |
igsaw | +0.031 |
nail | +0.030 |
block | +0.029 |
pad | +0.028 |
Neg logit contributions | |
Amen | -0.032 |
cle | -0.031 |
ting | -0.030 |
Mr | -0.030 |
Merry | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Amen | +0.020 |
cle | +0.020 |
ting | +0.019 |
Mr | +0.018 |
They | +0.018 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.023 |
block | -0.023 |
nail | -0.022 |
pad | -0.021 |
Token | edge |
Token ID | 5743 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Amen | +0.037 |
cle | +0.036 |
ting | +0.034 |
Mr | +0.033 |
es | +0.033 |
Neg logit contributions | |
block | -0.024 |
nail | -0.022 |
run | -0.021 |
foot | -0.021 |
square | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
run | +0.017 |
igsaw | +0.016 |
block | +0.016 |
nail | +0.015 |
pad | +0.015 |
Neg logit contributions | |
Amen | -0.020 |
cle | -0.019 |
ting | -0.019 |
Mr | -0.019 |
Merry | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
run | +0.010 |
igsaw | +0.010 |
ooter | +0.010 |
inter | +0.009 |
pad | +0.009 |
Neg logit contributions | |
ting | -0.005 |
Amen | -0.005 |
Mr | -0.005 |
cle | -0.005 |
God | -0.005 |
Token | shore |
Token ID | 15191 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Amen | +0.019 |
cle | +0.019 |
ting | +0.018 |
Mr | +0.018 |
sets | +0.017 |
Neg logit contributions | |
block | -0.012 |
nail | -0.011 |
igsaw | -0.011 |
run | -0.010 |
pattern | -0.010 |
Token | line |
Token ID | 1370 |
Feature activation | -5.71e+00 |
Pos logit contributions | |
run | +0.043 |
block | +0.041 |
igsaw | +0.040 |
nail | +0.039 |
pad | +0.039 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.031 |
Mr | -0.030 |
ting | -0.029 |
Merry | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
run | +0.188 |
igsaw | +0.181 |
block | +0.174 |
nail | +0.173 |
pad | +0.169 |
Neg logit contributions | |
Amen | -0.120 |
cle | -0.117 |
ting | -0.114 |
Mr | -0.109 |
Merry | -0.107 |
Token | just |
Token ID | 655 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Amen | +0.010 |
cle | +0.010 |
ting | +0.010 |
Mr | +0.009 |
Merry | +0.009 |
Neg logit contributions | |
run | -0.010 |
igsaw | -0.010 |
block | -0.010 |
nail | -0.010 |
pad | -0.009 |
Token | stood |
Token ID | 6204 |
Feature activation | +8.85e-01 |
Pos logit contributions | |
run | +0.035 |
block | +0.032 |
igsaw | +0.031 |
nail | +0.031 |
pad | +0.031 |
Neg logit contributions | |
Amen | -0.037 |
cle | -0.036 |
Mr | -0.035 |
ting | -0.034 |
Miss | -0.034 |
Token | there |
Token ID | 612 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
cle | +0.026 |
adays | +0.026 |
Amen | +0.026 |
Mr | +0.025 |
Merry | +0.025 |
Neg logit contributions | |
block | -0.020 |
run | -0.020 |
nail | -0.019 |
Half | -0.018 |
pad | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
run | +0.070 |
block | +0.065 |
pad | +0.065 |
igsaw | +0.063 |
nail | +0.062 |
Neg logit contributions | |
Amen | -0.048 |
cle | -0.046 |
Mr | -0.042 |
ting | -0.041 |
Merry | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
run | +0.030 |
block | +0.028 |
igsaw | +0.028 |
nail | +0.028 |
pad | +0.027 |
Neg logit contributions | |
Amen | -0.025 |
cle | -0.024 |
ting | -0.024 |
Mr | -0.024 |
Merry | -0.023 |
Token | always |
Token ID | 1464 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
run | +0.026 |
igsaw | +0.025 |
block | +0.023 |
nail | +0.023 |
pad | +0.022 |
Neg logit contributions | |
Amen | -0.029 |
cle | -0.029 |
ting | -0.028 |
Mr | -0.028 |
Merry | -0.027 |
Token | there |
Token ID | 612 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
Amen | +0.057 |
cle | +0.056 |
ting | +0.055 |
Mr | +0.054 |
Merry | +0.053 |
Neg logit contributions | |
run | -0.041 |
igsaw | -0.039 |
block | -0.037 |
nail | -0.037 |
pad | -0.035 |
Token | teaching |
Token ID | 7743 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
run | +0.070 |
igsaw | +0.065 |
block | +0.063 |
nail | +0.062 |
pad | +0.062 |
Neg logit contributions | |
Amen | -0.081 |
cle | -0.077 |
Mr | -0.075 |
ting | -0.075 |
Santa | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Amen | +0.003 |
cle | +0.003 |
Mr | +0.003 |
ting | +0.003 |
Santa | +0.002 |
Neg logit contributions | |
run | -0.003 |
igsaw | -0.003 |
nail | -0.002 |
block | -0.002 |
pad | -0.002 |
Token | 3 |
Token ID | 513 |
Feature activation | -5.66e+00 |
Pos logit contributions | |
run | +0.055 |
igsaw | +0.051 |
block | +0.048 |
ooter | +0.048 |
pad | +0.047 |
Neg logit contributions | |
Amen | -0.056 |
ting | -0.054 |
cle | -0.054 |
Merry | -0.053 |
Mr | -0.052 |
Token | - |
Token ID | 12 |
Feature activation | -4.89e+00 |
Pos logit contributions | |
run | +0.171 |
igsaw | +0.163 |
pad | +0.159 |
nail | +0.157 |
inter | +0.156 |
Neg logit contributions | |
Amen | -0.133 |
cle | -0.125 |
ting | -0.120 |
Merry | -0.118 |
Mr | -0.116 |
Token | year |
Token ID | 1941 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
run | +0.125 |
igsaw | +0.120 |
block | +0.113 |
nail | +0.112 |
ooter | +0.108 |
Neg logit contributions | |
Amen | -0.140 |
cle | -0.136 |
ting | -0.134 |
Mr | -0.130 |
Merry | -0.128 |
Token | - |
Token ID | 12 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
run | +0.123 |
igsaw | +0.117 |
block | +0.113 |
nail | +0.112 |
pad | +0.110 |
Neg logit contributions | |
Amen | -0.114 |
cle | -0.112 |
ting | -0.109 |
123 | -0.105 |
Mr | -0.104 |
Token | old |
Token ID | 727 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
run | +0.130 |
igsaw | +0.125 |
block | +0.118 |
nail | +0.117 |
pad | +0.113 |
Neg logit contributions | |
Amen | -0.149 |
cle | -0.146 |
ting | -0.144 |
Mr | -0.139 |
Merry | -0.137 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
run | +0.044 |
igsaw | +0.042 |
block | +0.039 |
nail | +0.039 |
ooter | +0.038 |
Neg logit contributions | |
Amen | -0.047 |
cle | -0.047 |
Mr | -0.044 |
ting | -0.043 |
Santa | -0.042 |
Token | help |
Token ID | 1037 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
cle | +0.063 |
ting | +0.062 |
Amen | +0.060 |
sets | +0.059 |
Merry | +0.059 |
Neg logit contributions | |
block | -0.038 |
nail | -0.038 |
run | -0.035 |
rake | -0.034 |
stack | -0.034 |
Token | you |
Token ID | 345 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Amen | +0.073 |
narrative | +0.068 |
adays | +0.066 |
sets | +0.063 |
cle | +0.063 |
Neg logit contributions | |
nail | -0.087 |
block | -0.087 |
run | -0.082 |
foot | -0.082 |
stack | -0.079 |
Token | . |
Token ID | 13 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
run | +0.010 |
igsaw | +0.010 |
block | +0.010 |
nail | +0.010 |
pad | +0.009 |
Neg logit contributions | |
Amen | -0.005 |
cle | -0.004 |
ting | -0.004 |
Mr | -0.004 |
They | -0.004 |
Token | I |
Token ID | 314 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
sets | +0.021 |
cle | +0.021 |
ting | +0.021 |
glers | +0.020 |
pa | +0.020 |
Neg logit contributions | |
run | -0.019 |
Half | -0.018 |
block | -0.017 |
igsaw | -0.017 |
inter | -0.016 |
Token | 'm |
Token ID | 1101 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
igsaw | +0.018 |
run | +0.017 |
nail | +0.016 |
ooter | +0.016 |
block | +0.016 |
Neg logit contributions | |
Amen | -0.009 |
cle | -0.008 |
bless | -0.008 |
They | -0.008 |
Dear | -0.007 |
Token | sorry |
Token ID | 7926 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Amen | +0.017 |
ting | +0.016 |
Merry | +0.015 |
God | +0.015 |
Mr | +0.015 |
Neg logit contributions | |
igsaw | -0.023 |
run | -0.022 |
pad | -0.021 |
ooter | -0.021 |
inter | -0.021 |
Token | I |
Token ID | 314 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
cle | +0.096 |
rob | +0.090 |
Amen | +0.086 |
Say | +0.085 |
leness | +0.084 |
Neg logit contributions | |
run | -0.066 |
block | -0.064 |
favorite | -0.064 |
foot | -0.062 |
nail | -0.060 |
Token | broke |
Token ID | 6265 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
run | +0.022 |
igsaw | +0.021 |
block | +0.020 |
nail | +0.020 |
pad | +0.019 |
Neg logit contributions | |
Amen | -0.023 |
cle | -0.022 |
ting | -0.022 |
Mr | -0.021 |
Merry | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
Amen | +0.017 |
cle | +0.016 |
amen | +0.015 |
Say | +0.015 |
bless | +0.014 |
Neg logit contributions | |
block | -0.016 |
run | -0.016 |
nail | -0.016 |
igsaw | -0.016 |
foot | -0.014 |
Token | pink |
Token ID | 11398 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
run | +0.014 |
igsaw | +0.013 |
Half | +0.011 |
ooter | +0.011 |
inter | +0.010 |
Neg logit contributions | |
Mr | -0.025 |
cle | -0.024 |
Merry | -0.024 |
Amen | -0.024 |
ting | -0.024 |
Token | cup |
Token ID | 6508 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
run | +0.062 |
igsaw | +0.056 |
nail | +0.048 |
ooter | +0.047 |
block | +0.047 |
Neg logit contributions | |
Amen | -0.140 |
ting | -0.139 |
cle | -0.139 |
Mr | -0.135 |
Merry | -0.135 |
Token | stem |
Token ID | 10717 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
igsaw | +0.034 |
run | +0.033 |
Half | +0.028 |
block | +0.028 |
inter | +0.028 |
Neg logit contributions | |
cle | -0.036 |
ourselves | -0.035 |
Amen | -0.035 |
ting | -0.034 |
Merry | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
run | +0.063 |
igsaw | +0.060 |
block | +0.059 |
nail | +0.058 |
pad | +0.057 |
Neg logit contributions | |
Amen | -0.033 |
cle | -0.031 |
ting | -0.030 |
Mr | -0.029 |
Merry | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
Merry | +0.021 |
They | +0.021 |
Mr | +0.021 |
ting | +0.021 |
Amen | +0.021 |
Neg logit contributions | |
igsaw | -0.015 |
run | -0.014 |
ooter | -0.014 |
pad | -0.013 |
nail | -0.013 |
Token | were |
Token ID | 547 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ting | +0.019 |
cle | +0.019 |
They | +0.018 |
Amen | +0.018 |
Mr | +0.018 |
Neg logit contributions | |
igsaw | -0.031 |
run | -0.028 |
ooter | -0.027 |
Half | -0.025 |
inter | -0.025 |
Token | th |
Token ID | 294 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
ting | +0.006 |
They | +0.006 |
boys | +0.006 |
Mr | +0.006 |
Amen | +0.006 |
Neg logit contributions | |
igsaw | -0.008 |
ooter | -0.007 |
run | -0.006 |
inter | -0.006 |
Half | -0.006 |
Token | orns |
Token ID | 19942 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Amen | +0.051 |
cle | +0.050 |
ting | +0.049 |
Mr | +0.048 |
They | +0.047 |
Neg logit contributions | |
run | -0.051 |
igsaw | -0.049 |
block | -0.046 |
nail | -0.046 |
ooter | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
Amen | +0.065 |
cle | +0.062 |
Merry | +0.057 |
Mr | +0.057 |
ting | +0.055 |
Neg logit contributions | |
run | -0.094 |
igsaw | -0.089 |
block | -0.089 |
nail | -0.089 |
pad | -0.087 |
Token | They |
Token ID | 1119 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
Amen | +0.024 |
cle | +0.023 |
ting | +0.023 |
Mr | +0.023 |
They | +0.022 |
Neg logit contributions | |
run | -0.029 |
igsaw | -0.028 |
block | -0.027 |
nail | -0.027 |
ooter | -0.026 |
Token | hurt |
Token ID | 5938 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
Amen | +0.022 |
cle | +0.022 |
ting | +0.022 |
Mr | +0.021 |
They | +0.021 |
Neg logit contributions | |
igsaw | -0.033 |
run | -0.033 |
ooter | -0.030 |
block | -0.029 |
Half | -0.029 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
Amen | +0.045 |
cle | +0.039 |
amen | +0.037 |
bless | +0.037 |
Claus | +0.036 |
Neg logit contributions | |
run | -0.043 |
block | -0.041 |
nail | -0.041 |
foot | -0.039 |
pad | -0.037 |
Token | 's |
Token ID | 338 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
Amen | +0.011 |
cle | +0.011 |
ting | +0.010 |
Mr | +0.010 |
They | +0.010 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.016 |
block | -0.015 |
nail | -0.015 |
ooter | -0.015 |
Token | boat |
Token ID | 8848 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Amen | +0.015 |
cle | +0.014 |
ting | +0.014 |
Mr | +0.014 |
They | +0.013 |
Neg logit contributions | |
run | -0.009 |
igsaw | -0.009 |
block | -0.008 |
nail | -0.008 |
pad | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
run | +0.012 |
block | +0.011 |
igsaw | +0.011 |
nail | +0.011 |
ooter | +0.011 |
Neg logit contributions | |
Amen | -0.008 |
cle | -0.007 |
ting | -0.007 |
Merry | -0.007 |
Mr | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +6.73e-01 |
Pos logit contributions | |
igsaw | +0.004 |
nail | +0.004 |
run | +0.004 |
block | +0.004 |
ooter | +0.003 |
Neg logit contributions | |
ting | -0.003 |
They | -0.003 |
cle | -0.003 |
Mr | -0.003 |
Amen | -0.003 |
Token | asked |
Token ID | 1965 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
Amen | +0.016 |
ting | +0.015 |
cle | +0.015 |
Merry | +0.014 |
Mr | +0.014 |
Neg logit contributions | |
run | -0.021 |
block | -0.020 |
igsaw | -0.020 |
nail | -0.019 |
pad | -0.019 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
run | +0.018 |
igsaw | +0.017 |
block | +0.016 |
nail | +0.016 |
pad | +0.016 |
Neg logit contributions | |
Amen | -0.019 |
cle | -0.017 |
Mr | -0.016 |
sets | -0.016 |
ting | -0.016 |
Token | if |
Token ID | 611 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
run | +0.008 |
igsaw | +0.007 |
block | +0.007 |
nail | +0.007 |
pad | +0.007 |
Neg logit contributions | |
Amen | -0.008 |
cle | -0.007 |
ting | -0.007 |
Mr | -0.007 |
Merry | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
Amen | +0.080 |
cle | +0.074 |
ting | +0.071 |
Mr | +0.070 |
123 | +0.068 |
Neg logit contributions | |
run | -0.079 |
nail | -0.074 |
igsaw | -0.072 |
block | -0.071 |
Half | -0.069 |
Token | 'd |
Token ID | 1549 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
run | +0.027 |
block | +0.024 |
nail | +0.024 |
igsaw | +0.024 |
pad | +0.023 |
Neg logit contributions | |
Amen | -0.027 |
ting | -0.026 |
cle | -0.026 |
Mr | -0.024 |
sets | -0.024 |
Token | like |
Token ID | 588 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
run | +0.024 |
igsaw | +0.023 |
block | +0.022 |
nail | +0.022 |
pad | +0.021 |
Neg logit contributions | |
Amen | -0.026 |
cle | -0.025 |
ting | -0.025 |
Mr | -0.024 |
Merry | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
run | +0.035 |
igsaw | +0.033 |
block | +0.032 |
nail | +0.032 |
pad | +0.030 |
Neg logit contributions | |
Amen | -0.036 |
cle | -0.036 |
ting | -0.034 |
Mr | -0.033 |
Merry | -0.033 |
Token | help |
Token ID | 1037 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
run | +0.030 |
nail | +0.030 |
block | +0.030 |
igsaw | +0.028 |
ooter | +0.026 |
Neg logit contributions | |
ting | -0.042 |
Amen | -0.041 |
cle | -0.040 |
Merry | -0.040 |
sets | -0.039 |
Token | give |
Token ID | 1577 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
run | +0.016 |
block | +0.014 |
nail | +0.014 |
igsaw | +0.014 |
ooter | +0.013 |
Neg logit contributions | |
Amen | -0.019 |
cle | -0.018 |
ting | -0.018 |
sets | -0.018 |
Santa | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
Amen | +0.064 |
cle | +0.060 |
sets | +0.058 |
amen | +0.056 |
adays | +0.055 |
Neg logit contributions | |
run | -0.053 |
block | -0.051 |
nail | -0.049 |
igsaw | -0.046 |
pad | -0.046 |
Token | some |
Token ID | 617 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
run | +0.014 |
igsaw | +0.013 |
block | +0.013 |
nail | +0.012 |
pad | +0.012 |
Neg logit contributions | |
Amen | -0.016 |
cle | -0.015 |
ting | -0.015 |
Mr | -0.015 |
Merry | -0.014 |
Token | cake |
Token ID | 12187 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
run | +0.008 |
block | +0.007 |
igsaw | +0.007 |
nail | +0.007 |
inter | +0.007 |
Neg logit contributions | |
Amen | -0.010 |
cle | -0.009 |
ting | -0.009 |
sets | -0.009 |
123 | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Amen | +0.032 |
cle | +0.030 |
ting | +0.030 |
Mr | +0.028 |
Merry | +0.028 |
Neg logit contributions | |
run | -0.044 |
igsaw | -0.042 |
block | -0.042 |
nail | -0.040 |
pad | -0.039 |
Token | Or |
Token ID | 1471 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ting | +0.012 |
cle | +0.012 |
sets | +0.012 |
ises | +0.012 |
ley | +0.012 |
Neg logit contributions | |
run | -0.011 |
Half | -0.011 |
block | -0.011 |
igsaw | -0.011 |
nail | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
Amen | +0.072 |
cle | +0.066 |
ting | +0.066 |
sets | +0.063 |
Mr | +0.059 |
Neg logit contributions | |
run | -0.122 |
nail | -0.112 |
block | -0.111 |
igsaw | -0.108 |
ooter | -0.107 |
Token | have |
Token ID | 423 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
Amen | +0.007 |
cle | +0.007 |
ting | +0.007 |
sets | +0.007 |
Mr | +0.006 |
Neg logit contributions | |
run | -0.007 |
block | -0.006 |
nail | -0.006 |
igsaw | -0.006 |
ooter | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
Amen | +0.014 |
cle | +0.013 |
ting | +0.013 |
Mr | +0.013 |
Merry | +0.013 |
Neg logit contributions | |
run | -0.008 |
igsaw | -0.008 |
block | -0.007 |
nail | -0.007 |
pad | -0.007 |
Token | go |
Token ID | 467 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
block | +0.013 |
nail | +0.012 |
igsaw | +0.012 |
stack | +0.011 |
run | +0.011 |
Neg logit contributions | |
ting | -0.019 |
sets | -0.017 |
Amen | -0.017 |
we | -0.016 |
es | -0.016 |
Token | home |
Token ID | 1363 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Amen | +0.032 |
cle | +0.032 |
sets | +0.031 |
ting | +0.031 |
Mr | +0.030 |
Neg logit contributions | |
run | -0.013 |
block | -0.011 |
ooter | -0.011 |
igsaw | -0.010 |
nail | -0.010 |
Token | let |
Token ID | 1309 |
Feature activation | +7.84e-02 |
Pos logit contributions | |
ting | +0.033 |
Say | +0.033 |
rob | +0.032 |
sets | +0.032 |
Amen | +0.032 |
Neg logit contributions | |
run | -0.026 |
block | -0.025 |
nail | -0.024 |
foot | -0.023 |
stack | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
Amen | +0.002 |
cle | +0.002 |
sets | +0.002 |
Say | +0.002 |
ting | +0.002 |
Neg logit contributions | |
run | -0.002 |
block | -0.002 |
igsaw | -0.002 |
nail | -0.002 |
inter | -0.002 |
Token | miracle |
Token ID | 20820 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
run | +0.011 |
igsaw | +0.010 |
block | +0.010 |
nail | +0.010 |
pad | +0.009 |
Neg logit contributions | |
Amen | -0.014 |
cle | -0.013 |
ting | -0.013 |
Mr | -0.013 |
Merry | -0.012 |
Token | happen |
Token ID | 1645 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Amen | +0.021 |
ting | +0.021 |
cle | +0.021 |
Mr | +0.020 |
Say | +0.019 |
Neg logit contributions | |
run | -0.036 |
igsaw | -0.033 |
block | -0.033 |
nail | -0.032 |
pad | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Mr | +0.030 |
ting | +0.030 |
cle | +0.030 |
Say | +0.029 |
Miss | +0.029 |
Neg logit contributions | |
run | -0.038 |
block | -0.036 |
pad | -0.035 |
nail | -0.034 |
igsaw | -0.034 |
Token | save |
Token ID | 3613 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
run | +0.024 |
nail | +0.022 |
block | +0.022 |
igsaw | +0.022 |
Half | +0.021 |
Neg logit contributions | |
cle | -0.022 |
ting | -0.021 |
Miss | -0.021 |
Mr | -0.020 |
Amen | -0.020 |
Token | me |
Token ID | 502 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Amen | +0.097 |
cle | +0.089 |
Say | +0.087 |
MacDonald | +0.085 |
sets | +0.084 |
Neg logit contributions | |
run | -0.080 |
igsaw | -0.075 |
block | -0.074 |
nail | -0.073 |
foot | -0.066 |
Token | ." |
Token ID | 526 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
run | +0.052 |
block | +0.047 |
igsaw | +0.047 |
nail | +0.046 |
pad | +0.045 |
Neg logit contributions | |
Amen | -0.037 |
cle | -0.035 |
Mr | -0.035 |
ting | -0.035 |
Miss | -0.035 |
Token | |
Token ID | 220 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
run | +0.025 |
igsaw | +0.024 |
block | +0.022 |
nail | +0.022 |
Half | +0.021 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.033 |
ting | -0.033 |
sets | -0.031 |
Mr | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
run | +0.033 |
igsaw | +0.032 |
block | +0.030 |
nail | +0.030 |
pad | +0.029 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.033 |
ting | -0.032 |
Mr | -0.031 |
They | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
run | +0.019 |
igsaw | +0.018 |
block | +0.017 |
nail | +0.017 |
pad | +0.016 |
Neg logit contributions | |
Amen | -0.023 |
ting | -0.023 |
cle | -0.023 |
sets | -0.022 |
123 | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +9.18e-01 |
Pos logit contributions | |
run | +0.007 |
igsaw | +0.006 |
block | +0.006 |
nail | +0.006 |
pad | +0.006 |
Neg logit contributions | |
Amen | -0.007 |
cle | -0.007 |
ting | -0.007 |
Mr | -0.006 |
Merry | -0.006 |
Token | strange |
Token ID | 6283 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Amen | +0.027 |
cle | +0.026 |
Mr | +0.025 |
They | +0.025 |
ting | +0.025 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.023 |
ooter | -0.020 |
block | -0.020 |
inter | -0.020 |
Token | sound |
Token ID | 2128 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
run | +0.034 |
igsaw | +0.033 |
ooter | +0.030 |
block | +0.030 |
nail | +0.030 |
Neg logit contributions | |
Amen | -0.022 |
cle | -0.021 |
ting | -0.020 |
They | -0.019 |
sets | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Amen | +0.021 |
cle | +0.021 |
Mr | +0.020 |
Merry | +0.018 |
ports | +0.018 |
Neg logit contributions | |
run | -0.020 |
block | -0.019 |
nail | -0.019 |
pad | -0.018 |
pattern | -0.018 |
Token | like |
Token ID | 588 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
run | +0.005 |
block | +0.005 |
nail | +0.005 |
pad | +0.005 |
igsaw | +0.005 |
Neg logit contributions | |
Amen | -0.007 |
cle | -0.007 |
Mr | -0.007 |
ting | -0.007 |
Miss | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
run | +0.035 |
igsaw | +0.034 |
block | +0.032 |
nail | +0.031 |
ooter | +0.031 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.034 |
ting | -0.033 |
Mr | -0.032 |
Merry | -0.032 |
Token | grow |
Token ID | 1663 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
run | +0.016 |
igsaw | +0.015 |
ooter | +0.013 |
Half | +0.013 |
inter | +0.013 |
Neg logit contributions | |
Amen | -0.019 |
cle | -0.018 |
ting | -0.018 |
Merry | -0.017 |
Mr | -0.017 |
Token | l |
Token ID | 75 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
run | +0.041 |
block | +0.040 |
pattern | +0.038 |
nail | +0.038 |
inter | +0.037 |
Neg logit contributions | |
Amen | -0.039 |
cle | -0.038 |
Mr | -0.037 |
Miss | -0.034 |
Merry | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
run | +0.023 |
block | +0.023 |
pad | +0.023 |
nail | +0.022 |
inter | +0.021 |
Neg logit contributions | |
Amen | -0.018 |
cle | -0.018 |
Mr | -0.017 |
Merry | -0.017 |
Santa | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
Amen | +0.005 |
cle | +0.005 |
ting | +0.004 |
Mr | +0.004 |
Merry | +0.004 |
Neg logit contributions | |
run | -0.003 |
igsaw | -0.003 |
nail | -0.003 |
block | -0.003 |
ooter | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
Amen | +0.001 |
cle | +0.001 |
Mr | +0.001 |
They | +0.001 |
ting | +0.001 |
Neg logit contributions | |
run | -0.001 |
igsaw | -0.001 |
nail | -0.001 |
block | -0.001 |
ooter | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
Amen | +0.022 |
cle | +0.021 |
ting | +0.021 |
adays | +0.021 |
amen | +0.020 |
Neg logit contributions | |
run | -0.025 |
block | -0.025 |
pad | -0.023 |
igsaw | -0.023 |
nail | -0.023 |
Token | dad |
Token ID | 9955 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
run | +0.018 |
igsaw | +0.017 |
block | +0.017 |
nail | +0.017 |
pad | +0.016 |
Neg logit contributions | |
Amen | -0.017 |
cle | -0.017 |
ting | -0.017 |
Mr | -0.016 |
Merry | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Amen | +0.015 |
ting | +0.015 |
cle | +0.015 |
adays | +0.014 |
Mr | +0.014 |
Neg logit contributions | |
run | -0.022 |
block | -0.021 |
igsaw | -0.021 |
nail | -0.021 |
pad | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
Merry | +0.012 |
They | +0.012 |
Amen | +0.011 |
Mr | +0.011 |
Miss | +0.011 |
Neg logit contributions | |
run | -0.020 |
igsaw | -0.019 |
nail | -0.018 |
chie | -0.018 |
ooter | -0.017 |
Token | day |
Token ID | 1110 |
Feature activation | +9.92e-01 |
Pos logit contributions | |
run | +0.018 |
igsaw | +0.018 |
fault | +0.016 |
nail | +0.016 |
pad | +0.016 |
Neg logit contributions | |
cle | -0.012 |
They | -0.011 |
Merry | -0.011 |
Mr | -0.011 |
God | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e-03 |
Pos logit contributions | |
Amen | +0.027 |
cle | +0.025 |
ting | +0.024 |
Santa | +0.023 |
sets | +0.023 |
Neg logit contributions | |
run | -0.028 |
igsaw | -0.027 |
block | -0.027 |
nail | -0.026 |
Half | -0.025 |
Token | they |
Token ID | 484 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
run | +0.000 |
igsaw | +0.000 |
block | +0.000 |
nail | +0.000 |
pad | +0.000 |
Neg logit contributions | |
Amen | -0.000 |
cle | -0.000 |
ting | -0.000 |
Mr | -0.000 |
123 | -0.000 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
Amen | +0.027 |
cle | +0.026 |
ting | +0.025 |
ourselves | +0.024 |
123 | +0.024 |
Neg logit contributions | |
run | -0.034 |
block | -0.033 |
igsaw | -0.033 |
nail | -0.032 |
pad | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
run | +0.015 |
igsaw | +0.014 |
nail | +0.013 |
block | +0.013 |
ooter | +0.013 |
Neg logit contributions | |
Amen | -0.016 |
ting | -0.015 |
cle | -0.015 |
Mr | -0.015 |
They | -0.015 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Amen | +0.023 |
cle | +0.023 |
Mr | +0.023 |
Merry | +0.023 |
ting | +0.022 |
Neg logit contributions | |
run | -0.020 |
igsaw | -0.017 |
Half | -0.016 |
inter | -0.016 |
pad | -0.016 |
Token | flag |
Token ID | 6056 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
run | +0.032 |
igsaw | +0.028 |
inter | +0.026 |
nail | +0.026 |
Half | +0.026 |
Neg logit contributions | |
Amen | -0.038 |
cle | -0.037 |
ting | -0.036 |
Merry | -0.035 |
Mr | -0.035 |
Token | was |
Token ID | 373 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
Amen | +0.011 |
cle | +0.011 |
ting | +0.011 |
Mr | +0.011 |
They | +0.010 |
Neg logit contributions | |
igsaw | -0.014 |
run | -0.014 |
nail | -0.013 |
block | -0.013 |
ooter | -0.012 |
Token | so |
Token ID | 523 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
igsaw | +0.030 |
inter | +0.024 |
nail | +0.024 |
anger | +0.024 |
ooter | +0.023 |
Neg logit contributions | |
ting | -0.017 |
Amen | -0.016 |
They | -0.016 |
Santa | -0.015 |
from | -0.015 |
Token | surprised |
Token ID | 6655 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Amen | +0.000 |
They | +0.000 |
Mr | +0.000 |
cle | +0.000 |
amen | +0.000 |
Neg logit contributions | |
igsaw | -0.000 |
pad | -0.000 |
run | -0.000 |
inter | -0.000 |
nail | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
run | +0.043 |
block | +0.038 |
nail | +0.037 |
igsaw | +0.037 |
pad | +0.036 |
Neg logit contributions | |
Amen | -0.051 |
cle | -0.047 |
bless | -0.044 |
Mr | -0.044 |
Merry | -0.044 |
Token | he |
Token ID | 339 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
block | +0.001 |
run | +0.001 |
nail | +0.001 |
foot | +0.001 |
Half | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
cle | -0.001 |
Mr | -0.001 |
ting | -0.001 |
Miss | -0.001 |
Token | stopped |
Token ID | 5025 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
Amen | +0.028 |
cle | +0.027 |
sets | +0.025 |
Merry | +0.025 |
Him | +0.025 |
Neg logit contributions | |
run | -0.021 |
block | -0.019 |
nail | -0.019 |
pad | -0.018 |
ooter | -0.017 |
Token | ro |
Token ID | 686 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ting | +0.023 |
Amen | +0.023 |
cle | +0.022 |
They | +0.021 |
123 | +0.021 |
Neg logit contributions | |
igsaw | -0.028 |
run | -0.027 |
block | -0.025 |
inter | -0.024 |
nail | -0.024 |
Token | wing |
Token ID | 5469 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
Amen | +0.033 |
Merry | +0.032 |
cle | +0.031 |
ting | +0.030 |
sets | +0.029 |
Neg logit contributions | |
run | -0.044 |
block | -0.042 |
igsaw | -0.041 |
ooter | -0.041 |
inter | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
Amen | +0.006 |
cle | +0.006 |
amen | +0.005 |
bless | +0.005 |
Merry | +0.005 |
Neg logit contributions | |
run | -0.005 |
block | -0.005 |
nail | -0.005 |
pad | -0.005 |
igsaw | -0.005 |
Token | just |
Token ID | 655 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
run | +0.001 |
block | +0.001 |
nail | +0.001 |
pad | +0.001 |
Half | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
cle | -0.001 |
Mr | -0.001 |
Miss | -0.001 |
ting | -0.001 |
Token | looked |
Token ID | 3114 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
run | +0.040 |
block | +0.036 |
igsaw | +0.036 |
nail | +0.036 |
pad | +0.035 |
Neg logit contributions | |
Amen | -0.041 |
cle | -0.040 |
Mr | -0.039 |
ting | -0.038 |
Miss | -0.037 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
Amen | +0.009 |
cle | +0.009 |
ting | +0.009 |
Mr | +0.009 |
123 | +0.008 |
Neg logit contributions | |
run | -0.008 |
igsaw | -0.007 |
block | -0.007 |
nail | -0.007 |
pad | -0.007 |
Token | my |
Token ID | 1820 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Amen | +0.006 |
cle | +0.006 |
carriers | +0.006 |
ourselves | +0.006 |
ting | +0.006 |
Neg logit contributions | |
run | -0.006 |
pad | -0.006 |
block | -0.006 |
nail | -0.005 |
igsaw | -0.005 |
Token | made |
Token ID | 925 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
cle | +0.047 |
ting | +0.047 |
Amen | +0.047 |
ourselves | +0.046 |
carriers | +0.046 |
Neg logit contributions | |
run | -0.037 |
block | -0.036 |
pad | -0.036 |
nail | -0.034 |
pattern | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
God | +0.008 |
ting | +0.008 |
Santa | +0.008 |
ourselves | +0.008 |
They | +0.008 |
Neg logit contributions | |
igsaw | -0.014 |
ooter | -0.013 |
run | -0.013 |
pad | -0.013 |
inter | -0.013 |
Token | rare |
Token ID | 4071 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
Amen | +0.034 |
cle | +0.033 |
bless | +0.033 |
Mr | +0.033 |
Santa | +0.032 |
Neg logit contributions | |
run | -0.034 |
igsaw | -0.030 |
Half | -0.029 |
ooter | -0.028 |
inn | -0.028 |
Token | symbol |
Token ID | 6194 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
run | +0.023 |
igsaw | +0.021 |
Half | +0.019 |
inter | +0.019 |
pad | +0.019 |
Neg logit contributions | |
Amen | -0.030 |
cle | -0.029 |
ting | -0.028 |
bless | -0.028 |
Merry | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
Amen | +0.020 |
cle | +0.019 |
ting | +0.019 |
Mr | +0.018 |
Merry | +0.018 |
Neg logit contributions | |
run | -0.024 |
igsaw | -0.023 |
block | -0.023 |
nail | -0.022 |
pad | -0.022 |
Token | with |
Token ID | 351 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
run | +0.015 |
igsaw | +0.015 |
block | +0.014 |
nail | +0.014 |
pad | +0.014 |
Neg logit contributions | |
Amen | -0.016 |
cle | -0.015 |
ting | -0.015 |
Mr | -0.015 |
Merry | -0.014 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Amen | +0.003 |
ting | +0.003 |
cle | +0.003 |
They | +0.003 |
ourselves | +0.003 |
Neg logit contributions | |
run | -0.003 |
igsaw | -0.003 |
ooter | -0.003 |
inter | -0.003 |
pad | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
run | +0.033 |
igsaw | +0.031 |
block | +0.029 |
nail | +0.029 |
pad | +0.028 |
Neg logit contributions | |
Amen | -0.045 |
cle | -0.044 |
ting | -0.042 |
Mr | -0.042 |
Merry | -0.041 |
Token | different |
Token ID | 1180 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
run | +0.023 |
igsaw | +0.023 |
inter | +0.020 |
Half | +0.020 |
ooter | +0.020 |
Neg logit contributions | |
Amen | -0.025 |
ting | -0.024 |
cle | -0.024 |
Merry | -0.023 |
Mr | -0.023 |
Token | there |
Token ID | 612 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
run | +0.045 |
igsaw | +0.044 |
inter | +0.044 |
nail | +0.044 |
wn | +0.043 |
Neg logit contributions | |
Amen | -0.012 |
cle | -0.012 |
Merry | -0.011 |
They | -0.011 |
123 | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
run | +0.124 |
igsaw | +0.123 |
ooter | +0.115 |
nail | +0.113 |
pad | +0.113 |
Neg logit contributions | |
Amen | -0.063 |
cle | -0.062 |
ting | -0.061 |
Merry | -0.059 |
Mr | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
run | +0.044 |
ooter | +0.040 |
igsaw | +0.040 |
inter | +0.037 |
nail | +0.037 |
Neg logit contributions | |
Amen | -0.033 |
They | -0.032 |
Mr | -0.031 |
Say | -0.031 |
cle | -0.030 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
Amen | +0.028 |
cle | +0.028 |
ting | +0.027 |
Mr | +0.027 |
Merry | +0.026 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.015 |
block | -0.013 |
nail | -0.013 |
ooter | -0.013 |
Token | called |
Token ID | 1444 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
run | +0.003 |
block | +0.003 |
nail | +0.003 |
pad | +0.003 |
foot | +0.003 |
Neg logit contributions | |
sets | -0.003 |
adays | -0.003 |
Amen | -0.003 |
amen | -0.003 |
ourselves | -0.003 |
Token | N |
Token ID | 399 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
run | +0.022 |
igsaw | +0.021 |
block | +0.019 |
nail | +0.019 |
Half | +0.018 |
Neg logit contributions | |
Amen | -0.031 |
cle | -0.030 |
ting | -0.030 |
Mr | -0.029 |
They | -0.029 |
Token | ell |
Token ID | 695 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Amen | +0.017 |
cle | +0.017 |
ting | +0.017 |
Mr | +0.016 |
sets | +0.016 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.015 |
block | -0.014 |
nail | -0.014 |
pad | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
run | +0.041 |
block | +0.040 |
nail | +0.039 |
pad | +0.038 |
igsaw | +0.038 |
Neg logit contributions | |
Amen | -0.025 |
cle | -0.023 |
adays | -0.023 |
Merry | -0.023 |
ting | -0.023 |
Token | N |
Token ID | 399 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
run | +0.007 |
igsaw | +0.006 |
block | +0.006 |
nail | +0.006 |
pad | +0.006 |
Neg logit contributions | |
Amen | -0.006 |
cle | -0.006 |
ting | -0.006 |
Mr | -0.006 |
123 | -0.006 |
Token | ell |
Token ID | 695 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
cle | +0.010 |
Amen | +0.010 |
ting | +0.010 |
Merry | +0.010 |
Mr | +0.009 |
Neg logit contributions | |
run | -0.011 |
igsaw | -0.010 |
block | -0.010 |
nail | -0.010 |
pad | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
run | +0.045 |
block | +0.044 |
nail | +0.043 |
igsaw | +0.042 |
ooter | +0.041 |
Neg logit contributions | |
Amen | -0.039 |
ting | -0.038 |
cle | -0.037 |
Mr | -0.036 |
Merry | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +4.70e-01 |
Pos logit contributions | |
run | +0.013 |
pad | +0.012 |
igsaw | +0.012 |
block | +0.012 |
nail | +0.012 |
Neg logit contributions | |
Amen | -0.011 |
cle | -0.010 |
Mr | -0.009 |
amen | -0.009 |
Say | -0.009 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
Merry | +0.012 |
Amen | +0.012 |
Mr | +0.011 |
They | +0.011 |
cle | +0.011 |
Neg logit contributions | |
run | -0.013 |
nail | -0.013 |
igsaw | -0.013 |
block | -0.013 |
ooter | -0.012 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
run | +0.013 |
block | +0.013 |
igsaw | +0.013 |
pad | +0.011 |
Half | +0.011 |
Neg logit contributions | |
cle | -0.020 |
Amen | -0.020 |
ting | -0.019 |
bless | -0.019 |
amen | -0.019 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Amen | +0.006 |
pa | +0.006 |
God | +0.006 |
They | +0.006 |
Merry | +0.006 |
Neg logit contributions | |
run | -0.005 |
igsaw | -0.005 |
ption | -0.005 |
inter | -0.005 |
Half | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -9.58e-02 |
Pos logit contributions | |
run | +0.041 |
igsaw | +0.041 |
ooter | +0.039 |
inter | +0.038 |
nail | +0.037 |
Neg logit contributions | |
Amen | -0.036 |
They | -0.035 |
Mr | -0.033 |
Say | -0.033 |
cle | -0.032 |
Token | time |
Token ID | 640 |
Feature activation | -9.61e-01 |
Pos logit contributions | |
run | +0.002 |
nail | +0.002 |
igsaw | +0.002 |
ooter | +0.002 |
Half | +0.002 |
Neg logit contributions | |
cle | -0.003 |
Amen | -0.003 |
They | -0.003 |
Mr | -0.003 |
Say | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
run | +0.040 |
inter | +0.039 |
igsaw | +0.039 |
nail | +0.038 |
wn | +0.038 |
Neg logit contributions | |
Amen | -0.010 |
cle | -0.009 |
They | -0.009 |
Merry | -0.009 |
adays | -0.008 |
Token | there |
Token ID | 612 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
igsaw | +0.023 |
run | +0.022 |
ooter | +0.022 |
inter | +0.021 |
fault | +0.020 |
Neg logit contributions | |
Amen | -0.016 |
They | -0.016 |
Mr | -0.015 |
cle | -0.015 |
Merry | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
igsaw | +0.113 |
run | +0.111 |
ooter | +0.108 |
inter | +0.104 |
pad | +0.103 |
Neg logit contributions | |
Merry | -0.037 |
They | -0.037 |
Amen | -0.036 |
cle | -0.036 |
ting | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
run | +0.028 |
ooter | +0.025 |
igsaw | +0.025 |
inter | +0.024 |
nail | +0.023 |
Neg logit contributions | |
Amen | -0.019 |
They | -0.018 |
Mr | -0.018 |
Say | -0.018 |
Merry | -0.017 |
Token | little |
Token ID | 1310 |
Feature activation | +9.45e-02 |
Pos logit contributions | |
Amen | +0.044 |
cle | +0.044 |
ting | +0.043 |
Mr | +0.042 |
Merry | +0.042 |
Neg logit contributions | |
run | -0.027 |
igsaw | -0.025 |
block | -0.022 |
nail | -0.022 |
ooter | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
Amen | +0.018 |
ting | +0.018 |
cle | +0.017 |
They | +0.017 |
Mr | +0.017 |
Neg logit contributions | |
run | -0.025 |
igsaw | -0.024 |
nail | -0.023 |
block | -0.023 |
ooter | -0.022 |
Token | game |
Token ID | 983 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
They | +0.017 |
Mr | +0.017 |
Amen | +0.017 |
cle | +0.016 |
Miss | +0.016 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.014 |
ooter | -0.013 |
inter | -0.013 |
pad | -0.012 |
Token | near |
Token ID | 1474 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Amen | +0.015 |
ting | +0.015 |
cle | +0.015 |
They | +0.014 |
Mr | +0.014 |
Neg logit contributions | |
run | -0.029 |
igsaw | -0.028 |
nail | -0.027 |
block | -0.026 |
ooter | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
run | +0.012 |
igsaw | +0.012 |
ooter | +0.012 |
pad | +0.011 |
inter | +0.011 |
Neg logit contributions | |
cle | -0.008 |
ting | -0.007 |
Amen | -0.007 |
They | -0.007 |
ourselves | -0.007 |
Token | chim |
Token ID | 18205 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
run | +0.004 |
igsaw | +0.003 |
inter | +0.003 |
ooter | +0.003 |
wn | +0.003 |
Neg logit contributions | |
Amen | -0.004 |
Mr | -0.004 |
ting | -0.004 |
cle | -0.004 |
Merry | -0.004 |
Token | ney |
Token ID | 1681 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
run | +0.035 |
igsaw | +0.034 |
nail | +0.031 |
pad | +0.030 |
ooter | +0.029 |
Neg logit contributions | |
cle | -0.045 |
Amen | -0.045 |
They | -0.043 |
Mr | -0.043 |
ting | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
run | +0.078 |
igsaw | +0.076 |
block | +0.073 |
nail | +0.073 |
pad | +0.071 |
Neg logit contributions | |
Amen | -0.035 |
cle | -0.034 |
ting | -0.033 |
Mr | -0.031 |
Merry | -0.030 |
Token | They |
Token ID | 1119 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ting | +0.004 |
Amen | +0.004 |
They | +0.004 |
Mr | +0.004 |
Merry | +0.004 |
Neg logit contributions | |
run | -0.005 |
igsaw | -0.005 |
nail | -0.005 |
pad | -0.005 |
ooter | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Amen | +0.026 |
cle | +0.025 |
ting | +0.025 |
Mr | +0.024 |
They | +0.024 |
Neg logit contributions | |
run | -0.033 |
igsaw | -0.032 |
block | -0.030 |
nail | -0.030 |
ooter | -0.029 |
Token | very |
Token ID | 845 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ting | +0.003 |
Amen | +0.003 |
They | +0.003 |
boys | +0.003 |
ourselves | +0.003 |
Neg logit contributions | |
igsaw | -0.004 |
run | -0.004 |
inter | -0.004 |
ooter | -0.004 |
nail | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
Amen | +0.040 |
cle | +0.039 |
They | +0.039 |
Mr | +0.039 |
ting | +0.038 |
Neg logit contributions | |
run | -0.030 |
igsaw | -0.029 |
pad | -0.026 |
ooter | -0.025 |
nail | -0.025 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
Amen | +0.025 |
cle | +0.025 |
ting | +0.025 |
Mr | +0.024 |
They | +0.023 |
Neg logit contributions | |
run | -0.026 |
igsaw | -0.026 |
nail | -0.025 |
block | -0.025 |
pad | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
run | +0.023 |
igsaw | +0.023 |
nail | +0.021 |
block | +0.021 |
ooter | +0.020 |
Neg logit contributions | |
Amen | -0.018 |
cle | -0.017 |
ting | -0.017 |
Mr | -0.017 |
They | -0.016 |
Token | never |
Token ID | 1239 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
igsaw | +0.011 |
inter | +0.010 |
run | +0.010 |
ooter | +0.010 |
nail | +0.010 |
Neg logit contributions | |
They | -0.005 |
Mr | -0.005 |
Santa | -0.005 |
Dear | -0.005 |
granted | -0.005 |
Token | seen |
Token ID | 1775 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ting | +0.008 |
Merry | +0.008 |
cle | +0.008 |
Say | +0.008 |
bless | +0.008 |
Neg logit contributions | |
igsaw | -0.006 |
run | -0.005 |
inter | -0.005 |
ooter | -0.005 |
nail | -0.005 |
Token | meat |
Token ID | 6174 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
igsaw | +0.086 |
run | +0.086 |
ooter | +0.081 |
inter | +0.079 |
nail | +0.079 |
Neg logit contributions | |
ting | -0.065 |
Merry | -0.057 |
Mr | -0.056 |
God | -0.056 |
cle | -0.055 |
Token | so |
Token ID | 523 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Amen | +0.050 |
cle | +0.046 |
Mr | +0.042 |
123 | +0.042 |
Dear | +0.042 |
Neg logit contributions | |
run | -0.053 |
block | -0.050 |
igsaw | -0.050 |
pad | -0.049 |
nail | -0.049 |
Token | big |
Token ID | 1263 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
run | +0.029 |
igsaw | +0.027 |
block | +0.026 |
nail | +0.026 |
pad | +0.025 |
Neg logit contributions | |
Amen | -0.032 |
cle | -0.030 |
ting | -0.029 |
Mr | -0.028 |
sets | -0.028 |
Token | before |
Token ID | 878 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
run | +0.067 |
pad | +0.063 |
block | +0.063 |
igsaw | +0.061 |
nail | +0.060 |
Neg logit contributions | |
Amen | -0.075 |
cle | -0.072 |
Mr | -0.066 |
123 | -0.065 |
They | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
Amen | +0.018 |
cle | +0.016 |
Mr | +0.016 |
bless | +0.016 |
Miss | +0.016 |
Neg logit contributions | |
run | -0.017 |
block | -0.015 |
igsaw | -0.015 |
pad | -0.015 |
nail | -0.015 |
Token | he |
Token ID | 339 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
run | +0.049 |
igsaw | +0.046 |
block | +0.045 |
nail | +0.044 |
pad | +0.043 |
Neg logit contributions | |
Amen | -0.037 |
cle | -0.036 |
ting | -0.035 |
Mr | -0.034 |
123 | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Amen | +0.014 |
cle | +0.013 |
Mr | +0.013 |
ting | +0.013 |
They | +0.013 |
Neg logit contributions | |
igsaw | -0.021 |
run | -0.020 |
nail | -0.019 |
ooter | -0.019 |
inter | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
igsaw | +0.025 |
run | +0.024 |
ooter | +0.023 |
inter | +0.023 |
pad | +0.022 |
Neg logit contributions | |
Amen | -0.020 |
They | -0.019 |
cle | -0.019 |
Mr | -0.018 |
ting | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
igsaw | +0.115 |
run | +0.114 |
ooter | +0.109 |
inter | +0.105 |
pad | +0.105 |
Neg logit contributions | |
Amen | -0.040 |
Merry | -0.040 |
cle | -0.039 |
They | -0.039 |
Mr | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
run | +0.031 |
ooter | +0.028 |
igsaw | +0.028 |
inter | +0.026 |
nail | +0.026 |
Neg logit contributions | |
Amen | -0.022 |
They | -0.022 |
Mr | -0.021 |
Say | -0.021 |
cle | -0.020 |
Token | little |
Token ID | 1310 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
Amen | +0.043 |
cle | +0.042 |
ting | +0.041 |
Mr | +0.041 |
Merry | +0.040 |
Neg logit contributions | |
run | -0.027 |
igsaw | -0.025 |
block | -0.022 |
ooter | -0.022 |
nail | -0.022 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
Amen | +0.002 |
cle | +0.002 |
ting | +0.002 |
Mr | +0.002 |
123 | +0.002 |
Neg logit contributions | |
run | -0.002 |
igsaw | -0.002 |
block | -0.002 |
nail | -0.002 |
pad | -0.002 |
Token | named |
Token ID | 3706 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
sets | +0.010 |
adays | +0.010 |
amen | +0.010 |
ourselves | +0.010 |
ting | +0.010 |
Neg logit contributions | |
block | -0.010 |
run | -0.010 |
nail | -0.010 |
foot | -0.009 |
pad | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
run | +0.031 |
igsaw | +0.030 |
block | +0.028 |
nail | +0.028 |
ooter | +0.028 |
Neg logit contributions | |
Amen | -0.026 |
Merry | -0.025 |
cle | -0.025 |
Mr | -0.025 |
ting | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
adays | +0.001 |
Merry | +0.001 |
Amen | +0.001 |
ting | +0.001 |
amen | +0.001 |
Neg logit contributions | |
block | -0.001 |
run | -0.001 |
nail | -0.001 |
pad | -0.001 |
igsaw | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
Amen | +0.003 |
Merry | +0.003 |
They | +0.003 |
Mr | +0.003 |
ting | +0.003 |
Neg logit contributions | |
run | -0.005 |
igsaw | -0.005 |
ooter | -0.004 |
nail | -0.004 |
block | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | +9.19e-01 |
Pos logit contributions | |
ting | +0.020 |
cle | +0.019 |
Amen | +0.019 |
ourselves | +0.019 |
sets | +0.019 |
Neg logit contributions | |
block | -0.019 |
run | -0.018 |
nail | -0.018 |
pad | -0.017 |
igsaw | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ting | +0.025 |
Amen | +0.025 |
sets | +0.024 |
Merry | +0.024 |
God | +0.024 |
Neg logit contributions | |
run | -0.025 |
igsaw | -0.025 |
inter | -0.022 |
pad | -0.022 |
ooter | -0.021 |
Token | off |
Token ID | 572 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
run | +0.010 |
igsaw | +0.009 |
nail | +0.009 |
block | +0.009 |
pad | +0.008 |
Neg logit contributions | |
Amen | -0.011 |
ting | -0.011 |
cle | -0.011 |
They | -0.010 |
Merry | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
ting | +0.042 |
Amen | +0.042 |
cle | +0.041 |
123 | +0.041 |
They | +0.040 |
Neg logit contributions | |
run | -0.047 |
inter | -0.044 |
igsaw | -0.044 |
nail | -0.043 |
ooter | -0.043 |
Token | find |
Token ID | 1064 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
run | +0.005 |
ooter | +0.005 |
pad | +0.005 |
igsaw | +0.005 |
inter | +0.005 |
Neg logit contributions | |
Amen | -0.005 |
cle | -0.005 |
ourselves | -0.005 |
Merry | -0.004 |
ting | -0.004 |
Token | more |
Token ID | 517 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
run | +0.015 |
igsaw | +0.015 |
block | +0.014 |
nail | +0.014 |
Half | +0.013 |
Neg logit contributions | |
Amen | -0.019 |
cle | -0.018 |
ting | -0.018 |
Mr | -0.018 |
123 | -0.017 |
Token | things |
Token ID | 1243 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
run | +0.004 |
igsaw | +0.004 |
block | +0.003 |
nail | +0.003 |
ooter | +0.003 |
Neg logit contributions | |
Amen | -0.005 |
cle | -0.005 |
ting | -0.005 |
Mr | -0.004 |
They | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Amen | +0.050 |
cle | +0.047 |
ting | +0.045 |
Mr | +0.045 |
Merry | +0.044 |
Neg logit contributions | |
run | -0.047 |
igsaw | -0.044 |
block | -0.042 |
nail | -0.041 |
pad | -0.040 |
Token | do |
Token ID | 466 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
run | +0.042 |
igsaw | +0.039 |
block | +0.037 |
nail | +0.037 |
pad | +0.037 |
Neg logit contributions | |
Amen | -0.041 |
cle | -0.040 |
ting | -0.039 |
Mr | -0.038 |
They | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -7.13e-02 |
Pos logit contributions | |
run | +0.010 |
igsaw | +0.010 |
block | +0.009 |
nail | +0.009 |
pad | +0.009 |
Neg logit contributions | |
Amen | -0.007 |
cle | -0.007 |
ting | -0.007 |
Mr | -0.007 |
Merry | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
run | +0.002 |
igsaw | +0.002 |
block | +0.002 |
nail | +0.002 |
pad | +0.002 |
Neg logit contributions | |
Amen | -0.002 |
cle | -0.002 |
ting | -0.002 |
Mr | -0.002 |
Merry | -0.002 |
Token | John |
Token ID | 7554 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
run | +0.021 |
block | +0.020 |
igsaw | +0.019 |
Half | +0.018 |
pad | +0.018 |
Neg logit contributions | |
cle | -0.023 |
Amen | -0.023 |
ting | -0.021 |
amen | -0.021 |
bless | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
Amen | +0.008 |
ourselves | +0.007 |
cle | +0.007 |
ting | +0.007 |
Miss | +0.007 |
Neg logit contributions | |
block | -0.006 |
run | -0.006 |
pad | -0.006 |
nail | -0.005 |
stack | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
run | +0.013 |
igsaw | +0.012 |
block | +0.012 |
nail | +0.012 |
pad | +0.011 |
Neg logit contributions | |
Amen | -0.015 |
cle | -0.015 |
ting | -0.014 |
Mr | -0.014 |
Merry | -0.014 |
Token | little |
Token ID | 1310 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
Amen | +0.017 |
cle | +0.017 |
Mr | +0.016 |
Merry | +0.016 |
ting | +0.016 |
Neg logit contributions | |
run | -0.012 |
igsaw | -0.011 |
pad | -0.010 |
ooter | -0.010 |
block | -0.010 |
Token | 3 |
Token ID | 513 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
run | +0.019 |
igsaw | +0.018 |
ooter | +0.017 |
pad | +0.016 |
block | +0.016 |
Neg logit contributions | |
Amen | -0.013 |
ting | -0.012 |
cle | -0.012 |
Mr | -0.012 |
Merry | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | -3.68e+00 |
Pos logit contributions | |
run | +0.064 |
igsaw | +0.062 |
nail | +0.058 |
block | +0.058 |
pad | +0.057 |
Neg logit contributions | |
Amen | -0.059 |
cle | -0.058 |
ting | -0.057 |
Mr | -0.054 |
They | -0.054 |
Token | year |
Token ID | 1941 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
igsaw | +0.112 |
run | +0.108 |
pad | +0.100 |
fault | +0.099 |
inter | +0.099 |
Neg logit contributions | |
Amen | -0.094 |
cle | -0.085 |
ting | -0.084 |
Miss | -0.083 |
Dear | -0.081 |
Token | - |
Token ID | 12 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
run | +0.088 |
igsaw | +0.084 |
block | +0.079 |
nail | +0.079 |
pad | +0.078 |
Neg logit contributions | |
Amen | -0.071 |
cle | -0.069 |
ting | -0.066 |
Mr | -0.063 |
123 | -0.063 |
Token | old |
Token ID | 727 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
run | +0.123 |
igsaw | +0.122 |
nail | +0.111 |
inter | +0.111 |
pad | +0.111 |
Neg logit contributions | |
Amen | -0.105 |
cle | -0.101 |
Miss | -0.097 |
They | -0.094 |
ting | -0.094 |
Token | girl |
Token ID | 2576 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
Amen | +0.031 |
adays | +0.031 |
ourselves | +0.031 |
cle | +0.031 |
Mr | +0.031 |
Neg logit contributions | |
block | -0.018 |
run | -0.017 |
nail | -0.017 |
pad | -0.015 |
igsaw | -0.014 |
Token | found |
Token ID | 1043 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
block | +0.002 |
run | +0.002 |
nail | +0.002 |
pad | +0.001 |
Half | +0.001 |
Neg logit contributions | |
Amen | -0.002 |
ourselves | -0.002 |
sets | -0.002 |
amen | -0.002 |
Mr | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
run | +0.036 |
igsaw | +0.036 |
ooter | +0.034 |
pad | +0.034 |
inter | +0.033 |
Neg logit contributions | |
ting | -0.020 |
Amen | -0.017 |
Mr | -0.017 |
ourselves | -0.017 |
cle | -0.017 |
Token | frame |
Token ID | 5739 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
run | +0.001 |
inn | +0.001 |
inter | +0.001 |
igsaw | +0.001 |
ooter | +0.000 |
Neg logit contributions | |
Miss | -0.001 |
Dear | -0.001 |
ourselves | -0.001 |
singers | -0.001 |
123 | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
run | +0.004 |
igsaw | +0.004 |
block | +0.004 |
pad | +0.004 |
nail | +0.003 |
Neg logit contributions | |
Amen | -0.003 |
cle | -0.003 |
Mr | -0.003 |
123 | -0.003 |
Santa | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
Amen | +0.026 |
cle | +0.025 |
sets | +0.024 |
MacDonald | +0.024 |
ting | +0.023 |
Neg logit contributions | |
igsaw | -0.023 |
nail | -0.022 |
block | -0.022 |
run | -0.021 |
square | -0.020 |
Token | top |
Token ID | 1353 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Amen | +0.002 |
cle | +0.002 |
ting | +0.002 |
Mr | +0.002 |
Merry | +0.002 |
Neg logit contributions | |
run | -0.002 |
igsaw | -0.001 |
block | -0.001 |
nail | -0.001 |
ooter | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
run | +0.036 |
igsaw | +0.034 |
nail | +0.033 |
ooter | +0.032 |
block | +0.032 |
Neg logit contributions | |
cle | -0.021 |
ting | -0.021 |
Amen | -0.021 |
Mr | -0.020 |
They | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
run | +0.054 |
igsaw | +0.052 |
ooter | +0.049 |
inter | +0.049 |
block | +0.049 |
Neg logit contributions | |
Amen | -0.034 |
cle | -0.033 |
ting | -0.032 |
Mr | -0.032 |
Merry | -0.031 |
Token | pile |
Token ID | 14540 |
Feature activation | -4.84e+00 |
Pos logit contributions | |
run | +0.006 |
igsaw | +0.005 |
inter | +0.005 |
ooter | +0.005 |
nail | +0.004 |
Neg logit contributions | |
Mr | -0.009 |
cle | -0.009 |
Merry | -0.009 |
Amen | -0.009 |
ting | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
run | +0.151 |
igsaw | +0.145 |
block | +0.141 |
nail | +0.138 |
pad | +0.134 |
Neg logit contributions | |
Amen | -0.117 |
cle | -0.111 |
ting | -0.105 |
Mr | -0.105 |
123 | -0.102 |
Token | The |
Token ID | 383 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Amen | +0.007 |
Merry | +0.006 |
Mr | +0.006 |
They | +0.006 |
ting | +0.006 |
Neg logit contributions | |
run | -0.007 |
igsaw | -0.007 |
nail | -0.007 |
block | -0.007 |
ooter | -0.007 |
Token | end |
Token ID | 886 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
Amen | +0.024 |
cle | +0.023 |
ting | +0.023 |
123 | +0.021 |
Merry | +0.021 |
Neg logit contributions | |
igsaw | -0.037 |
run | -0.036 |
block | -0.036 |
nail | -0.036 |
pad | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +2.99e-01 |
Pos logit contributions | |
Amen | +0.000 |
cle | +0.000 |
ting | +0.000 |
They | +0.000 |
Mr | +0.000 |
Neg logit contributions | |
run | -0.001 |
igsaw | -0.001 |
nail | -0.000 |
ooter | -0.000 |
pad | -0.000 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
Amen | +0.008 |
cle | +0.007 |
Mr | +0.007 |
Merry | +0.007 |
ting | +0.007 |
Neg logit contributions | |
run | -0.009 |
igsaw | -0.008 |
nail | -0.008 |
block | -0.008 |
ooter | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -8.77e-02 |
Pos logit contributions | |
igsaw | +0.015 |
run | +0.014 |
nail | +0.013 |
ooter | +0.013 |
inter | +0.013 |
Neg logit contributions | |
ting | -0.014 |
Amen | -0.014 |
Mr | -0.013 |
cle | -0.013 |
They | -0.013 |
Token | Can |
Token ID | 6090 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
run | +0.003 |
igsaw | +0.003 |
block | +0.003 |
nail | +0.003 |
pad | +0.003 |
Neg logit contributions | |
Amen | -0.002 |
cle | -0.002 |
ting | -0.002 |
123 | -0.002 |
adays | -0.002 |
Token | I |
Token ID | 314 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Amen | +0.012 |
ting | +0.012 |
cle | +0.012 |
sets | +0.010 |
Santa | +0.010 |
Neg logit contributions | |
run | -0.020 |
nail | -0.019 |
block | -0.019 |
igsaw | -0.019 |
ooter | -0.018 |
Token | have |
Token ID | 423 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
run | +0.040 |
igsaw | +0.039 |
nail | +0.036 |
block | +0.035 |
pad | +0.035 |
Neg logit contributions | |
Amen | -0.040 |
cle | -0.039 |
ting | -0.038 |
Mr | -0.037 |
Merry | -0.037 |
Token | another |
Token ID | 1194 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Amen | +0.007 |
Mr | +0.007 |
ting | +0.007 |
Merry | +0.007 |
cle | +0.007 |
Neg logit contributions | |
run | -0.010 |
igsaw | -0.010 |
inter | -0.009 |
ooter | -0.009 |
pad | -0.009 |
Token | black |
Token ID | 2042 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
igsaw | +0.007 |
run | +0.006 |
ption | +0.006 |
iddled | +0.006 |
Half | +0.005 |
Neg logit contributions | |
," | -0.005 |
." | -0.004 |
!" | -0.004 |
?" | -0.004 |
Merry | -0.004 |
Token | pr |
Token ID | 778 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
igsaw | +0.125 |
run | +0.111 |
wn | +0.098 |
Half | +0.095 |
Half | +0.095 |
Neg logit contributions | |
ting | -0.107 |
," | -0.102 |
!" | -0.094 |
Merry | -0.094 |
cle | -0.094 |
Token | une |
Token ID | 1726 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ting | +0.000 |
es | +0.000 |
Merry | +0.000 |
cle | +0.000 |
bless | +0.000 |
Neg logit contributions | |
igsaw | -0.000 |
run | -0.000 |
tant | -0.000 |
ption | -0.000 |
nail | -0.000 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
run | +0.064 |
igsaw | +0.064 |
nail | +0.059 |
inter | +0.058 |
pad | +0.058 |
Neg logit contributions | |
ting | -0.029 |
Amen | -0.029 |
cle | -0.028 |
Mr | -0.027 |
Merry | -0.026 |
Token | Her |
Token ID | 2332 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
run | +0.032 |
igsaw | +0.031 |
nail | +0.029 |
block | +0.028 |
pad | +0.028 |
Neg logit contributions | |
Amen | -0.044 |
cle | -0.042 |
ting | -0.041 |
Mr | -0.040 |
Merry | -0.040 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Amen | +0.003 |
cle | +0.003 |
pa | +0.003 |
men | +0.002 |
boys | +0.002 |
Neg logit contributions | |
run | -0.012 |
igsaw | -0.012 |
inter | -0.012 |
wn | -0.012 |
chie | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
run | +0.042 |
igsaw | +0.041 |
block | +0.039 |
nail | +0.038 |
pad | +0.037 |
Neg logit contributions | |
Amen | -0.040 |
cle | -0.039 |
ting | -0.038 |
Mr | -0.037 |
Merry | -0.036 |
Token | fun |
Token ID | 1257 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
run | +0.006 |
igsaw | +0.005 |
block | +0.005 |
nail | +0.005 |
pad | +0.005 |
Neg logit contributions | |
Amen | -0.007 |
cle | -0.007 |
ting | -0.007 |
Mr | -0.007 |
Merry | -0.007 |
Token | pictures |
Token ID | 5986 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
run | +0.023 |
igsaw | +0.022 |
block | +0.021 |
nail | +0.021 |
pad | +0.020 |
Neg logit contributions | |
Amen | -0.017 |
cle | -0.016 |
ting | -0.016 |
Mr | -0.015 |
Merry | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
Amen | +0.012 |
cle | +0.012 |
Mr | +0.011 |
ting | +0.011 |
Merry | +0.011 |
Neg logit contributions | |
run | -0.019 |
igsaw | -0.018 |
block | -0.018 |
nail | -0.017 |
pad | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
run | +0.054 |
igsaw | +0.053 |
block | +0.051 |
nail | +0.050 |
pad | +0.048 |
Neg logit contributions | |
Amen | -0.044 |
cle | -0.042 |
ting | -0.041 |
Mr | -0.039 |
Merry | -0.039 |
Token | black |
Token ID | 2042 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
run | +0.023 |
igsaw | +0.022 |
block | +0.020 |
nail | +0.020 |
pad | +0.019 |
Neg logit contributions | |
Amen | -0.044 |
cle | -0.044 |
ting | -0.043 |
Mr | -0.042 |
Merry | -0.041 |
Token | board |
Token ID | 3526 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
run | +0.093 |
igsaw | +0.080 |
nail | +0.075 |
block | +0.072 |
Half | +0.072 |
Neg logit contributions | |
cle | -0.149 |
ting | -0.148 |
Amen | -0.146 |
sets | -0.143 |
They | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
run | +0.074 |
igsaw | +0.072 |
block | +0.070 |
nail | +0.069 |
pad | +0.068 |
Neg logit contributions | |
Amen | -0.038 |
cle | -0.037 |
ting | -0.035 |
Mr | -0.034 |
Merry | -0.033 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
Amen | +0.003 |
cle | +0.003 |
ting | +0.003 |
Mr | +0.003 |
They | +0.003 |
Neg logit contributions | |
run | -0.003 |
igsaw | -0.003 |
block | -0.003 |
nail | -0.003 |
ooter | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
run | +0.016 |
block | +0.015 |
igsaw | +0.015 |
nail | +0.015 |
pad | +0.015 |
Neg logit contributions | |
Amen | -0.014 |
cle | -0.013 |
ting | -0.013 |
Merry | -0.012 |
Mr | -0.012 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
igsaw | +0.013 |
run | +0.013 |
ooter | +0.013 |
inter | +0.013 |
nail | +0.012 |
Neg logit contributions | |
They | -0.010 |
Mr | -0.010 |
Merry | -0.009 |
Santa | -0.009 |
ting | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
Amen | +0.010 |
cle | +0.010 |
ting | +0.009 |
Mr | +0.009 |
Merry | +0.009 |
Neg logit contributions | |
run | -0.016 |
igsaw | -0.015 |
block | -0.015 |
nail | -0.015 |
pad | -0.014 |
Token | stove |
Token ID | 27635 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
run | +0.001 |
block | +0.001 |
igsaw | +0.001 |
nail | +0.001 |
inter | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
cle | -0.001 |
ting | -0.001 |
Mr | -0.001 |
Merry | -0.001 |
Token | just |
Token ID | 655 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
Amen | +0.006 |
cle | +0.005 |
Mr | +0.005 |
ting | +0.005 |
Merry | +0.005 |
Neg logit contributions | |
run | -0.006 |
block | -0.005 |
nail | -0.005 |
igsaw | -0.005 |
pad | -0.005 |
Token | wasn |
Token ID | 2492 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
run | +0.042 |
block | +0.039 |
nail | +0.038 |
igsaw | +0.037 |
pad | +0.036 |
Neg logit contributions | |
Amen | -0.053 |
cle | -0.050 |
Mr | -0.048 |
Miss | -0.047 |
They | -0.046 |
Token | 't |
Token ID | 470 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
run | +0.038 |
igsaw | +0.038 |
inter | +0.035 |
pad | +0.035 |
nail | +0.035 |
Neg logit contributions | |
Amen | -0.024 |
Mr | -0.023 |
They | -0.022 |
ting | -0.022 |
cle | -0.022 |
Token | there |
Token ID | 612 |
Feature activation | -4.11e+00 |
Pos logit contributions | |
igsaw | +0.036 |
run | +0.035 |
ooter | +0.033 |
inter | +0.032 |
block | +0.031 |
Neg logit contributions | |
cle | -0.029 |
Amen | -0.029 |
ting | -0.029 |
Santa | -0.028 |
They | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +7.88e-02 |
Pos logit contributions | |
run | +0.134 |
block | +0.126 |
pad | +0.124 |
igsaw | +0.123 |
nail | +0.123 |
Neg logit contributions | |
Amen | -0.094 |
cle | -0.088 |
Mr | -0.083 |
ting | -0.080 |
They | -0.079 |
Token | They |
Token ID | 1119 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Amen | +0.002 |
They | +0.002 |
ting | +0.002 |
Merry | +0.002 |
Mr | +0.002 |
Neg logit contributions | |
run | -0.003 |
igsaw | -0.003 |
nail | -0.002 |
block | -0.002 |
ooter | -0.002 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Amen | +0.009 |
ting | +0.008 |
cle | +0.008 |
Mr | +0.008 |
They | +0.008 |
Neg logit contributions | |
run | -0.010 |
igsaw | -0.010 |
block | -0.009 |
nail | -0.009 |
ooter | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
run | +0.005 |
igsaw | +0.005 |
block | +0.005 |
nail | +0.005 |
pad | +0.005 |
Neg logit contributions | |
cle | -0.006 |
Amen | -0.006 |
ting | -0.006 |
Mr | -0.005 |
123 | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
Amen | +0.027 |
cle | +0.026 |
ting | +0.026 |
Mr | +0.025 |
Merry | +0.024 |
Neg logit contributions | |
run | -0.036 |
igsaw | -0.035 |
block | -0.033 |
nail | -0.033 |
ooter | -0.033 |