Token | Cr |
Token ID | 3864 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
aj | +0.021 |
ittens | +0.016 |
omed | +0.015 |
atmeal | +0.014 |
inc | +0.014 |
Neg logit contributions | |
baby | -0.018 |
tered | -0.017 |
generation | -0.017 |
Welcome | -0.016 |
infant | -0.016 |
Token | ust |
Token ID | 436 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
baby | +0.040 |
tered | +0.038 |
generation | +0.037 |
infant | +0.036 |
Welcome | +0.036 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.023 |
udd | -0.021 |
omed | -0.021 |
inc | -0.021 |
Token | y |
Token ID | 88 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
Promise | +0.086 |
passer | +0.085 |
Welcome | +0.082 |
infant | +0.079 |
tered | +0.079 |
Neg logit contributions | |
aj | -0.120 |
inc | -0.106 |
endant | -0.104 |
ig | -0.103 |
c | -0.100 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
tered | +0.017 |
baby | +0.017 |
generation | +0.016 |
decides | +0.016 |
Welcome | +0.015 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.015 |
omed | -0.013 |
inc | -0.013 |
igs | -0.013 |
Token | Cr |
Token ID | 3864 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
baby | +0.041 |
tered | +0.040 |
generation | +0.039 |
infant | +0.037 |
decides | +0.037 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.016 |
omed | -0.015 |
inc | -0.015 |
igs | -0.014 |
Token | ust |
Token ID | 436 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
baby | +0.050 |
tered | +0.048 |
generation | +0.046 |
Welcome | +0.046 |
infant | +0.045 |
Neg logit contributions | |
aj | -0.035 |
ittens | -0.025 |
udd | -0.024 |
inc | -0.023 |
omed | -0.023 |
Token | y |
Token ID | 88 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
passer | +0.120 |
Welcome | +0.113 |
baby | +0.109 |
Promise | +0.105 |
infant | +0.104 |
Neg logit contributions | |
aj | -0.134 |
endant | -0.123 |
ig | -0.120 |
c | -0.119 |
adow | -0.117 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
baby | +0.004 |
tered | +0.004 |
generation | +0.004 |
decides | +0.004 |
infant | +0.003 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.010 |
omed | -0.009 |
inc | -0.009 |
atmeal | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -4.94e-03 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.002 |
ittens | -0.002 |
omed | -0.002 |
inc | -0.002 |
atmeal | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
aj | +0.011 |
ittens | +0.010 |
omed | +0.009 |
atmeal | +0.009 |
inc | +0.009 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.004 |
infant | -0.004 |
decides | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
aj | +0.008 |
ittens | +0.006 |
omed | +0.006 |
atmeal | +0.006 |
inc | +0.006 |
Neg logit contributions | |
baby | -0.004 |
tered | -0.004 |
generation | -0.004 |
decides | -0.003 |
infant | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
tered | +0.015 |
baby | +0.015 |
generation | +0.015 |
Welcome | +0.013 |
infant | +0.013 |
Neg logit contributions | |
aj | -0.027 |
ittens | -0.022 |
omed | -0.021 |
atmeal | -0.021 |
inc | -0.020 |
Token | sure |
Token ID | 1654 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
tered | +0.041 |
generation | +0.040 |
Welcome | +0.037 |
decides | +0.036 |
ancy | +0.036 |
Neg logit contributions | |
aj | -0.053 |
ittens | -0.043 |
Johnny | -0.041 |
dizz | -0.040 |
igs | -0.040 |
Token | to |
Token ID | 284 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
tered | +0.015 |
baby | +0.014 |
generation | +0.014 |
decides | +0.013 |
Welcome | +0.013 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.020 |
omed | -0.019 |
fing | -0.018 |
inc | -0.018 |
Token | always |
Token ID | 1464 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
tered | +0.041 |
baby | +0.039 |
Welcome | +0.037 |
generation | +0.036 |
decides | +0.035 |
Neg logit contributions | |
aj | -0.070 |
ittens | -0.058 |
fing | -0.056 |
igs | -0.054 |
atmeal | -0.053 |
Token | keep |
Token ID | 1394 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
tered | +0.048 |
baby | +0.046 |
ancy | +0.042 |
generation | +0.042 |
infant | +0.041 |
Neg logit contributions | |
aj | -0.069 |
fing | -0.057 |
ittens | -0.054 |
atmeal | -0.052 |
vest | -0.052 |
Token | an |
Token ID | 281 |
Feature activation | +8.89e-02 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.013 |
generation | +0.013 |
decides | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.020 |
ittens | -0.016 |
omed | -0.015 |
igs | -0.015 |
Johnny | -0.015 |
Token | eye |
Token ID | 4151 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
Welcome | +0.140 |
vows | +0.138 |
Prize | +0.135 |
Who | +0.134 |
tered | +0.128 |
Neg logit contributions | |
aj | -0.126 |
ittens | -0.114 |
vest | -0.106 |
ivering | -0.102 |
udd | -0.096 |
Token | on |
Token ID | 319 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
aj | +0.013 |
ittens | +0.010 |
omed | +0.010 |
inc | +0.010 |
atmeal | +0.010 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.005 |
infant | -0.005 |
decides | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
tered | +0.024 |
baby | +0.023 |
generation | +0.023 |
decides | +0.022 |
Welcome | +0.021 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.031 |
omed | -0.028 |
inc | -0.027 |
igs | -0.027 |
Token | puppy |
Token ID | 26188 |
Feature activation | +1.69e-04 |
Pos logit contributions | |
tered | +0.015 |
baby | +0.014 |
generation | +0.014 |
decides | +0.013 |
Whoever | +0.013 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.020 |
omed | -0.018 |
inc | -0.017 |
uddle | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.000 |
ittens | -0.000 |
omed | -0.000 |
atmeal | -0.000 |
inc | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
tered | +0.012 |
baby | +0.011 |
generation | +0.011 |
decides | +0.010 |
Welcome | +0.010 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.014 |
omed | -0.013 |
Johnny | -0.013 |
igs | -0.012 |
Token | park |
Token ID | 3952 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
tered | +0.016 |
baby | +0.016 |
generation | +0.015 |
decides | +0.014 |
Welcome | +0.014 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.013 |
omed | -0.012 |
atmeal | -0.012 |
uddle | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.010 |
generation | +0.009 |
decides | +0.009 |
infant | +0.009 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.009 |
omed | -0.009 |
inc | -0.008 |
atmeal | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
baby | +0.011 |
tered | +0.011 |
generation | +0.010 |
infant | +0.010 |
decides | +0.009 |
Neg logit contributions | |
aj | -0.015 |
ittens | -0.012 |
omed | -0.012 |
inc | -0.011 |
atmeal | -0.011 |
Token | chased |
Token ID | 26172 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
generation | +0.036 |
tered | +0.036 |
baby | +0.035 |
infant | +0.033 |
example | +0.032 |
Neg logit contributions | |
aj | -0.050 |
ittens | -0.040 |
omed | -0.039 |
mo | -0.039 |
Johnny | -0.038 |
Token | each |
Token ID | 1123 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
aj | +0.010 |
ittens | +0.008 |
omed | +0.008 |
atmeal | +0.008 |
inc | +0.008 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.002 |
infant | -0.002 |
decides | -0.002 |
Token | other |
Token ID | 584 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
vows | +0.137 |
rier | +0.131 |
Amen | +0.129 |
generation | +0.129 |
aciously | +0.127 |
Neg logit contributions | |
ittens | -0.100 |
aj | -0.090 |
c | -0.089 |
ig | -0.089 |
ons | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
generation | +0.061 |
baby | +0.058 |
decides | +0.058 |
tered | +0.058 |
Welcome | +0.055 |
Neg logit contributions | |
aj | -0.067 |
ittens | -0.053 |
omed | -0.048 |
mers | -0.048 |
uddle | -0.048 |
Token | laughed |
Token ID | 13818 |
Feature activation | +4.18e-03 |
Pos logit contributions | |
baby | +0.024 |
generation | +0.024 |
tered | +0.024 |
infant | +0.022 |
decides | +0.022 |
Neg logit contributions | |
aj | -0.028 |
ittens | -0.022 |
omed | -0.021 |
Johnny | -0.020 |
inc | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
baby | +0.005 |
tered | +0.005 |
generation | +0.005 |
decides | +0.005 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.008 |
ittens | -0.007 |
omed | -0.006 |
inc | -0.006 |
atmeal | -0.006 |
Token | But |
Token ID | 887 |
Feature activation | +2.40e-03 |
Pos logit contributions | |
baby | +0.013 |
tered | +0.012 |
generation | +0.012 |
infant | +0.011 |
decides | +0.010 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.019 |
omed | -0.019 |
inc | -0.018 |
Johnny | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
baby | +0.005 |
tered | +0.005 |
generation | +0.005 |
infant | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
aj | -0.011 |
ittens | -0.009 |
omed | -0.008 |
atmeal | -0.008 |
inc | -0.008 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
tered | +0.027 |
generation | +0.025 |
baby | +0.025 |
Whoever | +0.024 |
decides | +0.023 |
Neg logit contributions | |
aj | -0.027 |
ittens | -0.021 |
Johnny | -0.019 |
vest | -0.018 |
atmeal | -0.018 |
Token | liked |
Token ID | 8288 |
Feature activation | +5.59e-04 |
Pos logit contributions | |
baby | +0.017 |
tered | +0.017 |
generation | +0.016 |
infant | +0.014 |
Welcome | +0.014 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.025 |
omed | -0.024 |
atmeal | -0.023 |
inc | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
atmeal | -0.001 |
inc | -0.001 |
Token | race |
Token ID | 3234 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
aj | +0.018 |
ittens | +0.015 |
omed | +0.014 |
inc | +0.013 |
uddle | +0.013 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.010 |
generation | -0.009 |
decides | -0.009 |
infant | -0.009 |
Token | each |
Token ID | 1123 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
aj | +0.004 |
ittens | +0.003 |
omed | +0.003 |
atmeal | +0.003 |
inc | +0.003 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.002 |
Token | other |
Token ID | 584 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
vows | +0.152 |
ancy | +0.144 |
rily | +0.143 |
Amelia | +0.140 |
rier | +0.139 |
Neg logit contributions | |
--- | -0.078 |
Once | -0.074 |
ons | -0.073 |
? | -0.072 |
ittens | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +9.96e-03 |
Pos logit contributions | |
baby | +0.046 |
generation | +0.046 |
tered | +0.045 |
decides | +0.043 |
Whoever | +0.042 |
Neg logit contributions | |
aj | -0.042 |
ittens | -0.030 |
omed | -0.029 |
mers | -0.027 |
--- | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.007 |
generation | +0.007 |
decides | +0.006 |
infant | +0.006 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.020 |
omed | -0.020 |
inc | -0.019 |
atmeal | -0.019 |
Token | ran |
Token ID | 4966 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
generation | +0.028 |
baby | +0.028 |
tered | +0.027 |
infant | +0.026 |
ancy | +0.025 |
Neg logit contributions | |
aj | -0.038 |
ittens | -0.032 |
omed | -0.030 |
mers | -0.030 |
fing | -0.029 |
Token | fast |
Token ID | 3049 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
generation | +0.065 |
baby | +0.063 |
infant | +0.059 |
decides | +0.059 |
vows | +0.057 |
Neg logit contributions | |
aj | -0.060 |
dizz | -0.048 |
inc | -0.047 |
omed | -0.046 |
mers | -0.045 |
Token | lake |
Token ID | 13546 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
aj | +0.056 |
ittens | +0.049 |
inc | +0.042 |
omed | +0.042 |
atmeal | +0.041 |
Neg logit contributions | |
baby | -0.041 |
decides | -0.036 |
generation | -0.035 |
Welcome | -0.035 |
person | -0.033 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.014 |
generation | +0.013 |
decides | +0.012 |
infant | +0.012 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.019 |
omed | -0.018 |
inc | -0.017 |
atmeal | -0.017 |
Token | |
Token ID | 220 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
tered | +0.018 |
baby | +0.018 |
generation | +0.018 |
decides | +0.017 |
infant | +0.017 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.013 |
omed | -0.013 |
inc | -0.012 |
atmeal | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
tered | +0.036 |
baby | +0.036 |
generation | +0.035 |
decides | +0.033 |
infant | +0.033 |
Neg logit contributions | |
aj | -0.042 |
ittens | -0.032 |
omed | -0.030 |
inc | -0.029 |
uddle | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
tered | +0.068 |
baby | +0.067 |
generation | +0.066 |
decides | +0.064 |
infant | +0.064 |
Neg logit contributions | |
aj | -0.048 |
ittens | -0.036 |
Johnny | -0.035 |
inc | -0.032 |
omed | -0.032 |
Token | Iss |
Token ID | 27738 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
baby | +0.053 |
tered | +0.051 |
generation | +0.049 |
Welcome | +0.049 |
infant | +0.049 |
Neg logit contributions | |
aj | -0.041 |
ittens | -0.032 |
Johnny | -0.032 |
fing | -0.031 |
inc | -0.030 |
Token | y |
Token ID | 88 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
Welcome | +0.132 |
Enjoy | +0.131 |
generation | +0.124 |
Bye | +0.117 |
Sale | +0.117 |
Neg logit contributions | |
aj | -0.120 |
c | -0.107 |
ig | -0.104 |
ak | -0.093 |
light | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
generation | +0.027 |
baby | +0.026 |
tered | +0.025 |
Welcome | +0.024 |
infant | +0.023 |
Neg logit contributions | |
aj | -0.048 |
ittens | -0.038 |
omed | -0.036 |
uddle | -0.035 |
inc | -0.035 |
Token | so |
Token ID | 523 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
generation | +0.030 |
tered | +0.029 |
baby | +0.027 |
decides | +0.027 |
Whoever | +0.026 |
Neg logit contributions | |
aj | -0.034 |
ittens | -0.026 |
omed | -0.025 |
inc | -0.023 |
dizz | -0.023 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
generation | +0.025 |
tered | +0.023 |
baby | +0.022 |
infant | +0.021 |
decides | +0.021 |
Neg logit contributions | |
aj | -0.033 |
ittens | -0.026 |
omed | -0.024 |
inc | -0.024 |
dizz | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
aj | +0.055 |
ittens | +0.046 |
omed | +0.044 |
atmeal | +0.044 |
igs | +0.043 |
Neg logit contributions | |
baby | -0.019 |
tered | -0.017 |
generation | -0.015 |
Welcome | -0.014 |
infant | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
aj | +0.008 |
ittens | +0.007 |
omed | +0.006 |
atmeal | +0.006 |
inc | +0.006 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.005 |
decides | -0.005 |
Welcome | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | +7.81e-03 |
Pos logit contributions | |
baby | +0.018 |
tered | +0.018 |
generation | +0.017 |
infant | +0.016 |
decides | +0.016 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.020 |
omed | -0.019 |
inc | -0.019 |
igs | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
tered | +0.008 |
baby | +0.008 |
generation | +0.008 |
decides | +0.007 |
Whoever | +0.007 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.014 |
omed | -0.013 |
atmeal | -0.013 |
inc | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
generation | +0.044 |
baby | +0.044 |
tered | +0.042 |
infant | +0.041 |
decides | +0.040 |
Neg logit contributions | |
aj | -0.038 |
ittens | -0.030 |
omed | -0.030 |
inc | -0.028 |
igs | -0.026 |
Token | Cr |
Token ID | 3864 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
baby | +0.035 |
generation | +0.034 |
tered | +0.034 |
decides | +0.032 |
infant | +0.032 |
Neg logit contributions | |
aj | -0.028 |
ittens | -0.023 |
omed | -0.021 |
inc | -0.021 |
dizz | -0.020 |
Token | ust |
Token ID | 436 |
Feature activation | +8.64e-02 |
Pos logit contributions | |
baby | +0.057 |
tered | +0.055 |
generation | +0.053 |
Welcome | +0.052 |
infant | +0.051 |
Neg logit contributions | |
aj | -0.038 |
udd | -0.026 |
ittens | -0.026 |
inc | -0.025 |
uddle | -0.024 |
Token | y |
Token ID | 88 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
passer | +0.124 |
Welcome | +0.111 |
person | +0.111 |
Promise | +0.110 |
infant | +0.110 |
Neg logit contributions | |
aj | -0.128 |
light | -0.115 |
adow | -0.114 |
inc | -0.113 |
ig | -0.113 |
Token | found |
Token ID | 1043 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
baby | +0.002 |
tered | +0.002 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.003 |
ittens | -0.002 |
omed | -0.002 |
inc | -0.002 |
atmeal | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.014 |
generation | +0.013 |
decides | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.018 |
omed | -0.017 |
inc | -0.016 |
igs | -0.016 |
Token | shiny |
Token ID | 22441 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
tered | +0.022 |
generation | +0.020 |
baby | +0.020 |
decides | +0.019 |
Welcome | +0.019 |
Neg logit contributions | |
aj | -0.029 |
ittens | -0.022 |
uddle | -0.021 |
omed | -0.021 |
inc | -0.021 |
Token | shell |
Token ID | 7582 |
Feature activation | -7.66e-04 |
Pos logit contributions | |
tered | +0.030 |
baby | +0.029 |
generation | +0.028 |
Welcome | +0.027 |
decides | +0.027 |
Neg logit contributions | |
aj | -0.027 |
ittens | -0.021 |
uddle | -0.019 |
igs | -0.019 |
omed | -0.019 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
generation | +0.044 |
tered | +0.042 |
Whoever | +0.041 |
baby | +0.039 |
decides | +0.038 |
Neg logit contributions | |
aj | -0.042 |
dizz | -0.032 |
ittens | -0.030 |
inc | -0.029 |
mo | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -6.26e-03 |
Pos logit contributions | |
aj | +0.066 |
ittens | +0.056 |
omed | +0.054 |
atmeal | +0.051 |
igs | +0.050 |
Neg logit contributions | |
baby | -0.027 |
tered | -0.023 |
generation | -0.021 |
Welcome | -0.021 |
infant | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
aj | +0.014 |
ittens | +0.011 |
omed | +0.011 |
atmeal | +0.010 |
inc | +0.010 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.007 |
generation | -0.006 |
Welcome | -0.006 |
decides | -0.006 |
Token | thanked |
Token ID | 26280 |
Feature activation | -2.18e-03 |
Pos logit contributions | |
baby | +0.011 |
tered | +0.011 |
generation | +0.011 |
infant | +0.010 |
Welcome | +0.009 |
Neg logit contributions | |
aj | -0.020 |
ittens | -0.016 |
omed | -0.015 |
inc | -0.015 |
atmeal | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
aj | +0.005 |
ittens | +0.004 |
omed | +0.004 |
inc | +0.003 |
atmeal | +0.003 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.002 |
Token | kind |
Token ID | 1611 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
tered | +0.057 |
Whoever | +0.048 |
Drop | +0.048 |
generation | +0.048 |
ively | +0.047 |
Neg logit contributions | |
aj | -0.073 |
dizz | -0.071 |
vest | -0.070 |
gum | -0.067 |
mask | -0.065 |
Token | person |
Token ID | 1048 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
tered | +0.097 |
Welcome | +0.097 |
Drop | +0.097 |
sc | +0.094 |
Whoever | +0.092 |
Neg logit contributions | |
ott | -0.102 |
aj | -0.100 |
? | -0.098 |
vest | -0.095 |
ister | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +2.79e-05 |
Pos logit contributions | |
tered | +0.039 |
generation | +0.037 |
baby | +0.037 |
decides | +0.035 |
Whoever | +0.035 |
Neg logit contributions | |
aj | -0.054 |
ittens | -0.044 |
omed | -0.041 |
fing | -0.040 |
atmeal | -0.039 |
Token | From |
Token ID | 3574 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.000 |
ittens | -0.000 |
omed | -0.000 |
atmeal | -0.000 |
inc | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
aj | +0.034 |
ittens | +0.028 |
omed | +0.028 |
atmeal | +0.027 |
inc | +0.026 |
Neg logit contributions | |
baby | -0.015 |
tered | -0.014 |
decides | -0.013 |
generation | -0.013 |
infant | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
tered | +0.028 |
baby | +0.027 |
generation | +0.026 |
vows | +0.026 |
Whoever | +0.026 |
Neg logit contributions | |
aj | -0.040 |
ittens | -0.033 |
fing | -0.031 |
omed | -0.030 |
atmeal | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
baby | +0.023 |
tered | +0.023 |
generation | +0.023 |
Welcome | +0.020 |
infant | +0.020 |
Neg logit contributions | |
aj | -0.044 |
ittens | -0.035 |
omed | -0.034 |
inc | -0.033 |
atmeal | -0.032 |
Token | being |
Token ID | 852 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
tered | +0.020 |
baby | +0.019 |
generation | +0.018 |
decides | +0.018 |
Whoever | +0.018 |
Neg logit contributions | |
aj | -0.028 |
ittens | -0.022 |
omed | -0.022 |
inc | -0.021 |
fing | -0.020 |
Token | held |
Token ID | 2714 |
Feature activation | +8.71e-03 |
Pos logit contributions | |
tered | +0.016 |
baby | +0.015 |
generation | +0.015 |
decides | +0.014 |
Whoever | +0.014 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.017 |
omed | -0.017 |
inc | -0.016 |
fing | -0.016 |
Token | captive |
Token ID | 25798 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.010 |
generation | +0.009 |
decides | +0.009 |
Welcome | +0.008 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.015 |
omed | -0.014 |
inc | -0.014 |
igs | -0.013 |
Token | by |
Token ID | 416 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
baby | +0.032 |
tered | +0.031 |
generation | +0.031 |
Whoever | +0.029 |
decides | +0.029 |
Neg logit contributions | |
aj | -0.039 |
ittens | -0.029 |
omed | -0.028 |
inc | -0.026 |
igs | -0.026 |
Token | an |
Token ID | 281 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
tered | +0.011 |
baby | +0.011 |
generation | +0.010 |
decides | +0.010 |
Welcome | +0.010 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.014 |
omed | -0.014 |
inc | -0.013 |
igs | -0.013 |
Token | evil |
Token ID | 6181 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
Welcome | +0.136 |
Whoever | +0.135 |
Enjoy | +0.133 |
vows | +0.132 |
Let | +0.132 |
Neg logit contributions | |
aj | -0.093 |
unatt | -0.084 |
endant | -0.083 |
vest | -0.080 |
ak | -0.077 |
Token | witch |
Token ID | 16365 |
Feature activation | -1.79e-03 |
Pos logit contributions | |
tered | +0.026 |
baby | +0.023 |
generation | +0.023 |
Whoever | +0.022 |
decides | +0.022 |
Neg logit contributions | |
aj | -0.040 |
ittens | -0.032 |
omed | -0.030 |
inc | -0.030 |
fing | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -8.65e-03 |
Pos logit contributions | |
aj | +0.003 |
ittens | +0.003 |
omed | +0.003 |
atmeal | +0.002 |
inc | +0.002 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.002 |
Token | Jill |
Token ID | 22772 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
aj | +0.016 |
ittens | +0.012 |
omed | +0.011 |
atmeal | +0.011 |
igs | +0.011 |
Neg logit contributions | |
tered | -0.013 |
baby | -0.013 |
generation | -0.012 |
decides | -0.011 |
Welcome | -0.011 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
generation | +0.037 |
baby | +0.036 |
tered | +0.035 |
Welcome | +0.035 |
ancy | +0.034 |
Neg logit contributions | |
aj | -0.059 |
omed | -0.047 |
ittens | -0.046 |
inc | -0.046 |
mers | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
aj | +0.004 |
ittens | +0.004 |
omed | +0.003 |
atmeal | +0.003 |
inc | +0.003 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.003 |
infant | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
aj | +0.009 |
ittens | +0.008 |
omed | +0.007 |
inc | +0.007 |
atmeal | +0.007 |
Neg logit contributions | |
baby | -0.004 |
tered | -0.004 |
generation | -0.004 |
infant | -0.004 |
Welcome | -0.004 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
baby | +0.015 |
tered | +0.015 |
generation | +0.015 |
infant | +0.014 |
decides | +0.014 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.019 |
omed | -0.018 |
atmeal | -0.018 |
inc | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -5.42e-03 |
Pos logit contributions | |
generation | +0.050 |
baby | +0.049 |
infant | +0.045 |
tered | +0.045 |
decides | +0.045 |
Neg logit contributions | |
aj | -0.054 |
ittens | -0.041 |
inc | -0.041 |
omed | -0.041 |
dizz | -0.040 |
Token | chased |
Token ID | 26172 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
aj | +0.011 |
ittens | +0.009 |
omed | +0.009 |
atmeal | +0.008 |
inc | +0.008 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.006 |
decides | -0.005 |
Welcome | -0.005 |
Token | each |
Token ID | 1123 |
Feature activation | +8.56e-02 |
Pos logit contributions | |
baby | +0.011 |
generation | +0.010 |
tered | +0.010 |
decides | +0.009 |
Welcome | +0.009 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.022 |
omed | -0.020 |
igs | -0.020 |
inc | -0.020 |
Token | other |
Token ID | 584 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
vows | +0.146 |
lder | +0.139 |
generation | +0.139 |
Amen | +0.139 |
person | +0.136 |
Neg logit contributions | |
ittens | -0.081 |
--- | -0.078 |
Sam | -0.077 |
Once | -0.076 |
jam | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
generation | +0.045 |
baby | +0.045 |
tered | +0.043 |
decides | +0.043 |
Welcome | +0.042 |
Neg logit contributions | |
aj | -0.046 |
ittens | -0.035 |
omed | -0.033 |
igs | -0.031 |
inc | -0.031 |
Token | laughing |
Token ID | 14376 |
Feature activation | +5.86e-03 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.008 |
generation | +0.007 |
decides | +0.007 |
infant | +0.007 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.005 |
omed | -0.005 |
inc | -0.004 |
atmeal | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
baby | +0.007 |
tered | +0.007 |
generation | +0.007 |
decides | +0.006 |
Welcome | +0.006 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.010 |
omed | -0.009 |
inc | -0.009 |
atmeal | -0.009 |
Token | shouting |
Token ID | 19642 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
tered | +0.011 |
baby | +0.011 |
generation | +0.011 |
decides | +0.010 |
infant | +0.010 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.014 |
omed | -0.013 |
inc | -0.012 |
atmeal | -0.012 |
Token | bought |
Token ID | 5839 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
tered | +0.020 |
generation | +0.019 |
baby | +0.019 |
decides | +0.018 |
infant | +0.018 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.020 |
omed | -0.019 |
atmeal | -0.018 |
inc | -0.018 |
Token | some |
Token ID | 617 |
Feature activation | +8.01e-03 |
Pos logit contributions | |
generation | +0.080 |
tered | +0.075 |
decides | +0.071 |
ny | +0.069 |
infant | +0.068 |
Neg logit contributions | |
aj | -0.075 |
ittens | -0.061 |
omed | -0.060 |
ons | -0.057 |
fing | -0.056 |
Token | fun |
Token ID | 1257 |
Feature activation | -4.68e-03 |
Pos logit contributions | |
tered | +0.011 |
baby | +0.011 |
generation | +0.011 |
decides | +0.010 |
Welcome | +0.010 |
Neg logit contributions | |
aj | -0.015 |
ittens | -0.012 |
omed | -0.011 |
igs | -0.010 |
atmeal | -0.010 |
Token | beach |
Token ID | 10481 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
aj | +0.008 |
ittens | +0.007 |
omed | +0.006 |
inc | +0.006 |
atmeal | +0.006 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.007 |
generation | -0.006 |
decides | -0.006 |
Welcome | -0.006 |
Token | toys |
Token ID | 14958 |
Feature activation | -5.66e-03 |
Pos logit contributions | |
aj | +0.050 |
ittens | +0.042 |
omed | +0.040 |
igs | +0.037 |
Johnny | +0.037 |
Neg logit contributions | |
baby | -0.031 |
tered | -0.028 |
generation | -0.026 |
vows | -0.025 |
Welcome | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +8.45e-02 |
Pos logit contributions | |
aj | +0.011 |
ittens | +0.009 |
omed | +0.008 |
atmeal | +0.008 |
inc | +0.008 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.007 |
generation | -0.007 |
decides | -0.006 |
Welcome | -0.006 |
Token | Lib |
Token ID | 7980 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
urtle | +0.117 |
baby | +0.112 |
y | +0.111 |
mate | +0.110 |
ley | +0.110 |
Neg logit contributions | |
aj | -0.106 |
omed | -0.090 |
inc | -0.089 |
� | -0.083 |
There | -0.081 |
Token | by |
Token ID | 1525 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
tered | +0.066 |
Welcome | +0.060 |
generation | +0.058 |
Give | +0.057 |
Prize | +0.056 |
Neg logit contributions | |
aj | -0.082 |
ittens | -0.059 |
ig | -0.058 |
udd | -0.056 |
omed | -0.056 |
Token | was |
Token ID | 373 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
tered | +0.019 |
generation | +0.018 |
baby | +0.018 |
Welcome | +0.017 |
infant | +0.016 |
Neg logit contributions | |
aj | -0.038 |
ittens | -0.030 |
omed | -0.028 |
inc | -0.028 |
atmeal | -0.028 |
Token | so |
Token ID | 523 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
generation | +0.032 |
tered | +0.031 |
decides | +0.029 |
baby | +0.029 |
Whoever | +0.029 |
Neg logit contributions | |
aj | -0.041 |
ittens | -0.031 |
dizz | -0.029 |
inc | -0.029 |
omed | -0.029 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
generation | +0.046 |
tered | +0.042 |
decides | +0.039 |
baby | +0.039 |
infant | +0.039 |
Neg logit contributions | |
aj | -0.049 |
dizz | -0.037 |
ittens | -0.036 |
inc | -0.035 |
omed | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | +8.37e-03 |
Pos logit contributions | |
baby | +0.016 |
tered | +0.015 |
generation | +0.015 |
infant | +0.014 |
decides | +0.014 |
Neg logit contributions | |
aj | -0.020 |
ittens | -0.016 |
omed | -0.015 |
inc | -0.014 |
Johnny | -0.014 |
Token | They |
Token ID | 2990 |
Feature activation | -6.57e-03 |
Pos logit contributions | |
baby | +0.015 |
tered | +0.015 |
generation | +0.015 |
infant | +0.014 |
decides | +0.014 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.009 |
omed | -0.008 |
inc | -0.008 |
Johnny | -0.008 |
Token | laughed |
Token ID | 13818 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
aj | +0.014 |
ittens | +0.011 |
omed | +0.011 |
atmeal | +0.010 |
inc | +0.010 |
Neg logit contributions | |
tered | -0.008 |
baby | -0.008 |
generation | -0.007 |
decides | -0.007 |
infant | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
aj | +0.012 |
ittens | +0.010 |
omed | +0.009 |
atmeal | +0.009 |
inc | +0.009 |
Neg logit contributions | |
tered | -0.005 |
baby | -0.005 |
generation | -0.004 |
decides | -0.004 |
infant | -0.004 |
Token | chased |
Token ID | 26172 |
Feature activation | +7.22e-03 |
Pos logit contributions | |
aj | +0.038 |
ittens | +0.030 |
omed | +0.029 |
atmeal | +0.028 |
inc | +0.028 |
Neg logit contributions | |
tered | -0.022 |
baby | -0.022 |
generation | -0.019 |
decides | -0.018 |
infant | -0.017 |
Token | each |
Token ID | 1123 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
tered | +0.007 |
baby | +0.007 |
generation | +0.007 |
Welcome | +0.007 |
decides | +0.007 |
Neg logit contributions | |
aj | -0.015 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
igs | -0.012 |
Token | other |
Token ID | 584 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
aciously | +0.140 |
vows | +0.138 |
lder | +0.132 |
ured | +0.129 |
ancy | +0.128 |
Neg logit contributions | |
ittens | -0.079 |
jam | -0.079 |
ons | -0.079 |
robat | -0.079 |
ede | -0.079 |
Token | around |
Token ID | 1088 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
baby | +0.025 |
tered | +0.024 |
generation | +0.024 |
decides | +0.023 |
infant | +0.022 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.026 |
omed | -0.024 |
inc | -0.023 |
igs | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +4.67e-03 |
Pos logit contributions | |
tered | +0.022 |
baby | +0.021 |
generation | +0.021 |
decides | +0.020 |
Whoever | +0.020 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.021 |
omed | -0.020 |
fing | -0.019 |
igs | -0.019 |
Token | yard |
Token ID | 12699 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
tered | +0.007 |
baby | +0.007 |
generation | +0.007 |
Welcome | +0.006 |
decides | +0.006 |
Neg logit contributions | |
aj | -0.008 |
ittens | -0.006 |
omed | -0.006 |
atmeal | -0.006 |
igs | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
baby | +0.022 |
tered | +0.022 |
generation | +0.021 |
decides | +0.021 |
infant | +0.020 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.019 |
omed | -0.019 |
inc | -0.018 |
uddle | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
aj | +0.129 |
omed | +0.112 |
igs | +0.109 |
inc | +0.108 |
atmeal | +0.108 |
Neg logit contributions | |
baby | -0.036 |
tered | -0.024 |
infant | -0.021 |
person | -0.018 |
each | -0.017 |
Token | wife |
Token ID | 3656 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
tered | +0.059 |
generation | +0.055 |
ively | +0.053 |
example | +0.051 |
urtle | +0.051 |
Neg logit contributions | |
aj | -0.070 |
ittens | -0.060 |
atmeal | -0.058 |
fing | -0.055 |
dizz | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
tered | +0.026 |
generation | +0.025 |
baby | +0.025 |
Whoever | +0.024 |
decides | +0.023 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.020 |
omed | -0.018 |
atmeal | -0.017 |
inc | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
tered | +0.008 |
baby | +0.008 |
generation | +0.007 |
infant | +0.006 |
decides | +0.006 |
Neg logit contributions | |
aj | -0.028 |
ittens | -0.024 |
omed | -0.023 |
inc | -0.022 |
atmeal | -0.022 |
Token | love |
Token ID | 1842 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
tered | +0.055 |
baby | +0.054 |
generation | +0.053 |
infant | +0.051 |
example | +0.049 |
Neg logit contributions | |
aj | -0.070 |
atmeal | -0.058 |
ittens | -0.057 |
fing | -0.054 |
mo | -0.053 |
Token | each |
Token ID | 1123 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
tered | +0.034 |
generation | +0.031 |
Whoever | +0.029 |
baby | +0.028 |
decides | +0.027 |
Neg logit contributions | |
aj | -0.050 |
ittens | -0.041 |
atmeal | -0.039 |
fing | -0.038 |
inc | -0.036 |
Token | other |
Token ID | 584 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
tered | +0.123 |
nown | +0.120 |
ified | +0.115 |
ured | +0.112 |
generation | +0.111 |
Neg logit contributions | |
ittens | -0.098 |
jam | -0.095 |
atmeal | -0.093 |
P | -0.091 |
moderation | -0.091 |
Token | very |
Token ID | 845 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
baby | +0.024 |
tered | +0.024 |
generation | +0.024 |
Whoever | +0.022 |
Welcome | +0.022 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.029 |
omed | -0.027 |
atmeal | -0.026 |
udd | -0.026 |
Token | much |
Token ID | 881 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
baby | +0.013 |
tered | +0.012 |
generation | +0.012 |
decides | +0.011 |
Whoever | +0.011 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.015 |
omed | -0.014 |
atmeal | -0.013 |
igs | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
tered | +0.026 |
baby | +0.026 |
generation | +0.025 |
Whoever | +0.024 |
decides | +0.024 |
Neg logit contributions | |
aj | -0.027 |
ittens | -0.020 |
omed | -0.019 |
igs | -0.017 |
inc | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
baby | +0.003 |
tered | +0.002 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.005 |
ittens | -0.004 |
omed | -0.004 |
inc | -0.004 |
atmeal | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.16e-04 |
Pos logit contributions | |
baby | +0.019 |
tered | +0.019 |
generation | +0.019 |
infant | +0.017 |
decides | +0.017 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.019 |
omed | -0.017 |
Johnny | -0.016 |
inc | -0.016 |
Token | They |
Token ID | 2990 |
Feature activation | +5.33e-04 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
inc | -0.001 |
atmeal | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
inc | -0.001 |
atmeal | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
tered | +0.055 |
generation | +0.053 |
ancy | +0.052 |
vows | +0.049 |
baby | +0.048 |
Neg logit contributions | |
aj | -0.061 |
dizz | -0.046 |
ittens | -0.046 |
inc | -0.046 |
fing | -0.045 |
Token | race |
Token ID | 3234 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
tered | +0.024 |
baby | +0.022 |
generation | +0.022 |
Welcome | +0.021 |
ancy | +0.021 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.025 |
fing | -0.024 |
vest | -0.023 |
Johnny | -0.023 |
Token | each |
Token ID | 1123 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
baby | +0.043 |
generation | +0.042 |
tered | +0.042 |
ancy | +0.042 |
infant | +0.041 |
Neg logit contributions | |
aj | -0.051 |
mers | -0.041 |
dizz | -0.041 |
--- | -0.041 |
fing | -0.041 |
Token | other |
Token ID | 584 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
vows | +0.132 |
ancy | +0.125 |
ured | +0.123 |
lder | +0.120 |
generation | +0.115 |
Neg logit contributions | |
ons | -0.096 |
ittens | -0.094 |
on | -0.093 |
ig | -0.093 |
vest | -0.089 |
Token | on |
Token ID | 319 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
baby | +0.056 |
generation | +0.055 |
tered | +0.053 |
infant | +0.051 |
decides | +0.051 |
Neg logit contributions | |
aj | -0.055 |
ittens | -0.041 |
omed | -0.041 |
dizz | -0.039 |
inc | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
tered | +0.052 |
Welcome | +0.051 |
decides | +0.051 |
generation | +0.050 |
baby | +0.049 |
Neg logit contributions | |
aj | -0.052 |
ittens | -0.042 |
igs | -0.039 |
omed | -0.039 |
Johnny | -0.037 |
Token | path |
Token ID | 3108 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
tered | +0.069 |
generation | +0.066 |
ancy | +0.062 |
Welcome | +0.062 |
baby | +0.061 |
Neg logit contributions | |
aj | -0.045 |
vest | -0.035 |
ittens | -0.035 |
uddle | -0.032 |
pants | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
baby | +0.054 |
generation | +0.051 |
tered | +0.051 |
infant | +0.050 |
decides | +0.048 |
Neg logit contributions | |
aj | -0.048 |
omed | -0.037 |
ittens | -0.036 |
inc | -0.034 |
mers | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.010 |
generation | +0.010 |
infant | +0.009 |
decides | +0.009 |
Neg logit contributions | |
aj | -0.014 |
ittens | -0.011 |
omed | -0.010 |
inc | -0.010 |
Johnny | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
baby | +0.004 |
tered | +0.004 |
generation | +0.004 |
decides | +0.004 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.005 |
ittens | -0.004 |
omed | -0.004 |
inc | -0.004 |
atmeal | -0.004 |
Token | ball |
Token ID | 2613 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
tered | +0.025 |
generation | +0.024 |
baby | +0.024 |
ancy | +0.022 |
decides | +0.022 |
Neg logit contributions | |
aj | -0.035 |
ittens | -0.027 |
omed | -0.027 |
uddle | -0.026 |
inc | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
aj | +0.038 |
ittens | +0.031 |
omed | +0.028 |
atmeal | +0.028 |
igs | +0.028 |
Neg logit contributions | |
tered | -0.019 |
baby | -0.019 |
decides | -0.016 |
generation | -0.016 |
infant | -0.015 |
Token | not |
Token ID | 407 |
Feature activation | +4.44e-03 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.010 |
generation | +0.010 |
decides | +0.009 |
Welcome | +0.009 |
Neg logit contributions | |
aj | -0.013 |
ittens | -0.010 |
omed | -0.009 |
inc | -0.009 |
igs | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +8.29e-02 |
Pos logit contributions | |
baby | +0.005 |
tered | +0.005 |
generation | +0.005 |
decides | +0.005 |
Welcome | +0.005 |
Neg logit contributions | |
aj | -0.009 |
ittens | -0.007 |
omed | -0.007 |
inc | -0.007 |
igs | -0.007 |
Token | ball |
Token ID | 2613 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
ively | +0.128 |
tered | +0.124 |
ped | +0.120 |
eyed | +0.114 |
If | +0.113 |
Neg logit contributions | |
vest | -0.098 |
gum | -0.097 |
mask | -0.095 |
dizz | -0.095 |
chess | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
generation | +0.075 |
decides | +0.071 |
tered | +0.071 |
baby | +0.071 |
vows | +0.069 |
Neg logit contributions | |
aj | -0.052 |
ittens | -0.043 |
omed | -0.040 |
mers | -0.038 |
uddle | -0.038 |
Token | It |
Token ID | 632 |
Feature activation | +8.62e-03 |
Pos logit contributions | |
baby | +0.012 |
tered | +0.012 |
generation | +0.012 |
infant | +0.011 |
decides | +0.010 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.021 |
omed | -0.021 |
inc | -0.020 |
fing | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.008 |
generation | +0.008 |
infant | +0.007 |
Welcome | +0.007 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.016 |
omed | -0.015 |
inc | -0.015 |
atmeal | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
generation | +0.018 |
tered | +0.018 |
baby | +0.018 |
decides | +0.017 |
Whoever | +0.017 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.019 |
omed | -0.018 |
inc | -0.018 |
igs | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
aj | +0.071 |
atmeal | +0.058 |
omed | +0.057 |
igs | +0.056 |
inations | +0.056 |
Neg logit contributions | |
baby | -0.027 |
tered | -0.023 |
They | -0.021 |
Welcome | -0.021 |
generation | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
aj | +0.012 |
ittens | +0.010 |
omed | +0.009 |
atmeal | +0.009 |
inc | +0.009 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.007 |
generation | -0.006 |
decides | -0.006 |
Welcome | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
aj | +0.030 |
omed | +0.022 |
ittens | +0.021 |
atmeal | +0.021 |
auldron | +0.020 |
Neg logit contributions | |
baby | -0.026 |
tered | -0.026 |
generation | -0.024 |
decides | -0.023 |
Whoever | -0.023 |
Token | nurse |
Token ID | 15849 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
tered | +0.023 |
generation | +0.022 |
Whoever | +0.019 |
ancy | +0.019 |
decides | +0.019 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.025 |
omed | -0.023 |
uddle | -0.022 |
atmeal | -0.022 |
Token | called |
Token ID | 1444 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
aj | +0.024 |
ittens | +0.020 |
omed | +0.018 |
igs | +0.018 |
atmeal | +0.018 |
Neg logit contributions | |
baby | -0.016 |
tered | -0.016 |
generation | -0.014 |
decides | -0.014 |
infant | -0.013 |
Token | an |
Token ID | 281 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
tered | +0.010 |
baby | +0.010 |
generation | +0.010 |
decides | +0.009 |
infant | +0.009 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.013 |
inc | -0.012 |
igs | -0.012 |
Token | ambulance |
Token ID | 22536 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
Whoever | +0.143 |
vows | +0.143 |
Welcome | +0.142 |
tered | +0.142 |
Mine | +0.141 |
Neg logit contributions | |
aj | -0.092 |
ittens | -0.070 |
pants | -0.064 |
nightmares | -0.058 |
udd | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
baby | +0.016 |
tered | +0.016 |
generation | +0.015 |
decides | +0.014 |
infant | +0.014 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.017 |
omed | -0.017 |
inc | -0.016 |
atmeal | -0.016 |
Token | put |
Token ID | 1234 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
tered | +0.021 |
generation | +0.021 |
baby | +0.020 |
ancy | +0.019 |
decides | +0.019 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.025 |
omed | -0.024 |
inc | -0.023 |
atmeal | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +5.40e-03 |
Pos logit contributions | |
baby | +0.005 |
tered | +0.005 |
generation | +0.004 |
decides | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
aj | -0.008 |
ittens | -0.007 |
omed | -0.006 |
inc | -0.006 |
atmeal | -0.006 |
Token | elderly |
Token ID | 13830 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
tered | +0.006 |
baby | +0.006 |
generation | +0.006 |
decides | +0.006 |
Welcome | +0.006 |
Neg logit contributions | |
aj | -0.011 |
ittens | -0.009 |
omed | -0.008 |
atmeal | -0.008 |
inc | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
generation | +0.024 |
tered | +0.022 |
baby | +0.021 |
Whoever | +0.020 |
decides | +0.020 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.026 |
omed | -0.024 |
igs | -0.023 |
uddle | -0.022 |
Token | them |
Token ID | 606 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
tered | +0.028 |
generation | +0.027 |
decides | +0.024 |
baby | +0.024 |
Whoever | +0.024 |
Neg logit contributions | |
aj | -0.044 |
ittens | -0.038 |
igs | -0.035 |
omed | -0.034 |
fing | -0.033 |
Token | liked |
Token ID | 8288 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
baby | +0.010 |
generation | +0.010 |
tered | +0.010 |
infant | +0.009 |
decides | +0.008 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.020 |
omed | -0.019 |
inc | -0.019 |
atmeal | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
tered | +0.012 |
generation | +0.011 |
baby | +0.011 |
decides | +0.010 |
Whoever | +0.010 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.019 |
omed | -0.017 |
inc | -0.017 |
igs | -0.017 |
Token | race |
Token ID | 3234 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
baby | +0.002 |
tered | +0.002 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.004 |
ittens | -0.003 |
omed | -0.003 |
atmeal | -0.003 |
inc | -0.003 |
Token | each |
Token ID | 1123 |
Feature activation | +8.22e-02 |
Pos logit contributions | |
baby | +0.012 |
tered | +0.012 |
generation | +0.012 |
infant | +0.010 |
decides | +0.010 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.018 |
omed | -0.017 |
igs | -0.017 |
inc | -0.017 |
Token | other |
Token ID | 584 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
vows | +0.135 |
person | +0.122 |
Amelia | +0.121 |
ancy | +0.120 |
seventy | +0.119 |
Neg logit contributions | |
ig | -0.088 |
ede | -0.088 |
robat | -0.087 |
ites | -0.086 |
c | -0.086 |
Token | every |
Token ID | 790 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
generation | +0.071 |
baby | +0.070 |
tered | +0.067 |
decides | +0.066 |
vows | +0.066 |
Neg logit contributions | |
aj | -0.057 |
mers | -0.043 |
omed | -0.042 |
ittens | -0.042 |
dizz | -0.041 |
Token | day |
Token ID | 1110 |
Feature activation | +5.35e-03 |
Pos logit contributions | |
tered | +0.060 |
generation | +0.054 |
vows | +0.054 |
decides | +0.053 |
baby | +0.052 |
Neg logit contributions | |
aj | -0.063 |
ittens | -0.055 |
fing | -0.050 |
omed | -0.050 |
igs | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.008 |
generation | +0.007 |
decides | +0.007 |
infant | +0.007 |
Neg logit contributions | |
aj | -0.009 |
ittens | -0.007 |
omed | -0.007 |
inc | -0.007 |
igs | -0.007 |
Token | Today |
Token ID | 6288 |
Feature activation | +5.26e-03 |
Pos logit contributions | |
baby | +0.003 |
tered | +0.003 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.005 |
ittens | -0.004 |
omed | -0.004 |
inc | -0.004 |
atmeal | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
tered | +0.032 |
baby | +0.030 |
generation | +0.030 |
infant | +0.026 |
Whoever | +0.025 |
Neg logit contributions | |
aj | -0.069 |
ittens | -0.053 |
udd | -0.052 |
atmeal | -0.052 |
omed | -0.052 |
Token | Max |
Token ID | 5436 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
tered | +0.026 |
generation | +0.025 |
baby | +0.025 |
Whoever | +0.024 |
decides | +0.023 |
Neg logit contributions | |
aj | -0.028 |
ittens | -0.022 |
Johnny | -0.020 |
atmeal | -0.020 |
omed | -0.020 |
Token | liked |
Token ID | 8288 |
Feature activation | -5.65e-04 |
Pos logit contributions | |
tered | +0.031 |
baby | +0.031 |
generation | +0.030 |
infant | +0.027 |
Whoever | +0.026 |
Neg logit contributions | |
aj | -0.057 |
omed | -0.044 |
ittens | -0.044 |
atmeal | -0.043 |
inc | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
aj | +0.001 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.000 |
decides | -0.000 |
infant | -0.000 |
Token | race |
Token ID | 3234 |
Feature activation | -4.92e-03 |
Pos logit contributions | |
aj | +0.023 |
ittens | +0.019 |
omed | +0.018 |
inc | +0.017 |
uddle | +0.017 |
Neg logit contributions | |
baby | -0.013 |
tered | -0.012 |
generation | -0.012 |
decides | -0.011 |
infant | -0.011 |
Token | each |
Token ID | 1123 |
Feature activation | +8.18e-02 |
Pos logit contributions | |
aj | +0.010 |
ittens | +0.008 |
omed | +0.008 |
atmeal | +0.008 |
inc | +0.007 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.006 |
decides | -0.005 |
infant | -0.005 |
Token | other |
Token ID | 584 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
vows | +0.133 |
ancy | +0.127 |
lder | +0.125 |
seventy | +0.124 |
generation | +0.122 |
Neg logit contributions | |
--- | -0.082 |
ittens | -0.078 |
ons | -0.078 |
? | -0.075 |
ig | -0.074 |
Token | in |
Token ID | 287 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
baby | +0.043 |
generation | +0.041 |
tered | +0.041 |
decides | +0.040 |
Welcome | +0.039 |
Neg logit contributions | |
aj | -0.039 |
ittens | -0.028 |
omed | -0.027 |
inc | -0.025 |
mers | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -7.04e-03 |
Pos logit contributions | |
tered | +0.017 |
baby | +0.016 |
generation | +0.016 |
decides | +0.015 |
Welcome | +0.014 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.020 |
omed | -0.018 |
Johnny | -0.018 |
igs | -0.018 |
Token | park |
Token ID | 3952 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aj | +0.014 |
ittens | +0.011 |
omed | +0.010 |
atmeal | +0.010 |
inc | +0.010 |
Neg logit contributions | |
baby | -0.010 |
generation | -0.009 |
tered | -0.009 |
decides | -0.008 |
infant | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.10e-03 |
Pos logit contributions | |
baby | +0.021 |
tered | +0.020 |
generation | +0.020 |
infant | +0.019 |
decides | +0.019 |
Neg logit contributions | |
aj | -0.021 |
ittens | -0.016 |
omed | -0.015 |
inc | -0.015 |
atmeal | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
tered | +0.016 |
baby | +0.016 |
generation | +0.015 |
decides | +0.015 |
Whoever | +0.014 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.012 |
igs | -0.011 |
inc | -0.011 |
Token | brother |
Token ID | 3956 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
tered | +0.019 |
generation | +0.018 |
baby | +0.017 |
Whoever | +0.016 |
decides | +0.016 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.020 |
omed | -0.019 |
uddle | -0.019 |
inc | -0.019 |
Token | got |
Token ID | 1392 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
aj | +0.024 |
ittens | +0.020 |
omed | +0.019 |
igs | +0.018 |
atmeal | +0.018 |
Neg logit contributions | |
baby | -0.009 |
tered | -0.009 |
generation | -0.008 |
decides | -0.008 |
infant | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -9.22e-03 |
Pos logit contributions | |
aj | +0.023 |
ittens | +0.019 |
omed | +0.018 |
atmeal | +0.017 |
igs | +0.017 |
Neg logit contributions | |
baby | -0.014 |
tered | -0.013 |
generation | -0.012 |
decides | -0.011 |
infant | -0.011 |
Token | hold |
Token ID | 1745 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
aj | +0.020 |
ittens | +0.017 |
omed | +0.016 |
inc | +0.015 |
atmeal | +0.015 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.010 |
generation | -0.009 |
decides | -0.008 |
infant | -0.008 |
Token | an |
Token ID | 281 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
tered | +0.006 |
baby | +0.006 |
generation | +0.006 |
decides | +0.005 |
Welcome | +0.005 |
Neg logit contributions | |
aj | -0.011 |
ittens | -0.009 |
omed | -0.009 |
inc | -0.009 |
igs | -0.009 |
Token | all |
Token ID | 477 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
Welcome | +0.133 |
Who | +0.123 |
Let | +0.116 |
vows | +0.115 |
Whoever | +0.115 |
Neg logit contributions | |
aj | -0.099 |
ittens | -0.093 |
ivering | -0.087 |
iver | -0.085 |
igs | -0.084 |
Token | igator |
Token ID | 23823 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
baby | +0.002 |
tered | +0.002 |
generation | +0.002 |
decides | +0.002 |
Welcome | +0.002 |
Neg logit contributions | |
aj | -0.005 |
ittens | -0.004 |
omed | -0.004 |
atmeal | -0.003 |
inc | -0.003 |
Token | toy |
Token ID | 13373 |
Feature activation | +9.64e-03 |
Pos logit contributions | |
aj | +0.009 |
ittens | +0.007 |
omed | +0.007 |
inc | +0.007 |
atmeal | +0.007 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.005 |
infant | -0.005 |
decides | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +3.36e-04 |
Pos logit contributions | |
tered | +0.013 |
baby | +0.013 |
generation | +0.013 |
decides | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.014 |
omed | -0.013 |
inc | -0.013 |
igs | -0.013 |
Token | But |
Token ID | 887 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
atmeal | -0.001 |
inc | -0.001 |
Token | Rex |
Token ID | 17853 |
Feature activation | +6.14e-03 |
Pos logit contributions | |
aj | +0.041 |
omed | +0.033 |
ittens | +0.032 |
igs | +0.031 |
inc | +0.030 |
Neg logit contributions | |
baby | -0.030 |
tered | -0.027 |
generation | -0.026 |
infant | -0.025 |
Welcome | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
baby | +0.009 |
tered | +0.009 |
generation | +0.009 |
decides | +0.008 |
infant | +0.008 |
Neg logit contributions | |
aj | -0.011 |
ittens | -0.008 |
omed | -0.008 |
inc | -0.008 |
atmeal | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | +6.75e-03 |
Pos logit contributions | |
aj | +0.027 |
ittens | +0.022 |
omed | +0.021 |
atmeal | +0.021 |
inc | +0.021 |
Neg logit contributions | |
baby | -0.013 |
tered | -0.012 |
generation | -0.011 |
decides | -0.011 |
Welcome | -0.011 |
Token | would |
Token ID | 561 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.008 |
generation | +0.008 |
infant | +0.007 |
decides | +0.007 |
Neg logit contributions | |
aj | -0.014 |
ittens | -0.011 |
omed | -0.011 |
inc | -0.010 |
atmeal | -0.010 |
Token | chase |
Token ID | 15505 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
tered | +0.029 |
generation | +0.028 |
baby | +0.027 |
ancy | +0.025 |
infant | +0.025 |
Neg logit contributions | |
aj | -0.051 |
ittens | -0.043 |
mo | -0.040 |
fing | -0.039 |
vest | -0.039 |
Token | each |
Token ID | 1123 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
baby | +0.003 |
tered | +0.003 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.005 |
inc | -0.005 |
igs | -0.005 |
Token | other |
Token ID | 584 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
vows | +0.136 |
ancy | +0.131 |
rily | +0.128 |
generation | +0.127 |
aciously | +0.126 |
Neg logit contributions | |
ittens | -0.080 |
Sam | -0.079 |
--- | -0.073 |
robat | -0.072 |
c | -0.069 |
Token | in |
Token ID | 287 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
baby | +0.028 |
generation | +0.028 |
tered | +0.027 |
decides | +0.026 |
Welcome | +0.026 |
Neg logit contributions | |
aj | -0.040 |
ittens | -0.032 |
omed | -0.030 |
mers | -0.029 |
inc | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
tered | +0.021 |
generation | +0.020 |
baby | +0.019 |
decides | +0.019 |
ancy | +0.018 |
Neg logit contributions | |
aj | -0.028 |
ittens | -0.022 |
omed | -0.020 |
igs | -0.020 |
fing | -0.020 |
Token | park |
Token ID | 3952 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
aj | +0.016 |
ittens | +0.013 |
omed | +0.012 |
inc | +0.012 |
atmeal | +0.012 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.011 |
generation | -0.011 |
decides | -0.011 |
infant | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
baby | +0.028 |
tered | +0.027 |
generation | +0.026 |
infant | +0.025 |
decides | +0.025 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.025 |
omed | -0.024 |
inc | -0.023 |
mers | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
tered | +0.026 |
baby | +0.024 |
generation | +0.024 |
decides | +0.023 |
infant | +0.022 |
Neg logit contributions | |
aj | -0.042 |
ittens | -0.033 |
omed | -0.032 |
inc | -0.031 |
fing | -0.031 |
Token | go |
Token ID | 467 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
tered | +0.020 |
baby | +0.019 |
generation | +0.018 |
decides | +0.017 |
infant | +0.017 |
Neg logit contributions | |
aj | -0.043 |
ittens | -0.036 |
atmeal | -0.034 |
fing | -0.033 |
Johnny | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
aj | +0.011 |
ittens | +0.009 |
omed | +0.009 |
inc | +0.009 |
atmeal | +0.009 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.005 |
decides | -0.004 |
Welcome | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
tered | +0.027 |
baby | +0.025 |
generation | +0.024 |
decides | +0.023 |
infant | +0.023 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.024 |
fing | -0.022 |
Johnny | -0.022 |
omed | -0.022 |
Token | beach |
Token ID | 10481 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
tered | +0.047 |
baby | +0.040 |
ped | +0.040 |
generation | +0.040 |
ancy | +0.039 |
Neg logit contributions | |
aj | -0.043 |
atmeal | -0.031 |
ittens | -0.031 |
vest | -0.030 |
Johnny | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
aj | +0.043 |
ittens | +0.036 |
omed | +0.035 |
igs | +0.032 |
inc | +0.032 |
Neg logit contributions | |
baby | -0.021 |
tered | -0.019 |
generation | -0.019 |
decides | -0.017 |
Welcome | -0.017 |
Token | So |
Token ID | 1406 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
tered | +0.123 |
urtle | +0.119 |
baby | +0.116 |
trigger | +0.116 |
generation | +0.114 |
Neg logit contributions | |
aj | -0.094 |
inc | -0.070 |
ittens | -0.065 |
endant | -0.063 |
dizz | -0.061 |
Token | Lib |
Token ID | 7980 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
generation | +0.106 |
urtle | +0.104 |
infant | +0.102 |
Welcome | +0.101 |
tered | +0.100 |
Neg logit contributions | |
aj | -0.070 |
ittens | -0.055 |
omed | -0.051 |
inc | -0.048 |
fing | -0.047 |
Token | by |
Token ID | 1525 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
tered | +0.081 |
Welcome | +0.076 |
generation | +0.074 |
Give | +0.071 |
Prize | +0.071 |
Neg logit contributions | |
aj | -0.093 |
ittens | -0.065 |
ig | -0.064 |
udd | -0.062 |
endant | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
generation | +0.049 |
tered | +0.049 |
baby | +0.047 |
infant | +0.045 |
Welcome | +0.045 |
Neg logit contributions | |
aj | -0.079 |
ittens | -0.061 |
omed | -0.057 |
inc | -0.057 |
igs | -0.055 |
Token | her |
Token ID | 607 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
generation | +0.115 |
sc | +0.113 |
tered | +0.112 |
ny | +0.110 |
virtue | +0.108 |
Neg logit contributions | |
aj | -0.075 |
vest | -0.062 |
ittens | -0.055 |
yogurt | -0.053 |
lipstick | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
generation | +0.034 |
tered | +0.032 |
Whoever | +0.031 |
decides | +0.031 |
Welcome | +0.030 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.031 |
Linda | -0.027 |
igs | -0.027 |
omed | -0.027 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
tered | +0.017 |
generation | +0.015 |
baby | +0.013 |
Whoever | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.029 |
vest | -0.029 |
atmeal | -0.029 |
uddle | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
tered | +0.040 |
generation | +0.038 |
baby | +0.036 |
Whoever | +0.035 |
vows | +0.034 |
Neg logit contributions | |
aj | -0.049 |
ittens | -0.038 |
omed | -0.037 |
fing | -0.035 |
inc | -0.035 |
Token | � |
Token ID | 6184 |
Feature activation | -4.66e-02 |
Pos logit contributions | |
tered | +0.011 |
generation | +0.011 |
baby | +0.010 |
decides | +0.009 |
vows | +0.009 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.026 |
omed | -0.025 |
fing | -0.024 |
Johnny | -0.024 |
Token | � |
Token ID | 95 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
aj | +0.088 |
ittens | +0.068 |
omed | +0.066 |
inations | +0.063 |
light | +0.061 |
Neg logit contributions | |
tered | -0.062 |
generation | -0.061 |
Welcome | -0.059 |
sneak | -0.058 |
Whoever | -0.057 |
Token | € |
Token ID | 26391 |
Feature activation | -9.77e-02 |
Pos logit contributions | |
aj | +0.068 |
ittens | +0.057 |
omed | +0.053 |
igs | +0.052 |
uddle | +0.050 |
Neg logit contributions | |
tered | -0.040 |
generation | -0.038 |
Welcome | -0.036 |
Give | -0.034 |
five | -0.033 |
Token | � |
Token ID | 129 |
Feature activation | +1.69e-03 |
Pos logit contributions | |
aj | +0.158 |
fing | +0.157 |
igs | +0.155 |
inations | +0.148 |
pr | +0.148 |
Neg logit contributions | |
wants | -0.115 |
lder | -0.114 |
They | -0.105 |
loves | -0.104 |
Welcome | -0.099 |
Token | � |
Token ID | 241 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
baby | +0.002 |
tered | +0.002 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.003 |
ittens | -0.003 |
omed | -0.003 |
inc | -0.002 |
atmeal | -0.002 |
Token | Will |
Token ID | 8743 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
tered | +0.036 |
baby | +0.036 |
generation | +0.034 |
infant | +0.033 |
decides | +0.033 |
Neg logit contributions | |
aj | -0.052 |
ittens | -0.043 |
inc | -0.041 |
Johnny | -0.040 |
fing | -0.040 |
Token | you |
Token ID | 345 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
aj | +0.007 |
ittens | +0.006 |
omed | +0.006 |
atmeal | +0.005 |
igs | +0.005 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.004 |
decides | -0.004 |
infant | -0.004 |
Token | marry |
Token ID | 12479 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
tered | +0.012 |
baby | +0.012 |
generation | +0.012 |
decides | +0.011 |
infant | +0.011 |
Neg logit contributions | |
aj | -0.021 |
ittens | -0.017 |
omed | -0.016 |
inc | -0.016 |
atmeal | -0.016 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
aj | +0.143 |
ittens | +0.117 |
omed | +0.116 |
atmeal | +0.112 |
uddle | +0.111 |
Neg logit contributions | |
baby | -0.051 |
three | -0.039 |
tered | -0.037 |
other | -0.035 |
lesson | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
aj | +0.043 |
ittens | +0.034 |
omed | +0.033 |
atmeal | +0.032 |
inc | +0.030 |
Neg logit contributions | |
baby | -0.026 |
tered | -0.024 |
generation | -0.021 |
decides | -0.021 |
infant | -0.021 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
tered | +0.012 |
generation | +0.011 |
baby | +0.011 |
decides | +0.010 |
Welcome | +0.010 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
atmeal | -0.012 |
Token | � |
Token ID | 6184 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.014 |
generation | +0.014 |
decides | +0.013 |
Welcome | +0.013 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.015 |
omed | -0.014 |
igs | -0.014 |
atmeal | -0.013 |
Token | � |
Token ID | 95 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
aj | +0.081 |
ittens | +0.061 |
light | +0.055 |
omed | +0.055 |
elbows | +0.052 |
Neg logit contributions | |
tered | -0.065 |
Welcome | -0.060 |
generation | -0.058 |
sneak | -0.058 |
Whoever | -0.058 |
Token | € |
Token ID | 26391 |
Feature activation | -9.68e-02 |
Pos logit contributions | |
aj | +0.086 |
ittens | +0.072 |
igs | +0.065 |
uddle | +0.063 |
omed | +0.063 |
Neg logit contributions | |
tered | -0.055 |
Welcome | -0.050 |
generation | -0.050 |
Give | -0.049 |
five | -0.048 |
Token | � |
Token ID | 129 |
Feature activation | -6.48e-03 |
Pos logit contributions | |
fing | +0.167 |
aj | +0.162 |
ey | +0.154 |
inations | +0.152 |
eking | +0.152 |
Neg logit contributions | |
wants | -0.105 |
loves | -0.094 |
" | -0.093 |
lder | -0.092 |
They | -0.090 |
Token | � |
Token ID | 241 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
aj | +0.013 |
ittens | +0.011 |
omed | +0.010 |
atmeal | +0.010 |
inc | +0.010 |
Neg logit contributions | |
tered | -0.008 |
baby | -0.008 |
generation | -0.007 |
decides | -0.007 |
infant | -0.007 |
Token | What |
Token ID | 2061 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
baby | +0.005 |
tered | +0.005 |
generation | +0.004 |
decides | +0.004 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.006 |
ittens | -0.005 |
omed | -0.005 |
inc | -0.005 |
atmeal | -0.005 |
Token | are |
Token ID | 389 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
aj | +0.005 |
ittens | +0.004 |
omed | +0.004 |
inc | +0.004 |
atmeal | +0.004 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
aj | +0.037 |
omed | +0.029 |
ittens | +0.028 |
inc | +0.027 |
atmeal | +0.027 |
Neg logit contributions | |
baby | -0.025 |
tered | -0.023 |
generation | -0.022 |
Welcome | -0.021 |
infant | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
aj | +0.021 |
ittens | +0.017 |
omed | +0.016 |
atmeal | +0.016 |
igs | +0.016 |
Neg logit contributions | |
baby | -0.011 |
tered | -0.011 |
generation | -0.010 |
Welcome | -0.009 |
decides | -0.009 |
Token | He |
Token ID | 1544 |
Feature activation | +4.38e-04 |
Pos logit contributions | |
aj | +0.047 |
ittens | +0.034 |
atmeal | +0.032 |
endant | +0.031 |
omed | +0.030 |
Neg logit contributions | |
tered | -0.037 |
baby | -0.036 |
decides | -0.034 |
Whoever | -0.034 |
generation | -0.034 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.71e-03 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
inc | -0.001 |
atmeal | -0.001 |
Token | � |
Token ID | 6184 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
tered | +0.005 |
baby | +0.005 |
generation | +0.005 |
decides | +0.004 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.005 |
atmeal | -0.005 |
igs | -0.005 |
Token | � |
Token ID | 95 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
aj | +0.092 |
ittens | +0.071 |
omed | +0.065 |
elbows | +0.065 |
light | +0.064 |
Neg logit contributions | |
tered | -0.063 |
generation | -0.058 |
sneak | -0.056 |
ancy | -0.056 |
Welcome | -0.056 |
Token | € |
Token ID | 26391 |
Feature activation | -9.60e-02 |
Pos logit contributions | |
aj | +0.106 |
ittens | +0.087 |
omed | +0.076 |
uddle | +0.075 |
elbows | +0.075 |
Neg logit contributions | |
tered | -0.065 |
generation | -0.061 |
Welcome | -0.058 |
example | -0.057 |
five | -0.056 |
Token | � |
Token ID | 129 |
Feature activation | +8.48e-03 |
Pos logit contributions | |
aj | +0.166 |
fing | +0.155 |
pr | +0.150 |
inations | +0.148 |
igs | +0.148 |
Neg logit contributions | |
wants | -0.112 |
lder | -0.102 |
Welcome | -0.102 |
" | -0.098 |
loves | -0.094 |
Token | � |
Token ID | 241 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.010 |
generation | +0.010 |
infant | +0.009 |
decides | +0.009 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.014 |
omed | -0.013 |
inc | -0.013 |
igs | -0.013 |
Token | How |
Token ID | 2437 |
Feature activation | -2.36e-02 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.014 |
generation | +0.013 |
infant | +0.013 |
decides | +0.012 |
Neg logit contributions | |
aj | -0.020 |
ittens | -0.016 |
omed | -0.015 |
inc | -0.015 |
fing | -0.015 |
Token | does |
Token ID | 857 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
aj | +0.058 |
ittens | +0.049 |
omed | +0.044 |
elbows | +0.044 |
atmeal | +0.044 |
Neg logit contributions | |
baby | -0.020 |
tered | -0.020 |
decides | -0.018 |
generation | -0.017 |
wants | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
aj | +0.043 |
ittens | +0.035 |
omed | +0.033 |
atmeal | +0.033 |
uddle | +0.032 |
Neg logit contributions | |
baby | -0.023 |
tered | -0.021 |
generation | -0.020 |
infant | -0.019 |
Welcome | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
generation | +0.036 |
tered | +0.035 |
Whoever | +0.034 |
baby | +0.033 |
decides | +0.033 |
Neg logit contributions | |
aj | -0.033 |
ittens | -0.024 |
Johnny | -0.022 |
vest | -0.022 |
omed | -0.022 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
aj | +0.037 |
omed | +0.031 |
ittens | +0.031 |
inc | +0.029 |
atmeal | +0.029 |
Neg logit contributions | |
baby | -0.020 |
infant | -0.016 |
tered | -0.015 |
decides | -0.014 |
Welcome | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e-05 |
Pos logit contributions | |
tered | +0.027 |
generation | +0.027 |
baby | +0.025 |
Whoever | +0.024 |
vows | +0.024 |
Neg logit contributions | |
aj | -0.036 |
ittens | -0.028 |
omed | -0.027 |
atmeal | -0.026 |
fing | -0.025 |
Token | � |
Token ID | 6184 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.000 |
ittens | -0.000 |
omed | -0.000 |
atmeal | -0.000 |
inc | -0.000 |
Token | � |
Token ID | 95 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
aj | +0.082 |
ittens | +0.057 |
omed | +0.056 |
inations | +0.054 |
light | +0.053 |
Neg logit contributions | |
tered | -0.076 |
generation | -0.075 |
Welcome | -0.073 |
sneak | -0.071 |
Whoever | -0.070 |
Token | € |
Token ID | 26391 |
Feature activation | -9.43e-02 |
Pos logit contributions | |
aj | +0.079 |
ittens | +0.063 |
igs | +0.060 |
omed | +0.059 |
uddle | +0.057 |
Neg logit contributions | |
tered | -0.049 |
generation | -0.049 |
Welcome | -0.045 |
Give | -0.042 |
five | -0.042 |
Token | � |
Token ID | 129 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
aj | +0.139 |
fing | +0.138 |
igs | +0.136 |
inations | +0.129 |
ey | +0.129 |
Neg logit contributions | |
lder | -0.116 |
wants | -0.112 |
loves | -0.106 |
Welcome | -0.100 |
is | -0.100 |
Token | � |
Token ID | 241 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
aj | +0.016 |
ittens | +0.013 |
omed | +0.012 |
atmeal | +0.012 |
inc | +0.011 |
Neg logit contributions | |
tered | -0.010 |
baby | -0.010 |
generation | -0.010 |
decides | -0.009 |
infant | -0.009 |
Token | Mom |
Token ID | 29252 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
tered | +0.035 |
baby | +0.035 |
generation | +0.034 |
infant | +0.032 |
decides | +0.032 |
Neg logit contributions | |
aj | -0.049 |
ittens | -0.041 |
Johnny | -0.038 |
inc | -0.038 |
--- | -0.037 |
Token | my |
Token ID | 1820 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
aj | +0.032 |
ittens | +0.026 |
igs | +0.025 |
omed | +0.024 |
inc | +0.024 |
Neg logit contributions | |
baby | -0.024 |
tered | -0.022 |
decides | -0.021 |
infant | -0.021 |
Welcome | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -7.14e-03 |
Pos logit contributions | |
aj | +0.033 |
ittens | +0.027 |
omed | +0.026 |
igs | +0.025 |
atmeal | +0.025 |
Neg logit contributions | |
baby | -0.020 |
tered | -0.018 |
decides | -0.017 |
infant | -0.017 |
generation | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
generation | +0.033 |
tered | +0.032 |
Whoever | +0.032 |
baby | +0.031 |
decides | +0.031 |
Neg logit contributions | |
aj | -0.030 |
ittens | -0.023 |
omed | -0.022 |
igs | -0.021 |
Johnny | -0.020 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
aj | +0.002 |
ittens | +0.002 |
omed | +0.002 |
atmeal | +0.002 |
inc | +0.002 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
tered | +0.028 |
generation | +0.027 |
baby | +0.026 |
Whoever | +0.024 |
Welcome | +0.024 |
Neg logit contributions | |
aj | -0.033 |
ittens | -0.025 |
omed | -0.025 |
atmeal | -0.023 |
fing | -0.023 |
Token | � |
Token ID | 6184 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
tered | +0.003 |
baby | +0.003 |
generation | +0.003 |
decides | +0.003 |
infant | +0.003 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.010 |
omed | -0.010 |
inc | -0.009 |
fing | -0.009 |
Token | � |
Token ID | 95 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
aj | +0.097 |
ittens | +0.071 |
omed | +0.069 |
inations | +0.068 |
light | +0.063 |
Neg logit contributions | |
tered | -0.067 |
generation | -0.065 |
sneak | -0.065 |
Welcome | -0.063 |
Whoever | -0.061 |
Token | € |
Token ID | 26391 |
Feature activation | -9.40e-02 |
Pos logit contributions | |
aj | +0.091 |
ittens | +0.075 |
omed | +0.068 |
igs | +0.067 |
uddle | +0.067 |
Neg logit contributions | |
tered | -0.052 |
generation | -0.051 |
Welcome | -0.047 |
Give | -0.046 |
five | -0.045 |
Token | � |
Token ID | 129 |
Feature activation | -8.78e-03 |
Pos logit contributions | |
aj | +0.164 |
fing | +0.157 |
igs | +0.150 |
inations | +0.145 |
rou | +0.143 |
Neg logit contributions | |
lder | -0.108 |
wants | -0.104 |
loves | -0.091 |
Welcome | -0.090 |
" | -0.090 |
Token | � |
Token ID | 241 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
aj | +0.018 |
ittens | +0.014 |
omed | +0.014 |
atmeal | +0.013 |
inc | +0.013 |
Neg logit contributions | |
tered | -0.011 |
baby | -0.011 |
generation | -0.010 |
decides | -0.009 |
infant | -0.009 |
Token | Mom |
Token ID | 29252 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
tered | +0.023 |
baby | +0.023 |
generation | +0.021 |
infant | +0.021 |
decides | +0.020 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.026 |
inc | -0.024 |
omed | -0.024 |
Johnny | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
aj | +0.029 |
ittens | +0.023 |
omed | +0.022 |
igs | +0.021 |
atmeal | +0.021 |
Neg logit contributions | |
baby | -0.020 |
tered | -0.018 |
decides | -0.017 |
generation | -0.017 |
infant | -0.017 |
Token | why |
Token ID | 1521 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
aj | +0.045 |
ittens | +0.037 |
omed | +0.035 |
inc | +0.035 |
atmeal | +0.034 |
Neg logit contributions | |
baby | -0.024 |
tered | -0.020 |
infant | -0.019 |
Welcome | -0.019 |
generation | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -3.47e-03 |
Pos logit contributions | |
tered | +0.011 |
baby | +0.010 |
generation | +0.010 |
decides | +0.010 |
Welcome | +0.009 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
igs | -0.012 |
Token | water |
Token ID | 1660 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
aj | +0.006 |
ittens | +0.005 |
omed | +0.005 |
atmeal | +0.004 |
inc | +0.004 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.005 |
decides | -0.005 |
infant | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
aj | +0.034 |
ittens | +0.028 |
omed | +0.025 |
igs | +0.025 |
atmeal | +0.025 |
Neg logit contributions | |
baby | -0.021 |
tered | -0.020 |
generation | -0.019 |
decides | -0.018 |
Welcome | -0.018 |
Token | � |
Token ID | 6184 |
Feature activation | -5.12e-02 |
Pos logit contributions | |
aj | +0.028 |
ittens | +0.023 |
omed | +0.022 |
atmeal | +0.022 |
igs | +0.022 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.012 |
generation | -0.011 |
Welcome | -0.010 |
infant | -0.010 |
Token | � |
Token ID | 95 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
aj | +0.106 |
ittens | +0.081 |
inations | +0.078 |
omed | +0.077 |
elbows | +0.076 |
Neg logit contributions | |
tered | -0.063 |
five | -0.061 |
generation | -0.059 |
Welcome | -0.058 |
Whoever | -0.056 |
Token | € |
Token ID | 26391 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
aj | +0.083 |
ittens | +0.070 |
omed | +0.064 |
igs | +0.064 |
uddle | +0.062 |
Neg logit contributions | |
tered | -0.041 |
generation | -0.041 |
five | -0.036 |
Welcome | -0.036 |
ny | -0.035 |
Token | � |
Token ID | 129 |
Feature activation | -1.67e-03 |
Pos logit contributions | |
aj | +0.174 |
fing | +0.155 |
pr | +0.147 |
igs | +0.144 |
ittens | +0.143 |
Neg logit contributions | |
wants | -0.099 |
lder | -0.099 |
loves | -0.090 |
Welcome | -0.087 |
They | -0.086 |
Token | � |
Token ID | 241 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
aj | +0.003 |
ittens | +0.003 |
omed | +0.003 |
atmeal | +0.002 |
inc | +0.002 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.002 |
Token | Hello |
Token ID | 15496 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
tered | +0.029 |
baby | +0.029 |
generation | +0.027 |
infant | +0.026 |
decides | +0.026 |
Neg logit contributions | |
aj | -0.038 |
ittens | -0.031 |
inc | -0.028 |
omed | -0.028 |
Johnny | -0.028 |
Token | ! |
Token ID | 0 |
Feature activation | -6.68e-03 |
Pos logit contributions | |
aj | +0.048 |
ittens | +0.040 |
atmeal | +0.037 |
inations | +0.037 |
igs | +0.037 |
Neg logit contributions | |
baby | -0.032 |
tered | -0.027 |
Welcome | -0.026 |
infant | -0.025 |
decides | -0.025 |
Token | Can |
Token ID | 1680 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
aj | +0.015 |
ittens | +0.013 |
omed | +0.012 |
atmeal | +0.012 |
igs | +0.012 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.006 |
generation | -0.006 |
Welcome | -0.006 |
infant | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
generation | +0.037 |
Whoever | +0.035 |
tered | +0.034 |
decides | +0.033 |
baby | +0.031 |
Neg logit contributions | |
aj | -0.044 |
ittens | -0.037 |
igs | -0.033 |
atmeal | -0.032 |
omed | -0.032 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
aj | +0.032 |
omed | +0.027 |
ittens | +0.026 |
inc | +0.025 |
atmeal | +0.025 |
Neg logit contributions | |
baby | -0.018 |
infant | -0.014 |
tered | -0.013 |
decides | -0.013 |
Welcome | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.013 |
generation | +0.013 |
decides | +0.012 |
Whoever | +0.012 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.019 |
omed | -0.018 |
atmeal | -0.017 |
fing | -0.017 |
Token | � |
Token ID | 6184 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
aj | +0.025 |
ittens | +0.021 |
omed | +0.021 |
inc | +0.020 |
igs | +0.020 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.004 |
generation | -0.004 |
infant | -0.004 |
Welcome | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
aj | +0.093 |
omed | +0.066 |
ittens | +0.064 |
inations | +0.063 |
ons | +0.062 |
Neg logit contributions | |
tered | -0.072 |
generation | -0.069 |
Welcome | -0.069 |
sneak | -0.069 |
baby | -0.067 |
Token | € |
Token ID | 26391 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
aj | +0.089 |
ittens | +0.070 |
omed | +0.067 |
igs | +0.066 |
uddle | +0.064 |
Neg logit contributions | |
generation | -0.058 |
tered | -0.058 |
Welcome | -0.054 |
Give | -0.050 |
ancy | -0.050 |
Token | � |
Token ID | 129 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
fing | +0.139 |
aj | +0.138 |
ey | +0.132 |
rou | +0.125 |
vell | +0.124 |
Neg logit contributions | |
lder | -0.121 |
wants | -0.113 |
loves | -0.112 |
baby | -0.104 |
is | -0.100 |
Token | � |
Token ID | 241 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
aj | +0.023 |
ittens | +0.019 |
omed | +0.018 |
atmeal | +0.017 |
fing | +0.017 |
Neg logit contributions | |
tered | -0.014 |
baby | -0.014 |
generation | -0.013 |
decides | -0.012 |
infant | -0.012 |
Token | Can |
Token ID | 6090 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
tered | +0.039 |
baby | +0.039 |
generation | +0.037 |
infant | +0.036 |
decides | +0.035 |
Neg logit contributions | |
aj | -0.055 |
ittens | -0.046 |
inc | -0.042 |
Johnny | -0.042 |
--- | -0.041 |
Token | I |
Token ID | 314 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
aj | +0.043 |
ittens | +0.035 |
omed | +0.034 |
atmeal | +0.033 |
inc | +0.033 |
Neg logit contributions | |
baby | -0.020 |
tered | -0.020 |
generation | -0.018 |
Welcome | -0.017 |
decides | -0.017 |
Token | go |
Token ID | 467 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
aj | +0.038 |
omed | +0.031 |
ittens | +0.031 |
inc | +0.029 |
igs | +0.028 |
Neg logit contributions | |
baby | -0.014 |
tered | -0.013 |
generation | -0.012 |
Welcome | -0.011 |
decides | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
generation | +0.034 |
Whoever | +0.032 |
tered | +0.032 |
decides | +0.030 |
baby | +0.030 |
Neg logit contributions | |
aj | -0.042 |
ittens | -0.034 |
omed | -0.031 |
Linda | -0.030 |
igs | -0.029 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
aj | +0.037 |
ittens | +0.031 |
omed | +0.031 |
inc | +0.030 |
atmeal | +0.030 |
Neg logit contributions | |
baby | -0.019 |
infant | -0.014 |
tered | -0.014 |
decides | -0.013 |
Welcome | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +4.47e-03 |
Pos logit contributions | |
tered | +0.015 |
generation | +0.014 |
baby | +0.014 |
Whoever | +0.013 |
infant | +0.013 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.018 |
omed | -0.017 |
atmeal | -0.016 |
inc | -0.016 |
Token | � |
Token ID | 6184 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
tered | +0.003 |
baby | +0.003 |
generation | +0.003 |
decides | +0.003 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.011 |
ittens | -0.010 |
omed | -0.009 |
inc | -0.009 |
fing | -0.009 |
Token | � |
Token ID | 95 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
aj | +0.100 |
ittens | +0.070 |
omed | +0.069 |
inations | +0.069 |
ons | +0.068 |
Neg logit contributions | |
tered | -0.080 |
Welcome | -0.078 |
sneak | -0.077 |
generation | -0.075 |
lder | -0.074 |
Token | € |
Token ID | 26391 |
Feature activation | -9.35e-02 |
Pos logit contributions | |
aj | +0.093 |
ittens | +0.075 |
igs | +0.069 |
omed | +0.068 |
inations | +0.068 |
Neg logit contributions | |
tered | -0.059 |
generation | -0.059 |
Welcome | -0.056 |
Give | -0.052 |
ancy | -0.051 |
Token | � |
Token ID | 129 |
Feature activation | -6.94e-03 |
Pos logit contributions | |
fing | +0.151 |
aj | +0.142 |
ey | +0.138 |
inations | +0.131 |
ode | +0.131 |
Neg logit contributions | |
lder | -0.112 |
wants | -0.110 |
loves | -0.106 |
baby | -0.100 |
Welcome | -0.098 |
Token | � |
Token ID | 241 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
aj | +0.014 |
ittens | +0.011 |
omed | +0.011 |
atmeal | +0.010 |
inc | +0.010 |
Neg logit contributions | |
tered | -0.009 |
baby | -0.009 |
generation | -0.008 |
decides | -0.008 |
infant | -0.007 |
Token | Please |
Token ID | 5492 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
tered | +0.025 |
baby | +0.025 |
generation | +0.024 |
infant | +0.022 |
decides | +0.022 |
Neg logit contributions | |
aj | -0.040 |
ittens | -0.033 |
inc | -0.030 |
omed | -0.030 |
Johnny | -0.030 |
Token | can |
Token ID | 460 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
aj | +0.032 |
ittens | +0.026 |
omed | +0.025 |
atmeal | +0.024 |
igs | +0.024 |
Neg logit contributions | |
baby | -0.017 |
tered | -0.017 |
generation | -0.015 |
Welcome | -0.015 |
decides | -0.015 |
Token | I |
Token ID | 314 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
aj | +0.073 |
omed | +0.059 |
auldron | +0.058 |
ittens | +0.057 |
inc | +0.057 |
Neg logit contributions | |
baby | -0.023 |
tered | -0.021 |
Welcome | -0.018 |
generation | -0.016 |
Give | -0.016 |
Token | about |
Token ID | 546 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
tered | +0.018 |
generation | +0.017 |
baby | +0.016 |
Whoever | +0.015 |
decides | +0.015 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.020 |
omed | -0.019 |
inc | -0.018 |
fing | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
aj | +0.041 |
ittens | +0.034 |
omed | +0.032 |
inc | +0.031 |
uddle | +0.031 |
Neg logit contributions | |
baby | -0.018 |
tered | -0.016 |
generation | -0.016 |
infant | -0.014 |
Welcome | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-02 |
Pos logit contributions | |
aj | +0.023 |
ittens | +0.019 |
omed | +0.018 |
inc | +0.017 |
atmeal | +0.017 |
Neg logit contributions | |
baby | -0.014 |
tered | -0.014 |
generation | -0.013 |
infant | -0.012 |
decides | -0.012 |
Token | � |
Token ID | 6184 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
generation | +0.024 |
tered | +0.023 |
baby | +0.023 |
decides | +0.022 |
Whoever | +0.021 |
Neg logit contributions | |
aj | -0.044 |
ittens | -0.035 |
omed | -0.035 |
inc | -0.033 |
uddle | -0.032 |
Token | � |
Token ID | 95 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
aj | +0.101 |
ittens | +0.080 |
vest | +0.073 |
inations | +0.072 |
atmeal | +0.070 |
Neg logit contributions | |
tered | -0.080 |
generation | -0.072 |
Welcome | -0.071 |
Give | -0.070 |
example | -0.069 |
Token | € |
Token ID | 26391 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
aj | +0.083 |
ittens | +0.070 |
igs | +0.063 |
atmeal | +0.061 |
omed | +0.061 |
Neg logit contributions | |
tered | -0.054 |
generation | -0.051 |
Welcome | -0.047 |
example | -0.046 |
Give | -0.045 |
Token | � |
Token ID | 129 |
Feature activation | +4.73e-04 |
Pos logit contributions | |
aj | +0.157 |
fing | +0.151 |
ode | +0.145 |
cel | +0.143 |
atmeal | +0.137 |
Neg logit contributions | |
wants | -0.112 |
lder | -0.109 |
loves | -0.108 |
is | -0.102 |
baby | -0.097 |
Token | � |
Token ID | 241 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
inc | -0.001 |
atmeal | -0.001 |
Token | Why |
Token ID | 5195 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
baby | +0.032 |
tered | +0.032 |
generation | +0.031 |
decides | +0.029 |
infant | +0.029 |
Neg logit contributions | |
aj | -0.046 |
ittens | -0.038 |
omed | -0.035 |
inc | -0.035 |
Johnny | -0.034 |
Token | do |
Token ID | 466 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
aj | +0.042 |
ittens | +0.034 |
igs | +0.031 |
omed | +0.031 |
uddle | +0.031 |
Neg logit contributions | |
baby | -0.026 |
tered | -0.026 |
decides | -0.023 |
wants | -0.023 |
generation | -0.022 |
Token | you |
Token ID | 345 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
aj | +0.079 |
omed | +0.060 |
ittens | +0.059 |
endant | +0.057 |
ode | +0.057 |
Neg logit contributions | |
baby | -0.047 |
tered | -0.042 |
infant | -0.039 |
Welcome | -0.038 |
person | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
tered | +0.008 |
baby | +0.008 |
generation | +0.008 |
decides | +0.007 |
infant | +0.007 |
Neg logit contributions | |
aj | -0.013 |
ittens | -0.010 |
omed | -0.009 |
igs | -0.009 |
inc | -0.009 |
Token | tree |
Token ID | 5509 |
Feature activation | -6.98e-04 |
Pos logit contributions | |
aj | +0.024 |
ittens | +0.019 |
omed | +0.018 |
inc | +0.017 |
igs | +0.017 |
Neg logit contributions | |
baby | -0.013 |
tered | -0.012 |
generation | -0.011 |
infant | -0.011 |
decides | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +4.04e-04 |
Pos logit contributions | |
aj | +0.001 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | � |
Token ID | 6184 |
Feature activation | -5.33e-02 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
inc | -0.001 |
atmeal | -0.001 |
Token | � |
Token ID | 95 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
aj | +0.113 |
ittens | +0.086 |
inations | +0.085 |
Johnny | +0.081 |
omed | +0.078 |
Neg logit contributions | |
tered | -0.063 |
generation | -0.062 |
Welcome | -0.059 |
baby | -0.057 |
Give | -0.057 |
Token | € |
Token ID | 26391 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
aj | +0.113 |
ittens | +0.092 |
uddle | +0.085 |
inations | +0.084 |
igs | +0.082 |
Neg logit contributions | |
tered | -0.055 |
generation | -0.054 |
Welcome | -0.051 |
Give | -0.050 |
five | -0.047 |
Token | � |
Token ID | 129 |
Feature activation | -6.41e-03 |
Pos logit contributions | |
aj | +0.177 |
fing | +0.162 |
igs | +0.155 |
inations | +0.154 |
ittens | +0.152 |
Neg logit contributions | |
wants | -0.103 |
lder | -0.095 |
Welcome | -0.090 |
Give | -0.087 |
is | -0.087 |
Token | � |
Token ID | 241 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
aj | +0.013 |
ittens | +0.011 |
omed | +0.010 |
atmeal | +0.010 |
inc | +0.010 |
Neg logit contributions | |
tered | -0.007 |
baby | -0.007 |
generation | -0.007 |
decides | -0.006 |
Welcome | -0.006 |
Token | Can |
Token ID | 6090 |
Feature activation | -3.47e-02 |
Pos logit contributions | |
aj | +0.004 |
ittens | +0.003 |
omed | +0.003 |
atmeal | +0.003 |
igs | +0.003 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.002 |
Welcome | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
aj | +0.082 |
ittens | +0.065 |
omed | +0.064 |
auldron | +0.062 |
igs | +0.062 |
Neg logit contributions | |
baby | -0.033 |
tered | -0.031 |
Welcome | -0.027 |
generation | -0.027 |
decides | -0.026 |
Token | do |
Token ID | 466 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
aj | +0.053 |
ittens | +0.044 |
omed | +0.041 |
atmeal | +0.041 |
uddle | +0.040 |
Neg logit contributions | |
baby | -0.020 |
tered | -0.019 |
generation | -0.017 |
decides | -0.016 |
infant | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -5.78e-04 |
Pos logit contributions | |
aj | +0.052 |
ittens | +0.044 |
atmeal | +0.042 |
igs | +0.042 |
inc | +0.041 |
Neg logit contributions | |
baby | -0.017 |
tered | -0.016 |
infant | -0.013 |
generation | -0.013 |
decides | -0.012 |
Token | asked |
Token ID | 1965 |
Feature activation | +9.03e-03 |
Pos logit contributions | |
aj | +0.001 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-03 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.014 |
generation | +0.014 |
decides | +0.013 |
infant | +0.013 |
Neg logit contributions | |
aj | -0.015 |
ittens | -0.012 |
omed | -0.011 |
Johnny | -0.010 |
igs | -0.010 |
Token | � |
Token ID | 6184 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
baby | +0.002 |
tered | +0.002 |
generation | +0.002 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.006 |
inc | -0.005 |
atmeal | -0.005 |
Token | � |
Token ID | 95 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
aj | +0.095 |
ittens | +0.073 |
omed | +0.065 |
atmeal | +0.064 |
inc | +0.063 |
Neg logit contributions | |
tered | -0.072 |
generation | -0.068 |
sneak | -0.066 |
Welcome | -0.066 |
Whoever | -0.064 |
Token | € |
Token ID | 26391 |
Feature activation | -9.33e-02 |
Pos logit contributions | |
aj | +0.092 |
ittens | +0.076 |
uddle | +0.067 |
omed | +0.067 |
endant | +0.066 |
Neg logit contributions | |
tered | -0.059 |
generation | -0.058 |
Welcome | -0.056 |
ny | -0.053 |
teaches | -0.052 |
Token | � |
Token ID | 129 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
fing | +0.151 |
aj | +0.150 |
atmeal | +0.142 |
unatt | +0.140 |
yogurt | +0.136 |
Neg logit contributions | |
They | -0.106 |
wants | -0.102 |
loves | -0.101 |
Welcome | -0.100 |
" | -0.099 |
Token | � |
Token ID | 241 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
baby | +0.005 |
tered | +0.004 |
generation | +0.004 |
decides | +0.004 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.005 |
inc | -0.005 |
igs | -0.005 |
Token | What |
Token ID | 2061 |
Feature activation | +7.63e-03 |
Pos logit contributions | |
baby | +0.014 |
tered | +0.014 |
generation | +0.013 |
infant | +0.013 |
decides | +0.012 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.018 |
omed | -0.017 |
inc | -0.016 |
Johnny | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | -5.43e-05 |
Pos logit contributions | |
tered | +0.008 |
baby | +0.008 |
generation | +0.007 |
decides | +0.007 |
infant | +0.007 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.014 |
omed | -0.013 |
atmeal | -0.013 |
inc | -0.013 |
Token | sunrise |
Token ID | 40048 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
aj | +0.000 |
ittens | +0.000 |
omed | +0.000 |
atmeal | +0.000 |
inc | +0.000 |
Neg logit contributions | |
baby | -0.000 |
tered | -0.000 |
generation | -0.000 |
decides | -0.000 |
infant | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | -5.33e-03 |
Pos logit contributions | |
generation | +0.029 |
Whoever | +0.028 |
tered | +0.027 |
decides | +0.027 |
baby | +0.026 |
Neg logit contributions | |
aj | -0.034 |
ittens | -0.028 |
omed | -0.026 |
igs | -0.025 |
Linda | -0.025 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
aj | +0.011 |
ittens | +0.009 |
omed | +0.008 |
inc | +0.008 |
atmeal | +0.008 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.006 |
generation | -0.006 |
infant | -0.006 |
decides | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-03 |
Pos logit contributions | |
tered | +0.029 |
generation | +0.028 |
baby | +0.027 |
Whoever | +0.025 |
infant | +0.024 |
Neg logit contributions | |
aj | -0.036 |
ittens | -0.027 |
omed | -0.027 |
atmeal | -0.026 |
fing | -0.025 |
Token | � |
Token ID | 6184 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
aj | +0.004 |
ittens | +0.003 |
omed | +0.003 |
atmeal | +0.003 |
inc | +0.003 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | � |
Token ID | 95 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
aj | +0.077 |
ittens | +0.057 |
omed | +0.056 |
inc | +0.050 |
inations | +0.050 |
Neg logit contributions | |
tered | -0.059 |
generation | -0.056 |
baby | -0.054 |
Welcome | -0.054 |
Whoever | -0.053 |
Token | € |
Token ID | 26391 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
aj | +0.070 |
ittens | +0.056 |
omed | +0.052 |
uddle | +0.050 |
igs | +0.050 |
Neg logit contributions | |
tered | -0.046 |
generation | -0.045 |
Welcome | -0.041 |
baby | -0.039 |
Whoever | -0.039 |
Token | � |
Token ID | 129 |
Feature activation | +1.98e-03 |
Pos logit contributions | |
aj | +0.169 |
fing | +0.159 |
inations | +0.145 |
omed | +0.145 |
eking | +0.145 |
Neg logit contributions | |
lder | -0.102 |
wants | -0.097 |
loves | -0.088 |
is | -0.087 |
Welcome | -0.084 |
Token | � |
Token ID | 241 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
baby | +0.003 |
tered | +0.003 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.004 |
ittens | -0.003 |
omed | -0.003 |
inc | -0.003 |
atmeal | -0.003 |
Token | can |
Token ID | 5171 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
baby | +0.033 |
tered | +0.033 |
generation | +0.031 |
infant | +0.030 |
decides | +0.029 |
Neg logit contributions | |
aj | -0.048 |
ittens | -0.040 |
inc | -0.037 |
Johnny | -0.036 |
omed | -0.036 |
Token | I |
Token ID | 314 |
Feature activation | +7.92e-04 |
Pos logit contributions | |
aj | +0.053 |
ittens | +0.043 |
omed | +0.041 |
atmeal | +0.040 |
uddle | +0.040 |
Neg logit contributions | |
baby | -0.026 |
tered | -0.025 |
generation | -0.023 |
decides | -0.022 |
Welcome | -0.022 |
Token | have |
Token ID | 423 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.002 |
ittens | -0.001 |
omed | -0.001 |
inc | -0.001 |
atmeal | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +8.72e-03 |
Pos logit contributions | |
aj | +0.031 |
ittens | +0.026 |
omed | +0.024 |
igs | +0.024 |
inc | +0.024 |
Neg logit contributions | |
baby | -0.015 |
tered | -0.014 |
generation | -0.013 |
infant | -0.013 |
Welcome | -0.012 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
tered | +0.013 |
baby | +0.012 |
generation | +0.012 |
decides | +0.011 |
infant | +0.011 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.012 |
omed | -0.011 |
inc | -0.011 |
atmeal | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
generation | +0.046 |
tered | +0.045 |
baby | +0.043 |
decides | +0.043 |
Whoever | +0.042 |
Neg logit contributions | |
aj | -0.057 |
ittens | -0.045 |
omed | -0.043 |
Johnny | -0.041 |
fing | -0.039 |
Token | � |
Token ID | 6184 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
tered | +0.009 |
generation | +0.009 |
baby | +0.008 |
decides | +0.007 |
infant | +0.007 |
Neg logit contributions | |
aj | -0.027 |
ittens | -0.023 |
omed | -0.022 |
inc | -0.021 |
fing | -0.021 |
Token | � |
Token ID | 95 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
aj | +0.085 |
ittens | +0.066 |
inations | +0.059 |
elbows | +0.059 |
omed | +0.057 |
Neg logit contributions | |
tered | -0.065 |
Welcome | -0.061 |
generation | -0.061 |
sneak | -0.058 |
Whoever | -0.058 |
Token | € |
Token ID | 26391 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
aj | +0.085 |
ittens | +0.072 |
igs | +0.066 |
uddle | +0.066 |
omed | +0.063 |
Neg logit contributions | |
tered | -0.042 |
generation | -0.041 |
Welcome | -0.039 |
Give | -0.037 |
example | -0.035 |
Token | � |
Token ID | 129 |
Feature activation | -2.83e-03 |
Pos logit contributions | |
aj | +0.156 |
fing | +0.148 |
igs | +0.146 |
pr | +0.143 |
ittens | +0.142 |
Neg logit contributions | |
lder | -0.102 |
wants | -0.102 |
Welcome | -0.094 |
They | -0.093 |
loves | -0.093 |
Token | � |
Token ID | 241 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
aj | +0.006 |
ittens | +0.005 |
omed | +0.004 |
atmeal | +0.004 |
inc | +0.004 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.003 |
Welcome | -0.003 |
Token | M |
Token ID | 44 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
tered | +0.022 |
baby | +0.021 |
generation | +0.021 |
decides | +0.019 |
infant | +0.019 |
Neg logit contributions | |
aj | -0.030 |
ittens | -0.024 |
omed | -0.022 |
inc | -0.022 |
Johnny | -0.022 |
Token | ama |
Token ID | 1689 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
aj | +0.056 |
elbows | +0.043 |
fing | +0.042 |
Ol | +0.041 |
inc | +0.040 |
Neg logit contributions | |
baby | -0.048 |
tered | -0.045 |
ancy | -0.041 |
generation | -0.041 |
Welcome | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
aj | +0.039 |
ittens | +0.032 |
omed | +0.030 |
igs | +0.029 |
atmeal | +0.029 |
Neg logit contributions | |
baby | -0.025 |
tered | -0.023 |
generation | -0.021 |
Welcome | -0.021 |
infant | -0.021 |
Token | his |
Token ID | 465 |
Feature activation | -4.24e-04 |
Pos logit contributions | |
tered | +0.020 |
baby | +0.019 |
generation | +0.019 |
decides | +0.018 |
Whoever | +0.018 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.020 |
omed | -0.020 |
fing | -0.019 |
igs | -0.019 |
Token | newspaper |
Token ID | 7533 |
Feature activation | +9.75e-04 |
Pos logit contributions | |
aj | +0.001 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.07e-03 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.002 |
ittens | -0.002 |
omed | -0.002 |
atmeal | -0.002 |
inc | -0.002 |
Token | � |
Token ID | 6184 |
Feature activation | -4.70e-02 |
Pos logit contributions | |
aj | +0.005 |
ittens | +0.004 |
omed | +0.004 |
atmeal | +0.004 |
inc | +0.004 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
Welcome | -0.002 |
Token | � |
Token ID | 95 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
aj | +0.094 |
ittens | +0.075 |
omed | +0.070 |
inations | +0.070 |
light | +0.069 |
Neg logit contributions | |
tered | -0.059 |
five | -0.057 |
generation | -0.055 |
Welcome | -0.055 |
Give | -0.053 |
Token | € |
Token ID | 26391 |
Feature activation | -9.23e-02 |
Pos logit contributions | |
aj | +0.080 |
ittens | +0.068 |
omed | +0.062 |
igs | +0.062 |
uddle | +0.060 |
Neg logit contributions | |
tered | -0.040 |
generation | -0.040 |
Welcome | -0.036 |
five | -0.036 |
Give | -0.035 |
Token | � |
Token ID | 129 |
Feature activation | -5.84e-03 |
Pos logit contributions | |
aj | +0.163 |
pr | +0.148 |
fing | +0.142 |
ittens | +0.138 |
igs | +0.136 |
Neg logit contributions | |
wants | -0.108 |
lder | -0.098 |
Welcome | -0.097 |
loves | -0.095 |
They | -0.095 |
Token | � |
Token ID | 241 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
aj | +0.012 |
ittens | +0.010 |
omed | +0.009 |
atmeal | +0.009 |
inc | +0.009 |
Neg logit contributions | |
tered | -0.007 |
baby | -0.007 |
generation | -0.006 |
decides | -0.006 |
Welcome | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
tered | +0.031 |
baby | +0.031 |
generation | +0.029 |
infant | +0.028 |
decides | +0.027 |
Neg logit contributions | |
aj | -0.043 |
ittens | -0.035 |
inc | -0.033 |
omed | -0.033 |
fing | -0.032 |
Token | wouldn |
Token ID | 3636 |
Feature activation | -7.06e-04 |
Pos logit contributions | |
aj | +0.035 |
ittens | +0.030 |
omed | +0.027 |
igs | +0.027 |
atmeal | +0.027 |
Neg logit contributions | |
baby | -0.014 |
tered | -0.013 |
generation | -0.013 |
decides | -0.012 |
Welcome | -0.012 |
Token | â |
Token ID | 22940 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
aj | +0.002 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
aj | +0.035 |
ittens | +0.030 |
omed | +0.028 |
atmeal | +0.028 |
igs | +0.028 |
Neg logit contributions | |
baby | -0.016 |
tered | -0.015 |
generation | -0.014 |
infant | -0.013 |
decides | -0.012 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
aj | +0.054 |
ittens | +0.046 |
atmeal | +0.042 |
igs | +0.042 |
omed | +0.041 |
Neg logit contributions | |
baby | -0.041 |
tered | -0.036 |
decides | -0.035 |
generation | -0.034 |
Welcome | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
tered | +0.028 |
generation | +0.027 |
baby | +0.027 |
Whoever | +0.025 |
decides | +0.025 |
Neg logit contributions | |
aj | -0.038 |
ittens | -0.030 |
omed | -0.029 |
Johnny | -0.027 |
fing | -0.027 |
Token | � |
Token ID | 6184 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
tered | +0.010 |
baby | +0.010 |
generation | +0.010 |
decides | +0.008 |
infant | +0.008 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.026 |
omed | -0.025 |
inc | -0.024 |
fing | -0.024 |
Token | � |
Token ID | 95 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
aj | +0.093 |
ittens | +0.075 |
inations | +0.068 |
atmeal | +0.067 |
ons | +0.065 |
Neg logit contributions | |
tered | -0.064 |
Welcome | -0.062 |
generation | -0.061 |
sneak | -0.058 |
Give | -0.057 |
Token | € |
Token ID | 26391 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
aj | +0.091 |
ittens | +0.081 |
igs | +0.073 |
atmeal | +0.069 |
uddle | +0.069 |
Neg logit contributions | |
tered | -0.045 |
generation | -0.044 |
Welcome | -0.043 |
Give | -0.040 |
decides | -0.038 |
Token | � |
Token ID | 129 |
Feature activation | -9.57e-03 |
Pos logit contributions | |
aj | +0.162 |
ittens | +0.155 |
fing | +0.153 |
igs | +0.151 |
pr | +0.151 |
Neg logit contributions | |
wants | -0.099 |
They | -0.094 |
Welcome | -0.093 |
is | -0.088 |
lder | -0.087 |
Token | � |
Token ID | 241 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
aj | +0.020 |
ittens | +0.016 |
omed | +0.015 |
atmeal | +0.015 |
igs | +0.014 |
Neg logit contributions | |
tered | -0.011 |
baby | -0.011 |
generation | -0.011 |
decides | -0.010 |
Welcome | -0.010 |
Token | What |
Token ID | 2061 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
tered | +0.017 |
baby | +0.017 |
generation | +0.017 |
infant | +0.016 |
decides | +0.015 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.017 |
omed | -0.016 |
inc | -0.016 |
Johnny | -0.016 |
Token | should |
Token ID | 815 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
aj | +0.019 |
ittens | +0.016 |
omed | +0.015 |
igs | +0.015 |
inc | +0.015 |
Neg logit contributions | |
baby | -0.009 |
tered | -0.008 |
generation | -0.008 |
decides | -0.007 |
Welcome | -0.007 |
Token | I |
Token ID | 314 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
aj | +0.013 |
ittens | +0.010 |
omed | +0.010 |
atmeal | +0.009 |
inc | +0.009 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.010 |
generation | -0.010 |
Welcome | -0.009 |
decides | -0.009 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
baby | +0.004 |
tered | +0.004 |
generation | +0.004 |
decides | +0.004 |
Welcome | +0.004 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.006 |
inc | -0.005 |
atmeal | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -3.42e-03 |
Pos logit contributions | |
generation | +0.015 |
tered | +0.015 |
baby | +0.015 |
decides | +0.014 |
Whoever | +0.014 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.014 |
omed | -0.013 |
Johnny | -0.013 |
fing | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
aj | +0.007 |
ittens | +0.006 |
omed | +0.005 |
atmeal | +0.005 |
inc | +0.005 |
Neg logit contributions | |
baby | -0.004 |
tered | -0.004 |
generation | -0.004 |
decides | -0.004 |
infant | -0.004 |
Token | � |
Token ID | 6184 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
tered | +0.007 |
generation | +0.007 |
baby | +0.007 |
decides | +0.007 |
infant | +0.006 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.020 |
omed | -0.019 |
Johnny | -0.018 |
fing | -0.018 |
Token | � |
Token ID | 95 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
aj | +0.088 |
ittens | +0.066 |
omed | +0.066 |
inations | +0.062 |
elbows | +0.061 |
Neg logit contributions | |
tered | -0.060 |
generation | -0.055 |
baby | -0.053 |
sneak | -0.053 |
Welcome | -0.053 |
Token | € |
Token ID | 26391 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
aj | +0.091 |
ittens | +0.075 |
omed | +0.070 |
igs | +0.069 |
uddle | +0.068 |
Neg logit contributions | |
tered | -0.052 |
generation | -0.049 |
Welcome | -0.047 |
Give | -0.045 |
five | -0.045 |
Token | � |
Token ID | 129 |
Feature activation | -6.69e-03 |
Pos logit contributions | |
aj | +0.166 |
fing | +0.156 |
igs | +0.154 |
ey | +0.151 |
pr | +0.149 |
Neg logit contributions | |
lder | -0.096 |
wants | -0.095 |
loves | -0.084 |
Welcome | -0.080 |
" | -0.080 |
Token | � |
Token ID | 241 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
aj | +0.014 |
ittens | +0.011 |
omed | +0.011 |
atmeal | +0.010 |
inc | +0.010 |
Neg logit contributions | |
tered | -0.008 |
baby | -0.008 |
generation | -0.008 |
decides | -0.007 |
infant | -0.007 |
Token | Mom |
Token ID | 29252 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
baby | +0.030 |
tered | +0.030 |
generation | +0.028 |
infant | +0.027 |
decides | +0.027 |
Neg logit contributions | |
aj | -0.047 |
ittens | -0.039 |
Johnny | -0.037 |
inc | -0.037 |
fing | -0.036 |
Token | my |
Token ID | 1820 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
aj | +0.057 |
ittens | +0.047 |
igs | +0.044 |
inc | +0.044 |
atmeal | +0.043 |
Neg logit contributions | |
baby | -0.040 |
tered | -0.034 |
decides | -0.033 |
infant | -0.033 |
wants | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
aj | +0.038 |
ittens | +0.031 |
omed | +0.029 |
atmeal | +0.029 |
igs | +0.028 |
Neg logit contributions | |
baby | -0.022 |
tered | -0.021 |
infant | -0.019 |
decides | -0.019 |
Welcome | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | -4.32e-03 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.000 |
ittens | -0.000 |
omed | -0.000 |
atmeal | -0.000 |
inc | -0.000 |
Token | she |
Token ID | 673 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
aj | +0.008 |
ittens | +0.006 |
omed | +0.006 |
atmeal | +0.005 |
inc | +0.005 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.006 |
decides | -0.006 |
infant | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
aj | +0.008 |
ittens | +0.007 |
omed | +0.006 |
atmeal | +0.006 |
inc | +0.006 |
Neg logit contributions | |
baby | -0.004 |
tered | -0.004 |
generation | -0.004 |
decides | -0.004 |
infant | -0.003 |
Token | � |
Token ID | 6184 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
generation | +0.034 |
tered | +0.032 |
decides | +0.031 |
baby | +0.031 |
Whoever | +0.030 |
Neg logit contributions | |
aj | -0.045 |
ittens | -0.037 |
omed | -0.035 |
Johnny | -0.032 |
Linda | -0.032 |
Token | � |
Token ID | 95 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
aj | +0.100 |
ittens | +0.073 |
inations | +0.072 |
omed | +0.072 |
light | +0.068 |
Neg logit contributions | |
sneak | -0.072 |
tered | -0.071 |
lder | -0.070 |
Whoever | -0.070 |
generation | -0.069 |
Token | € |
Token ID | 26391 |
Feature activation | -9.21e-02 |
Pos logit contributions | |
aj | +0.092 |
ittens | +0.076 |
igs | +0.070 |
omed | +0.069 |
inations | +0.069 |
Neg logit contributions | |
tered | -0.057 |
generation | -0.056 |
Welcome | -0.053 |
Give | -0.052 |
Whoever | -0.052 |
Token | � |
Token ID | 129 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
aj | +0.163 |
igs | +0.158 |
inations | +0.156 |
fing | +0.156 |
ey | +0.151 |
Neg logit contributions | |
lder | -0.090 |
wants | -0.082 |
Welcome | -0.081 |
" | -0.079 |
Give | -0.076 |
Token | � |
Token ID | 241 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
aj | +0.028 |
ittens | +0.023 |
omed | +0.023 |
atmeal | +0.021 |
fing | +0.021 |
Neg logit contributions | |
tered | -0.016 |
baby | -0.016 |
generation | -0.015 |
decides | -0.014 |
infant | -0.013 |
Token | How |
Token ID | 2437 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
tered | +0.028 |
baby | +0.028 |
generation | +0.027 |
infant | +0.026 |
decides | +0.025 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.030 |
omed | -0.028 |
inc | -0.028 |
Johnny | -0.028 |
Token | can |
Token ID | 460 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
aj | +0.050 |
ittens | +0.042 |
omed | +0.038 |
atmeal | +0.038 |
inc | +0.038 |
Neg logit contributions | |
baby | -0.022 |
tered | -0.022 |
decides | -0.019 |
generation | -0.019 |
wants | -0.018 |
Token | we |
Token ID | 356 |
Feature activation | -5.69e-03 |
Pos logit contributions | |
aj | +0.039 |
ittens | +0.031 |
omed | +0.031 |
uddle | +0.030 |
inc | +0.029 |
Neg logit contributions | |
baby | -0.019 |
tered | -0.018 |
generation | -0.016 |
infant | -0.015 |
Welcome | -0.015 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
aj | +0.006 |
ittens | +0.005 |
omed | +0.005 |
igs | +0.004 |
inc | +0.004 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.006 |
decides | -0.005 |
infant | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +3.43e-03 |
Pos logit contributions | |
generation | +0.046 |
Whoever | +0.044 |
tered | +0.042 |
decides | +0.042 |
baby | +0.041 |
Neg logit contributions | |
aj | -0.052 |
ittens | -0.043 |
Johnny | -0.037 |
omed | -0.036 |
fing | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +3.73e-03 |
Pos logit contributions | |
tered | +0.003 |
baby | +0.003 |
generation | +0.003 |
decides | +0.003 |
infant | +0.003 |
Neg logit contributions | |
aj | -0.008 |
ittens | -0.006 |
omed | -0.006 |
inc | -0.006 |
atmeal | -0.006 |
Token | � |
Token ID | 6184 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
tered | +0.003 |
baby | +0.003 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.009 |
ittens | -0.008 |
omed | -0.008 |
inc | -0.007 |
atmeal | -0.007 |
Token | � |
Token ID | 95 |
Feature activation | -4.15e-02 |
Pos logit contributions | |
aj | +0.089 |
ittens | +0.065 |
omed | +0.065 |
light | +0.060 |
inations | +0.059 |
Neg logit contributions | |
tered | -0.066 |
generation | -0.063 |
Welcome | -0.061 |
sneak | -0.061 |
Whoever | -0.060 |
Token | € |
Token ID | 26391 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
aj | +0.085 |
ittens | +0.069 |
igs | +0.066 |
omed | +0.064 |
uddle | +0.063 |
Neg logit contributions | |
tered | -0.052 |
generation | -0.050 |
Welcome | -0.049 |
Give | -0.047 |
five | -0.046 |
Token | � |
Token ID | 129 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
aj | +0.146 |
fing | +0.143 |
igs | +0.140 |
ode | +0.137 |
cel | +0.135 |
Neg logit contributions | |
wants | -0.108 |
lder | -0.104 |
loves | -0.101 |
is | -0.098 |
Give | -0.093 |
Token | � |
Token ID | 241 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
aj | +0.018 |
ittens | +0.015 |
omed | +0.014 |
atmeal | +0.013 |
inc | +0.013 |
Neg logit contributions | |
tered | -0.012 |
baby | -0.012 |
generation | -0.011 |
decides | -0.011 |
Welcome | -0.010 |
Token | Mom |
Token ID | 29252 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
tered | +0.031 |
baby | +0.031 |
generation | +0.030 |
infant | +0.029 |
decides | +0.028 |
Neg logit contributions | |
aj | -0.040 |
ittens | -0.033 |
inc | -0.030 |
Johnny | -0.030 |
omed | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
aj | +0.015 |
ittens | +0.012 |
omed | +0.012 |
igs | +0.011 |
inc | +0.011 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.011 |
generation | -0.011 |
decides | -0.010 |
infant | -0.010 |
Token | can |
Token ID | 460 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
aj | +0.045 |
ittens | +0.036 |
omed | +0.036 |
inc | +0.035 |
igs | +0.035 |
Neg logit contributions | |
baby | -0.024 |
tered | -0.019 |
Welcome | -0.019 |
infant | -0.018 |
decides | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | +8.12e-03 |
Pos logit contributions | |
baby | +0.014 |
tered | +0.014 |
generation | +0.013 |
decides | +0.012 |
infant | +0.012 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.017 |
omed | -0.016 |
inc | -0.016 |
atmeal | -0.015 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
baby | +0.009 |
tered | +0.008 |
generation | +0.008 |
infant | +0.007 |
Welcome | +0.007 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.014 |
omed | -0.014 |
inc | -0.013 |
fing | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +7.65e-03 |
Pos logit contributions | |
tered | +0.017 |
generation | +0.017 |
baby | +0.017 |
decides | +0.016 |
Welcome | +0.015 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.017 |
omed | -0.016 |
igs | -0.015 |
fing | -0.015 |
Token | � |
Token ID | 6184 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
tered | +0.006 |
baby | +0.005 |
generation | +0.005 |
decides | +0.005 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.016 |
omed | -0.016 |
inc | -0.015 |
fing | -0.015 |
Token | � |
Token ID | 95 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
aj | +0.085 |
ittens | +0.068 |
omed | +0.061 |
elbows | +0.059 |
ons | +0.058 |
Neg logit contributions | |
tered | -0.056 |
generation | -0.055 |
Welcome | -0.050 |
sneak | -0.050 |
Whoever | -0.050 |
Token | € |
Token ID | 26391 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
aj | +0.089 |
ittens | +0.078 |
igs | +0.069 |
uddle | +0.067 |
omed | +0.067 |
Neg logit contributions | |
tered | -0.045 |
generation | -0.044 |
Welcome | -0.040 |
Whoever | -0.038 |
example | -0.037 |
Token | � |
Token ID | 129 |
Feature activation | -1.54e-03 |
Pos logit contributions | |
aj | +0.176 |
ittens | +0.161 |
igs | +0.158 |
pr | +0.156 |
fing | +0.153 |
Neg logit contributions | |
wants | -0.099 |
Welcome | -0.088 |
They | -0.086 |
lder | -0.086 |
loves | -0.085 |
Token | � |
Token ID | 241 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
aj | +0.003 |
ittens | +0.003 |
omed | +0.002 |
atmeal | +0.002 |
inc | +0.002 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.002 |
Token | What |
Token ID | 2061 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
tered | +0.012 |
baby | +0.012 |
generation | +0.012 |
infant | +0.011 |
decides | +0.011 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
fing | -0.012 |
Token | kind |
Token ID | 1611 |
Feature activation | -5.89e-04 |
Pos logit contributions | |
tered | +0.012 |
baby | +0.012 |
generation | +0.011 |
infant | +0.010 |
decides | +0.010 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.018 |
omed | -0.018 |
fing | -0.017 |
atmeal | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
aj | +0.001 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.000 |
infant | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
generation | +0.025 |
tered | +0.024 |
Whoever | +0.023 |
baby | +0.023 |
decides | +0.023 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.025 |
omed | -0.024 |
Johnny | -0.023 |
Linda | -0.022 |
Token | dad |
Token ID | 9955 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
aj | +0.021 |
ittens | +0.018 |
omed | +0.017 |
atmeal | +0.016 |
inc | +0.016 |
Neg logit contributions | |
baby | -0.013 |
tered | -0.011 |
infant | -0.010 |
decides | -0.010 |
generation | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +8.17e-04 |
Pos logit contributions | |
tered | +0.041 |
generation | +0.041 |
baby | +0.039 |
infant | +0.036 |
Whoever | +0.036 |
Neg logit contributions | |
aj | -0.052 |
omed | -0.040 |
ittens | -0.039 |
fing | -0.037 |
inc | -0.036 |
Token | � |
Token ID | 6184 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.002 |
ittens | -0.002 |
omed | -0.002 |
inc | -0.002 |
atmeal | -0.002 |
Token | � |
Token ID | 95 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
aj | +0.117 |
ittens | +0.084 |
inations | +0.083 |
omed | +0.080 |
light | +0.079 |
Neg logit contributions | |
Welcome | -0.071 |
tered | -0.070 |
Give | -0.070 |
Whoever | -0.069 |
generation | -0.068 |
Token | € |
Token ID | 26391 |
Feature activation | -9.15e-02 |
Pos logit contributions | |
aj | +0.107 |
ittens | +0.087 |
igs | +0.080 |
omed | +0.079 |
inations | +0.078 |
Neg logit contributions | |
tered | -0.053 |
generation | -0.051 |
Welcome | -0.050 |
Give | -0.050 |
Whoever | -0.049 |
Token | � |
Token ID | 129 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
aj | +0.180 |
inations | +0.164 |
fing | +0.164 |
igs | +0.162 |
cel | +0.158 |
Neg logit contributions | |
wants | -0.081 |
lder | -0.078 |
Welcome | -0.070 |
They | -0.070 |
" | -0.069 |
Token | � |
Token ID | 241 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
aj | +0.022 |
ittens | +0.018 |
omed | +0.017 |
atmeal | +0.016 |
igs | +0.016 |
Neg logit contributions | |
tered | -0.012 |
baby | -0.012 |
generation | -0.012 |
decides | -0.011 |
Welcome | -0.011 |
Token | What |
Token ID | 2061 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
tered | +0.032 |
baby | +0.031 |
generation | +0.030 |
infant | +0.029 |
decides | +0.028 |
Neg logit contributions | |
aj | -0.046 |
ittens | -0.038 |
inc | -0.035 |
Johnny | -0.035 |
omed | -0.035 |
Token | is |
Token ID | 318 |
Feature activation | +8.15e-03 |
Pos logit contributions | |
tered | +0.005 |
baby | +0.005 |
generation | +0.005 |
decides | +0.004 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.010 |
ittens | -0.008 |
omed | -0.008 |
atmeal | -0.008 |
inc | -0.007 |
Token | this |
Token ID | 428 |
Feature activation | +9.42e-03 |
Pos logit contributions | |
tered | +0.010 |
baby | +0.010 |
generation | +0.009 |
decides | +0.009 |
Welcome | +0.008 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.012 |
igs | -0.012 |
inc | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +6.31e-04 |
Pos logit contributions | |
generation | +0.025 |
baby | +0.024 |
tered | +0.023 |
decides | +0.023 |
Welcome | +0.023 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.031 |
omed | -0.029 |
uddle | -0.028 |
inc | -0.027 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.001 |
ittens | -0.001 |
omed | -0.001 |
atmeal | -0.001 |
inc | -0.001 |
Token | away |
Token ID | 1497 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
baby | +0.014 |
tered | +0.014 |
generation | +0.014 |
decides | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.020 |
omed | -0.020 |
inc | -0.019 |
fing | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
generation | +0.021 |
tered | +0.020 |
baby | +0.020 |
decides | +0.020 |
Welcome | +0.019 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.018 |
omed | -0.017 |
inc | -0.017 |
igs | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | -9.68e-03 |
Pos logit contributions | |
baby | +0.006 |
tered | +0.006 |
generation | +0.006 |
decides | +0.005 |
infant | +0.005 |
Neg logit contributions | |
aj | -0.015 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
igs | -0.012 |
Token | tremb |
Token ID | 29868 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
aj | +0.021 |
ittens | +0.017 |
omed | +0.016 |
atmeal | +0.016 |
igs | +0.015 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.011 |
generation | -0.010 |
decides | -0.010 |
infant | -0.009 |
Token | led |
Token ID | 992 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
Welcome | +0.094 |
generation | +0.093 |
seventy | +0.091 |
sixty | +0.089 |
baby | +0.086 |
Neg logit contributions | |
aj | -0.045 |
ittens | -0.034 |
omed | -0.033 |
udd | -0.031 |
igs | -0.029 |
Token | as |
Token ID | 355 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
baby | +0.015 |
tered | +0.015 |
generation | +0.014 |
decides | +0.013 |
Welcome | +0.013 |
Neg logit contributions | |
aj | -0.024 |
ittens | -0.019 |
omed | -0.019 |
inc | -0.018 |
igs | -0.017 |
Token | they |
Token ID | 484 |
Feature activation | -3.97e-02 |
Pos logit contributions | |
generation | +0.059 |
decides | +0.056 |
Whoever | +0.056 |
tered | +0.054 |
Welcome | +0.054 |
Neg logit contributions | |
aj | -0.054 |
dizz | -0.042 |
ittens | -0.041 |
igs | -0.041 |
mo | -0.040 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
aj | +0.094 |
ittens | +0.076 |
atmeal | +0.072 |
omed | +0.070 |
igs | +0.070 |
Neg logit contributions | |
baby | -0.041 |
tered | -0.040 |
decides | -0.033 |
sneak | -0.033 |
take | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +7.60e-03 |
Pos logit contributions | |
baby | +0.015 |
tered | +0.015 |
generation | +0.015 |
decides | +0.013 |
infant | +0.013 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.020 |
omed | -0.020 |
inc | -0.019 |
uddle | -0.019 |
Token | go |
Token ID | 467 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
aj | +0.027 |
ittens | +0.023 |
omed | +0.022 |
atmeal | +0.021 |
inc | +0.021 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.009 |
generation | -0.009 |
decides | -0.008 |
Welcome | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
tered | +0.022 |
generation | +0.021 |
baby | +0.020 |
infant | +0.019 |
decides | +0.018 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.029 |
omed | -0.029 |
fing | -0.027 |
inc | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
tered | +0.020 |
generation | +0.018 |
baby | +0.018 |
decides | +0.017 |
vows | +0.017 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.020 |
fing | -0.019 |
omed | -0.019 |
Johnny | -0.019 |
Token | house |
Token ID | 2156 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
tered | +0.022 |
generation | +0.020 |
baby | +0.020 |
decides | +0.019 |
Welcome | +0.019 |
Neg logit contributions | |
aj | -0.022 |
ittens | -0.016 |
uddle | -0.015 |
omed | -0.015 |
inc | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
tered | +0.025 |
baby | +0.024 |
generation | +0.024 |
decides | +0.022 |
infant | +0.022 |
Neg logit contributions | |
aj | -0.028 |
ittens | -0.021 |
omed | -0.020 |
inc | -0.020 |
fing | -0.019 |
Token | knock |
Token ID | 10643 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
tered | +0.004 |
baby | +0.004 |
generation | +0.004 |
infant | +0.004 |
decides | +0.004 |
Neg logit contributions | |
aj | -0.009 |
ittens | -0.007 |
omed | -0.007 |
atmeal | -0.007 |
inc | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
generation | +0.080 |
tered | +0.076 |
infant | +0.072 |
lder | +0.070 |
baby | +0.069 |
Neg logit contributions | |
aj | -0.062 |
omed | -0.050 |
fing | -0.046 |
ittens | -0.044 |
uddle | -0.043 |
Token | A |
Token ID | 317 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.008 |
generation | +0.008 |
infant | +0.007 |
decides | +0.007 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.021 |
omed | -0.020 |
inc | -0.020 |
fing | -0.019 |
Token | kind |
Token ID | 1611 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
tered | +0.007 |
baby | +0.006 |
generation | +0.006 |
decides | +0.006 |
infant | +0.006 |
Neg logit contributions | |
aj | -0.011 |
ittens | -0.009 |
omed | -0.009 |
inc | -0.008 |
atmeal | -0.008 |
Token | woman |
Token ID | 2415 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
tered | +0.026 |
generation | +0.024 |
baby | +0.023 |
decides | +0.023 |
Whoever | +0.022 |
Neg logit contributions | |
aj | -0.038 |
ittens | -0.031 |
omed | -0.030 |
inc | -0.029 |
uddle | -0.029 |
Token | opens |
Token ID | 9808 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
tered | +0.027 |
generation | +0.026 |
baby | +0.025 |
infant | +0.023 |
ancy | +0.022 |
Neg logit contributions | |
aj | -0.049 |
omed | -0.040 |
ittens | -0.038 |
fing | -0.037 |
inc | -0.037 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
tered | +0.058 |
generation | +0.049 |
Whoever | +0.048 |
ancy | +0.045 |
seventy | +0.044 |
Neg logit contributions | |
aj | -0.062 |
ittens | -0.049 |
uddle | -0.046 |
vest | -0.045 |
inc | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
tered | +0.037 |
generation | +0.036 |
baby | +0.035 |
Whoever | +0.034 |
ancy | +0.033 |
Neg logit contributions | |
aj | -0.035 |
ittens | -0.027 |
omed | -0.025 |
atmeal | -0.024 |
mers | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
tered | +0.023 |
baby | +0.022 |
generation | +0.022 |
Whoever | +0.020 |
decides | +0.020 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.025 |
omed | -0.023 |
inc | -0.022 |
atmeal | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | -9.14e-04 |
Pos logit contributions | |
baby | +0.006 |
tered | +0.006 |
generation | +0.006 |
infant | +0.005 |
Welcome | +0.005 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.016 |
omed | -0.015 |
inc | -0.015 |
atmeal | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
aj | +0.002 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | mean |
Token ID | 1612 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
tered | +0.065 |
generation | +0.056 |
Whoever | +0.055 |
ively | +0.054 |
ancy | +0.054 |
Neg logit contributions | |
aj | -0.062 |
ittens | -0.050 |
vest | -0.049 |
dizz | -0.048 |
mo | -0.048 |
Token | animal |
Token ID | 5044 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
tered | +0.081 |
generation | +0.072 |
Whoever | +0.071 |
seventy | +0.068 |
vows | +0.067 |
Neg logit contributions | |
aj | -0.070 |
ittens | -0.061 |
vest | -0.056 |
? | -0.054 |
uddle | -0.052 |
Token | ." |
Token ID | 526 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
tered | +0.020 |
baby | +0.019 |
generation | +0.019 |
decides | +0.018 |
Whoever | +0.018 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.018 |
omed | -0.017 |
inc | -0.016 |
atmeal | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
aj | +0.141 |
atmeal | +0.121 |
vell | +0.115 |
omed | +0.115 |
ode | +0.114 |
Neg logit contributions | |
They | -0.029 |
baby | -0.020 |
Who | -0.017 |
If | -0.017 |
Let | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
aj | +0.045 |
ittens | +0.036 |
atmeal | +0.036 |
omed | +0.035 |
inc | +0.034 |
Neg logit contributions | |
baby | -0.018 |
tered | -0.018 |
generation | -0.015 |
Welcome | -0.015 |
decides | -0.014 |
Token | But |
Token ID | 1537 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
aj | +0.063 |
atmeal | +0.048 |
omed | +0.046 |
ittens | +0.045 |
auldron | +0.044 |
Neg logit contributions | |
tered | -0.037 |
baby | -0.036 |
Let | -0.034 |
generation | -0.032 |
person | -0.032 |
Token | mel |
Token ID | 7758 |
Feature activation | -7.07e-02 |
Pos logit contributions | |
aj | +0.044 |
ittens | +0.035 |
omed | +0.033 |
igs | +0.032 |
fing | +0.031 |
Neg logit contributions | |
baby | -0.030 |
infant | -0.024 |
generation | -0.024 |
tered | -0.024 |
Welcome | -0.024 |
Token | on |
Token ID | 261 |
Feature activation | -5.61e-02 |
Pos logit contributions | |
aj | +0.124 |
elbows | +0.088 |
nightmares | +0.081 |
underwear | +0.079 |
stressed | +0.075 |
Neg logit contributions | |
baby | -0.094 |
tered | -0.094 |
y | -0.091 |
Welcome | -0.089 |
generation | -0.089 |
Token | home |
Token ID | 1363 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
aj | +0.165 |
omed | +0.146 |
ittens | +0.143 |
inc | +0.137 |
igs | +0.136 |
Neg logit contributions | |
baby | -0.019 |
from | -0.011 |
generation | -0.010 |
go | -0.008 |
person | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
aj | +0.038 |
ittens | +0.032 |
omed | +0.030 |
igs | +0.029 |
inc | +0.029 |
Neg logit contributions | |
tered | -0.021 |
baby | -0.020 |
generation | -0.020 |
infant | -0.017 |
Welcome | -0.017 |
Token | him |
Token ID | 683 |
Feature activation | -3.41e-02 |
Pos logit contributions | |
aj | +0.039 |
ittens | +0.031 |
omed | +0.030 |
uddle | +0.030 |
inc | +0.030 |
Neg logit contributions | |
baby | -0.017 |
tered | -0.016 |
generation | -0.016 |
infant | -0.014 |
Welcome | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
aj | +0.074 |
ittens | +0.063 |
omed | +0.059 |
igs | +0.058 |
atmeal | +0.058 |
Neg logit contributions | |
baby | -0.037 |
tered | -0.035 |
generation | -0.032 |
infant | -0.030 |
Welcome | -0.030 |
Token | He |
Token ID | 679 |
Feature activation | +2.01e-02 |
Pos logit contributions | |
baby | +0.092 |
ancy | +0.086 |
sneak | +0.085 |
tered | +0.082 |
Whoever | +0.080 |
Neg logit contributions | |
aj | -0.072 |
omed | -0.059 |
mers | -0.058 |
Johnny | -0.058 |
ittens | -0.057 |
Token | was |
Token ID | 373 |
Feature activation | -9.65e-04 |
Pos logit contributions | |
generation | +0.025 |
tered | +0.025 |
baby | +0.025 |
infant | +0.023 |
Welcome | +0.023 |
Neg logit contributions | |
aj | -0.039 |
ittens | -0.031 |
omed | -0.029 |
inc | -0.028 |
atmeal | -0.028 |
Token | very |
Token ID | 845 |
Feature activation | +9.18e-03 |
Pos logit contributions | |
aj | +0.002 |
ittens | +0.002 |
omed | +0.002 |
inc | +0.002 |
atmeal | +0.002 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | careful |
Token ID | 8161 |
Feature activation | +7.51e-03 |
Pos logit contributions | |
tered | +0.013 |
generation | +0.012 |
baby | +0.012 |
Whoever | +0.011 |
decides | +0.011 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
fing | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +7.49e-03 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.009 |
generation | +0.009 |
decides | +0.009 |
infant | +0.008 |
Neg logit contributions | |
aj | -0.015 |
ittens | -0.012 |
omed | -0.011 |
inc | -0.011 |
atmeal | -0.010 |
Token | string |
Token ID | 4731 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.013 |
generation | +0.013 |
decides | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
uddle | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
baby | +0.012 |
tered | +0.012 |
generation | +0.011 |
decides | +0.011 |
Welcome | +0.010 |
Neg logit contributions | |
aj | -0.021 |
ittens | -0.017 |
omed | -0.016 |
inc | -0.015 |
igs | -0.015 |
Token | started |
Token ID | 2067 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
baby | +0.023 |
generation | +0.023 |
tered | +0.023 |
Welcome | +0.021 |
infant | +0.021 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.024 |
omed | -0.023 |
inc | -0.023 |
igs | -0.023 |
Token | tying |
Token ID | 28379 |
Feature activation | +4.51e-03 |
Pos logit contributions | |
tered | +0.020 |
baby | +0.019 |
generation | +0.019 |
decides | +0.018 |
infant | +0.017 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.026 |
omed | -0.025 |
inc | -0.025 |
igs | -0.025 |
Token | knots |
Token ID | 33620 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
baby | +0.005 |
tered | +0.005 |
generation | +0.005 |
decides | +0.005 |
infant | +0.005 |
Neg logit contributions | |
aj | -0.009 |
ittens | -0.007 |
omed | -0.007 |
inc | -0.007 |
igs | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
baby | +0.025 |
generation | +0.024 |
tered | +0.024 |
decides | +0.023 |
infant | +0.023 |
Neg logit contributions | |
aj | -0.031 |
ittens | -0.025 |
omed | -0.024 |
inc | -0.023 |
igs | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | +6.19e-03 |
Pos logit contributions | |
baby | +0.062 |
tered | +0.061 |
vows | +0.060 |
decides | +0.060 |
generation | +0.059 |
Neg logit contributions | |
aj | -0.061 |
ittens | -0.053 |
inc | -0.048 |
omed | -0.048 |
dizz | -0.046 |
Token | tied |
Token ID | 8165 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.008 |
generation | +0.007 |
infant | +0.007 |
Welcome | +0.007 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.010 |
omed | -0.009 |
inc | -0.009 |
igs | -0.009 |
Token | together |
Token ID | 1978 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
tered | +0.027 |
baby | +0.026 |
generation | +0.026 |
decides | +0.025 |
infant | +0.024 |
Neg logit contributions | |
aj | -0.039 |
ittens | -0.032 |
omed | -0.030 |
igs | -0.030 |
inc | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
generation | +0.038 |
baby | +0.037 |
tered | +0.037 |
decides | +0.036 |
infant | +0.035 |
Neg logit contributions | |
aj | -0.051 |
ittens | -0.043 |
omed | -0.041 |
igs | -0.040 |
inc | -0.039 |
Token | strings |
Token ID | 13042 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
generation | +0.051 |
tered | +0.050 |
baby | +0.048 |
Welcome | +0.048 |
ancy | +0.047 |
Neg logit contributions | |
aj | -0.059 |
ittens | -0.046 |
igs | -0.044 |
omed | -0.043 |
vest | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
aj | +0.065 |
ittens | +0.054 |
omed | +0.050 |
atmeal | +0.050 |
igs | +0.050 |
Neg logit contributions | |
baby | -0.036 |
tered | -0.035 |
generation | -0.031 |
infant | -0.029 |
Welcome | -0.027 |
Token | He |
Token ID | 679 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
baby | +0.020 |
tered | +0.020 |
generation | +0.019 |
decides | +0.018 |
infant | +0.017 |
Neg logit contributions | |
aj | -0.034 |
ittens | -0.027 |
omed | -0.025 |
inc | -0.024 |
Johnny | -0.024 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.25e-03 |
Pos logit contributions | |
aj | +0.014 |
ittens | +0.012 |
omed | +0.011 |
atmeal | +0.011 |
igs | +0.010 |
Neg logit contributions | |
baby | -0.009 |
tered | -0.008 |
generation | -0.008 |
decides | -0.008 |
infant | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
aj | +0.009 |
ittens | +0.007 |
omed | +0.007 |
atmeal | +0.007 |
inc | +0.007 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.005 |
decides | -0.004 |
infant | -0.004 |
Token | t |
Token ID | 256 |
Feature activation | +5.98e-03 |
Pos logit contributions | |
generation | +0.019 |
tered | +0.019 |
baby | +0.019 |
decides | +0.018 |
Welcome | +0.017 |
Neg logit contributions | |
aj | -0.039 |
ittens | -0.032 |
omed | -0.031 |
dizz | -0.030 |
inc | -0.030 |
Token | ingle |
Token ID | 17697 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
baby | +0.009 |
tered | +0.009 |
generation | +0.009 |
decides | +0.008 |
Welcome | +0.008 |
Neg logit contributions | |
aj | -0.010 |
ittens | -0.008 |
omed | -0.007 |
inc | -0.007 |
atmeal | -0.007 |
Token | go |
Token ID | 467 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
generation | +0.038 |
decides | +0.037 |
tered | +0.036 |
baby | +0.035 |
ancy | +0.035 |
Neg logit contributions | |
aj | -0.044 |
omed | -0.036 |
ittens | -0.036 |
mo | -0.034 |
dizz | -0.034 |
Token | up |
Token ID | 510 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
aj | +0.010 |
ittens | +0.008 |
omed | +0.007 |
atmeal | +0.007 |
igs | +0.007 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.005 |
Welcome | -0.005 |
infant | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
aj | +0.046 |
ittens | +0.040 |
atmeal | +0.037 |
omed | +0.036 |
uddle | +0.036 |
Neg logit contributions | |
baby | -0.017 |
tered | -0.016 |
generation | -0.015 |
infant | -0.013 |
Welcome | -0.012 |
Token | leg |
Token ID | 1232 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
aj | +0.026 |
omed | +0.021 |
ittens | +0.021 |
atmeal | +0.020 |
fing | +0.020 |
Neg logit contributions | |
baby | -0.019 |
tered | -0.017 |
generation | -0.017 |
infant | -0.016 |
Welcome | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
aj | +0.030 |
ittens | +0.024 |
omed | +0.023 |
atmeal | +0.023 |
igs | +0.023 |
Neg logit contributions | |
baby | -0.015 |
tered | -0.014 |
generation | -0.013 |
infant | -0.012 |
Welcome | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
baby | +0.007 |
tered | +0.007 |
generation | +0.007 |
decides | +0.006 |
Welcome | +0.006 |
Neg logit contributions | |
aj | -0.009 |
ittens | -0.007 |
omed | -0.006 |
inc | -0.006 |
atmeal | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +6.75e-03 |
Pos logit contributions | |
aj | +0.031 |
ittens | +0.026 |
omed | +0.024 |
atmeal | +0.024 |
uddle | +0.023 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.012 |
generation | -0.011 |
Welcome | -0.010 |
decides | -0.010 |
Token | had |
Token ID | 550 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
baby | +0.006 |
tered | +0.006 |
generation | +0.006 |
infant | +0.005 |
decides | +0.005 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.013 |
inc | -0.012 |
atmeal | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
tered | +0.019 |
baby | +0.018 |
generation | +0.018 |
decides | +0.017 |
ancy | +0.016 |
Neg logit contributions | |
aj | -0.032 |
ittens | -0.026 |
inc | -0.024 |
omed | -0.024 |
Johnny | -0.023 |
Token | special |
Token ID | 2041 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
tered | +0.024 |
generation | +0.022 |
baby | +0.021 |
decides | +0.021 |
Welcome | +0.020 |
Neg logit contributions | |
aj | -0.033 |
ittens | -0.026 |
uddle | -0.024 |
inc | -0.023 |
omed | -0.023 |
Token | instrument |
Token ID | 8875 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
tered | +0.021 |
baby | +0.020 |
generation | +0.019 |
decides | +0.018 |
Welcome | +0.018 |
Neg logit contributions | |
aj | -0.025 |
ittens | -0.020 |
omed | -0.018 |
inc | -0.017 |
atmeal | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
tered | +0.020 |
baby | +0.020 |
generation | +0.019 |
decides | +0.018 |
Whoever | +0.018 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.021 |
omed | -0.019 |
inc | -0.019 |
igs | -0.018 |
Token | she |
Token ID | 673 |
Feature activation | +8.06e-03 |
Pos logit contributions | |
aj | +0.050 |
ittens | +0.041 |
omed | +0.039 |
uddle | +0.037 |
inc | +0.037 |
Neg logit contributions | |
baby | -0.030 |
tered | -0.029 |
generation | -0.027 |
Welcome | -0.026 |
infant | -0.025 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.007 |
generation | +0.007 |
decides | +0.006 |
infant | +0.006 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.015 |
omed | -0.014 |
inc | -0.014 |
atmeal | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
tered | +0.016 |
baby | +0.015 |
generation | +0.015 |
decides | +0.014 |
Whoever | +0.014 |
Neg logit contributions | |
aj | -0.029 |
ittens | -0.024 |
omed | -0.022 |
inc | -0.022 |
igs | -0.022 |
Token | play |
Token ID | 711 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
baby | +0.003 |
tered | +0.003 |
generation | +0.003 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.004 |
ittens | -0.003 |
omed | -0.003 |
atmeal | -0.003 |
inc | -0.003 |
Token | drops |
Token ID | 10532 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
tered | +0.022 |
generation | +0.021 |
baby | +0.021 |
infant | +0.019 |
ancy | +0.018 |
Neg logit contributions | |
aj | -0.044 |
omed | -0.034 |
ittens | -0.034 |
inc | -0.033 |
uddle | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
tered | +0.004 |
baby | +0.004 |
generation | +0.004 |
decides | +0.004 |
infant | +0.004 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.005 |
inc | -0.005 |
igs | -0.005 |
Token | car |
Token ID | 1097 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
tered | +0.010 |
baby | +0.010 |
generation | +0.010 |
decides | +0.009 |
Welcome | +0.009 |
Neg logit contributions | |
aj | -0.014 |
ittens | -0.011 |
omed | -0.010 |
inc | -0.010 |
atmeal | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
baby | +0.017 |
generation | +0.017 |
tered | +0.016 |
decides | +0.015 |
Welcome | +0.015 |
Neg logit contributions | |
aj | -0.026 |
ittens | -0.020 |
omed | -0.020 |
inc | -0.019 |
uddle | -0.018 |
Token | runs |
Token ID | 4539 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
aj | +0.006 |
ittens | +0.005 |
omed | +0.005 |
atmeal | +0.005 |
inc | +0.005 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.003 |
infant | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
generation | +0.040 |
tered | +0.038 |
baby | +0.037 |
infant | +0.035 |
decides | +0.034 |
Neg logit contributions | |
aj | -0.050 |
inc | -0.039 |
omed | -0.039 |
dizz | -0.037 |
ittens | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
tered | +0.033 |
generation | +0.030 |
decides | +0.030 |
baby | +0.030 |
infant | +0.028 |
Neg logit contributions | |
aj | -0.033 |
ittens | -0.026 |
Johnny | -0.024 |
fing | -0.024 |
Linda | -0.024 |
Token | doll |
Token ID | 3654 |
Feature activation | -7.80e-03 |
Pos logit contributions | |
tered | +0.051 |
generation | +0.047 |
ancy | +0.045 |
Whoever | +0.044 |
baby | +0.044 |
Neg logit contributions | |
aj | -0.054 |
vest | -0.038 |
uddle | -0.038 |
mo | -0.038 |
ittens | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
aj | +0.015 |
ittens | +0.012 |
omed | +0.012 |
igs | +0.011 |
atmeal | +0.011 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.010 |
generation | -0.010 |
infant | -0.009 |
decides | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +1.37e-03 |
Pos logit contributions | |
aj | +0.026 |
ittens | +0.021 |
atmeal | +0.021 |
omed | +0.021 |
igs | +0.020 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.011 |
generation | -0.010 |
Welcome | -0.010 |
decides | -0.009 |
Token | grabs |
Token ID | 22378 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.003 |
ittens | -0.003 |
omed | -0.002 |
inc | -0.002 |
atmeal | -0.002 |
Token | year |
Token ID | 1941 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
baby | +0.014 |
tered | +0.014 |
generation | +0.013 |
decides | +0.012 |
infant | +0.011 |
Neg logit contributions | |
aj | -0.037 |
ittens | -0.032 |
omed | -0.030 |
inc | -0.029 |
atmeal | -0.029 |
Token | old |
Token ID | 1468 |
Feature activation | -4.29e-03 |
Pos logit contributions | |
generation | +0.047 |
Welcome | +0.047 |
baby | +0.046 |
tered | +0.045 |
decides | +0.045 |
Neg logit contributions | |
aj | -0.058 |
ittens | -0.049 |
igs | -0.046 |
inc | -0.043 |
omed | -0.041 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
aj | +0.009 |
ittens | +0.007 |
omed | +0.007 |
atmeal | +0.007 |
inc | +0.007 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.005 |
decides | -0.004 |
infant | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
tered | +0.014 |
baby | +0.014 |
generation | +0.014 |
infant | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.027 |
ittens | -0.022 |
omed | -0.021 |
inc | -0.021 |
atmeal | -0.020 |
Token | very |
Token ID | 845 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
tered | +0.008 |
baby | +0.008 |
generation | +0.007 |
decides | +0.007 |
Welcome | +0.007 |
Neg logit contributions | |
aj | -0.013 |
ittens | -0.011 |
omed | -0.010 |
inc | -0.010 |
atmeal | -0.010 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
generation | +0.026 |
tered | +0.026 |
baby | +0.025 |
Whoever | +0.024 |
decides | +0.023 |
Neg logit contributions | |
aj | -0.030 |
ittens | -0.023 |
inc | -0.022 |
omed | -0.021 |
dizz | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.002 |
ittens | -0.002 |
omed | -0.002 |
inc | -0.001 |
atmeal | -0.001 |
Token | But |
Token ID | 887 |
Feature activation | -2.49e-03 |
Pos logit contributions | |
aj | +0.005 |
ittens | +0.004 |
omed | +0.004 |
atmeal | +0.004 |
inc | +0.004 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
aj | +0.005 |
ittens | +0.004 |
omed | +0.004 |
inc | +0.004 |
atmeal | +0.004 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.003 |
infant | -0.003 |
Token | accepted |
Token ID | 6292 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
aj | +0.009 |
ittens | +0.008 |
omed | +0.007 |
atmeal | +0.007 |
igs | +0.007 |
Neg logit contributions | |
baby | -0.004 |
tered | -0.004 |
generation | -0.004 |
decides | -0.004 |
infant | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | +4.96e-03 |
Pos logit contributions | |
aj | +0.037 |
ittens | +0.030 |
omed | +0.029 |
atmeal | +0.028 |
uddle | +0.028 |
Neg logit contributions | |
baby | -0.018 |
tered | -0.017 |
generation | -0.016 |
infant | -0.014 |
decides | -0.014 |
Token | sorry |
Token ID | 7926 |
Feature activation | -8.72e-03 |
Pos logit contributions | |
aj | +0.055 |
ittens | +0.048 |
uddle | +0.045 |
omed | +0.044 |
atmeal | +0.044 |
Neg logit contributions | |
baby | -0.030 |
tered | -0.026 |
infant | -0.025 |
ear | -0.025 |
Welcome | -0.023 |
Token | again |
Token ID | 757 |
Feature activation | -5.22e-03 |
Pos logit contributions | |
aj | +0.019 |
ittens | +0.015 |
omed | +0.015 |
atmeal | +0.015 |
inc | +0.014 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.009 |
generation | -0.008 |
decides | -0.008 |
Welcome | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
aj | +0.010 |
ittens | +0.008 |
omed | +0.008 |
atmeal | +0.008 |
igs | +0.007 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.007 |
generation | -0.006 |
decides | -0.006 |
infant | -0.006 |
Token | helped |
Token ID | 4193 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
tered | +0.015 |
baby | +0.015 |
generation | +0.015 |
ancy | +0.014 |
Whoever | +0.014 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.015 |
omed | -0.014 |
fing | -0.014 |
atmeal | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
tered | +0.018 |
baby | +0.017 |
generation | +0.017 |
decides | +0.016 |
Welcome | +0.016 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.015 |
Johnny | -0.013 |
omed | -0.013 |
inc | -0.013 |
Token | clean |
Token ID | 3424 |
Feature activation | +8.50e-03 |
Pos logit contributions | |
tered | +0.027 |
generation | +0.027 |
baby | +0.027 |
Welcome | +0.025 |
vows | +0.025 |
Neg logit contributions | |
aj | -0.027 |
ittens | -0.019 |
omed | -0.018 |
atmeal | -0.018 |
inc | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +6.42e-03 |
Pos logit contributions | |
tered | +0.009 |
baby | +0.009 |
generation | +0.009 |
Welcome | +0.008 |
decides | +0.008 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.015 |
omed | -0.014 |
igs | -0.014 |
inc | -0.014 |
Token | room |
Token ID | 2119 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
tered | +0.010 |
baby | +0.010 |
generation | +0.009 |
decides | +0.009 |
infant | +0.009 |
Neg logit contributions | |
aj | -0.011 |
ittens | -0.009 |
omed | -0.008 |
inc | -0.008 |
uddle | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.49e-03 |
Pos logit contributions | |
aj | +0.027 |
ittens | +0.022 |
omed | +0.021 |
atmeal | +0.020 |
inc | +0.020 |
Neg logit contributions | |
baby | -0.017 |
tered | -0.017 |
generation | -0.016 |
decides | -0.015 |
infant | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
aj | +0.010 |
ittens | +0.008 |
omed | +0.008 |
atmeal | +0.007 |
inc | +0.007 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.005 |
infant | -0.004 |
decides | -0.004 |
Token | learned |
Token ID | 4499 |
Feature activation | -9.68e-03 |
Pos logit contributions | |
aj | +0.032 |
ittens | +0.027 |
omed | +0.025 |
igs | +0.024 |
atmeal | +0.024 |
Neg logit contributions | |
baby | -0.018 |
tered | -0.018 |
decides | -0.017 |
generation | -0.016 |
infant | -0.015 |
Token | Sam |
Token ID | 16305 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
aj | +0.034 |
ittens | +0.027 |
omed | +0.027 |
atmeal | +0.026 |
uddle | +0.026 |
Neg logit contributions | |
tered | -0.017 |
baby | -0.016 |
generation | -0.016 |
Welcome | -0.015 |
Whoever | -0.014 |
Token | shook |
Token ID | 14682 |
Feature activation | -8.52e-03 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.003 |
ittens | -0.003 |
omed | -0.003 |
inc | -0.003 |
atmeal | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
aj | +0.019 |
ittens | +0.016 |
omed | +0.015 |
atmeal | +0.015 |
uddle | +0.014 |
Neg logit contributions | |
baby | -0.009 |
tered | -0.009 |
generation | -0.008 |
infant | -0.008 |
decides | -0.008 |
Token | head |
Token ID | 1182 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
generation | +0.022 |
tered | +0.020 |
Welcome | +0.019 |
decides | +0.019 |
Whoever | +0.018 |
Neg logit contributions | |
aj | -0.046 |
ittens | -0.037 |
vest | -0.034 |
uddle | -0.034 |
igs | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
generation | +0.050 |
baby | +0.047 |
decides | +0.046 |
tered | +0.045 |
Welcome | +0.045 |
Neg logit contributions | |
aj | -0.048 |
ittens | -0.037 |
omed | -0.036 |
inc | -0.033 |
dizz | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
aj | +0.044 |
ittens | +0.037 |
atmeal | +0.036 |
inations | +0.035 |
omed | +0.035 |
Neg logit contributions | |
baby | -0.014 |
tered | -0.014 |
Welcome | -0.012 |
generation | -0.012 |
decides | -0.011 |
Token | did |
Token ID | 750 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
aj | +0.013 |
ittens | +0.011 |
omed | +0.010 |
atmeal | +0.010 |
igs | +0.010 |
Neg logit contributions | |
baby | -0.009 |
tered | -0.008 |
generation | -0.008 |
decides | -0.008 |
infant | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
aj | +0.040 |
ittens | +0.033 |
atmeal | +0.031 |
omed | +0.031 |
uddle | +0.030 |
Neg logit contributions | |
tered | -0.019 |
baby | -0.019 |
generation | -0.016 |
decides | -0.016 |
sneak | -0.015 |
Token | like |
Token ID | 588 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
aj | +0.046 |
ittens | +0.038 |
omed | +0.037 |
uddle | +0.036 |
igs | +0.035 |
Neg logit contributions | |
baby | -0.015 |
tered | -0.015 |
generation | -0.012 |
decides | -0.012 |
ny | -0.012 |
Token | dolls |
Token ID | 36062 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
aj | +0.036 |
ittens | +0.029 |
omed | +0.029 |
atmeal | +0.027 |
inc | +0.027 |
Neg logit contributions | |
baby | -0.022 |
tered | -0.020 |
generation | -0.019 |
infant | -0.018 |
decides | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
aj | +0.051 |
ittens | +0.041 |
omed | +0.039 |
igs | +0.039 |
Johnny | +0.038 |
Neg logit contributions | |
baby | -0.029 |
tered | -0.028 |
generation | -0.024 |
decides | -0.024 |
infant | -0.023 |
Token | " |
Token ID | 1 |
Feature activation | -1.37e-03 |
Pos logit contributions | |
baby | +0.011 |
tered | +0.011 |
generation | +0.011 |
infant | +0.010 |
decides | +0.009 |
Neg logit contributions | |
aj | -0.019 |
ittens | -0.015 |
omed | -0.014 |
inc | -0.014 |
fing | -0.014 |
Token | Yes |
Token ID | 5297 |
Feature activation | -2.21e-03 |
Pos logit contributions | |
aj | +0.003 |
ittens | +0.002 |
omed | +0.002 |
atmeal | +0.002 |
inc | +0.002 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.002 |
decides | -0.002 |
infant | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
aj | +0.004 |
ittens | +0.003 |
omed | +0.003 |
atmeal | +0.003 |
inc | +0.003 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.003 |
infant | -0.003 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
aj | +0.024 |
ittens | +0.019 |
omed | +0.019 |
atmeal | +0.018 |
igs | +0.018 |
Neg logit contributions | |
baby | -0.014 |
tered | -0.012 |
infant | -0.011 |
decides | -0.011 |
generation | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
aj | +0.032 |
ittens | +0.027 |
omed | +0.025 |
igs | +0.025 |
atmeal | +0.025 |
Neg logit contributions | |
baby | -0.016 |
tered | -0.014 |
decides | -0.013 |
generation | -0.013 |
infant | -0.013 |
Token | we |
Token ID | 356 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
aj | +0.025 |
ittens | +0.021 |
omed | +0.020 |
inc | +0.019 |
atmeal | +0.019 |
Neg logit contributions | |
baby | -0.013 |
tered | -0.011 |
infant | -0.010 |
decides | -0.010 |
Welcome | -0.010 |
Token | can |
Token ID | 460 |
Feature activation | -2.61e-03 |
Pos logit contributions | |
aj | +0.090 |
ittens | +0.078 |
igs | +0.072 |
omed | +0.070 |
light | +0.070 |
Neg logit contributions | |
baby | -0.025 |
decides | -0.025 |
tered | -0.022 |
wants | -0.022 |
take | -0.020 |
Token | do |
Token ID | 466 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
aj | +0.006 |
ittens | +0.005 |
omed | +0.005 |
inc | +0.004 |
atmeal | +0.004 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.002 |
infant | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
aj | +0.036 |
ittens | +0.030 |
omed | +0.029 |
atmeal | +0.027 |
inc | +0.027 |
Neg logit contributions | |
baby | -0.016 |
tered | -0.015 |
generation | -0.013 |
decides | -0.013 |
infant | -0.012 |
Token | ," |
Token ID | 553 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
tered | +0.014 |
generation | +0.014 |
baby | +0.014 |
Welcome | +0.013 |
Whoever | +0.013 |
Neg logit contributions | |
aj | -0.020 |
ittens | -0.015 |
omed | -0.014 |
uddle | -0.014 |
inc | -0.014 |
Token | Sara |
Token ID | 24799 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
baby | +0.002 |
tered | +0.002 |
generation | +0.002 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.003 |
ittens | -0.003 |
omed | -0.003 |
inc | -0.002 |
atmeal | -0.002 |
Token | really |
Token ID | 1107 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
aj | +0.036 |
ittens | +0.030 |
atmeal | +0.029 |
omed | +0.028 |
uddle | +0.028 |
Neg logit contributions | |
tered | -0.013 |
baby | -0.012 |
generation | -0.010 |
decides | -0.009 |
Whoever | -0.009 |
Token | hard |
Token ID | 1327 |
Feature activation | +3.14e-03 |
Pos logit contributions | |
baby | +0.017 |
generation | +0.016 |
tered | +0.015 |
decides | +0.015 |
infant | +0.015 |
Neg logit contributions | |
aj | -0.030 |
ittens | -0.025 |
omed | -0.024 |
igs | -0.024 |
inc | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
baby | +0.003 |
tered | +0.003 |
generation | +0.003 |
decides | +0.003 |
infant | +0.003 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.005 |
omed | -0.005 |
inc | -0.005 |
atmeal | -0.005 |
Token | clean |
Token ID | 3424 |
Feature activation | -6.44e-03 |
Pos logit contributions | |
tered | +0.009 |
baby | +0.009 |
generation | +0.008 |
decides | +0.008 |
Welcome | +0.008 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.012 |
igs | -0.012 |
fing | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e-03 |
Pos logit contributions | |
aj | +0.015 |
ittens | +0.012 |
omed | +0.012 |
atmeal | +0.011 |
inc | +0.011 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.006 |
decides | -0.005 |
infant | -0.005 |
Token | theater |
Token ID | 13766 |
Feature activation | -8.61e-03 |
Pos logit contributions | |
aj | +0.004 |
ittens | +0.003 |
omed | +0.003 |
atmeal | +0.003 |
inc | +0.003 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.003 |
infant | -0.003 |
Token | up |
Token ID | 510 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
aj | +0.017 |
ittens | +0.014 |
omed | +0.013 |
inc | +0.013 |
atmeal | +0.013 |
Neg logit contributions | |
baby | -0.011 |
tered | -0.011 |
generation | -0.010 |
decides | -0.009 |
infant | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-03 |
Pos logit contributions | |
aj | +0.039 |
ittens | +0.033 |
omed | +0.030 |
atmeal | +0.030 |
igs | +0.029 |
Neg logit contributions | |
tered | -0.022 |
baby | -0.021 |
generation | -0.020 |
infant | -0.017 |
decides | -0.017 |
Token | He |
Token ID | 679 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.002 |
ittens | -0.002 |
omed | -0.002 |
inc | -0.002 |
atmeal | -0.002 |
Token | put |
Token ID | 1234 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
aj | +0.023 |
ittens | +0.019 |
omed | +0.018 |
atmeal | +0.018 |
igs | +0.017 |
Neg logit contributions | |
baby | -0.011 |
tered | -0.011 |
generation | -0.010 |
decides | -0.009 |
infant | -0.009 |
Token | everything |
Token ID | 2279 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
aj | +0.066 |
ittens | +0.056 |
inc | +0.052 |
omed | +0.052 |
atmeal | +0.051 |
Neg logit contributions | |
baby | -0.024 |
tered | -0.023 |
generation | -0.018 |
infant | -0.017 |
ear | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -4.57e-03 |
Pos logit contributions | |
tered | +0.011 |
baby | +0.010 |
generation | +0.010 |
decides | +0.009 |
infant | +0.009 |
Neg logit contributions | |
aj | -0.020 |
ittens | -0.016 |
omed | -0.016 |
inc | -0.015 |
fing | -0.015 |
Token | cry |
Token ID | 3960 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
aj | +0.010 |
ittens | +0.008 |
omed | +0.008 |
inc | +0.007 |
atmeal | +0.007 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.005 |
decides | -0.004 |
infant | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
baby | +0.015 |
generation | +0.015 |
tered | +0.015 |
decides | +0.014 |
Welcome | +0.014 |
Neg logit contributions | |
aj | -0.021 |
ittens | -0.017 |
omed | -0.016 |
inc | -0.015 |
atmeal | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
aj | +0.005 |
ittens | +0.004 |
omed | +0.003 |
atmeal | +0.003 |
inc | +0.003 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.002 |
infant | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -5.95e-03 |
Pos logit contributions | |
baby | +0.002 |
tered | +0.002 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.003 |
ittens | -0.002 |
omed | -0.002 |
inc | -0.002 |
atmeal | -0.002 |
Token | Her |
Token ID | 9360 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
aj | +0.012 |
ittens | +0.009 |
omed | +0.009 |
atmeal | +0.009 |
igs | +0.008 |
Neg logit contributions | |
baby | -0.008 |
tered | -0.008 |
generation | -0.007 |
decides | -0.007 |
infant | -0.007 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
aj | +0.016 |
ittens | +0.013 |
omed | +0.013 |
atmeal | +0.013 |
igs | +0.013 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.009 |
generation | -0.008 |
infant | -0.008 |
decides | -0.008 |
Token | quickly |
Token ID | 2952 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
baby | +0.003 |
tered | +0.003 |
generation | +0.003 |
decides | +0.003 |
infant | +0.003 |
Neg logit contributions | |
aj | -0.004 |
ittens | -0.003 |
omed | -0.003 |
inc | -0.003 |
atmeal | -0.003 |
Token | opened |
Token ID | 4721 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
aj | +0.009 |
ittens | +0.007 |
omed | +0.007 |
atmeal | +0.007 |
inc | +0.006 |
Neg logit contributions | |
baby | -0.005 |
tered | -0.005 |
generation | -0.004 |
decides | -0.004 |
infant | -0.004 |
Token | up |
Token ID | 510 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
aj | +0.029 |
ittens | +0.025 |
atmeal | +0.024 |
omed | +0.023 |
uddle | +0.023 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.011 |
generation | -0.010 |
infant | -0.010 |
decides | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
aj | +0.033 |
ittens | +0.027 |
atmeal | +0.026 |
omed | +0.026 |
fing | +0.025 |
Neg logit contributions | |
baby | -0.013 |
tered | -0.013 |
generation | -0.011 |
infant | -0.011 |
decides | -0.010 |
Token | peaceful |
Token ID | 12309 |
Feature activation | +6.73e-03 |
Pos logit contributions | |
aj | +0.018 |
ittens | +0.015 |
omed | +0.014 |
inc | +0.013 |
atmeal | +0.013 |
Neg logit contributions | |
baby | -0.012 |
tered | -0.012 |
generation | -0.011 |
Welcome | -0.011 |
infant | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.010 |
generation | +0.010 |
decides | +0.009 |
infant | +0.009 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.009 |
omed | -0.009 |
atmeal | -0.008 |
inc | -0.008 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
aj | +0.013 |
ittens | +0.010 |
omed | +0.010 |
atmeal | +0.009 |
inc | +0.009 |
Neg logit contributions | |
baby | -0.007 |
tered | -0.007 |
generation | -0.007 |
Welcome | -0.006 |
decides | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -9.92e-04 |
Pos logit contributions | |
tered | +0.020 |
generation | +0.020 |
baby | +0.020 |
Whoever | +0.018 |
infant | +0.017 |
Neg logit contributions | |
aj | -0.037 |
omed | -0.029 |
ittens | -0.029 |
fing | -0.028 |
inc | -0.028 |
Token | very |
Token ID | 845 |
Feature activation | +7.77e-03 |
Pos logit contributions | |
aj | +0.002 |
ittens | +0.002 |
omed | +0.002 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | proud |
Token ID | 6613 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
tered | +0.011 |
baby | +0.011 |
generation | +0.011 |
decides | +0.010 |
infant | +0.010 |
Neg logit contributions | |
aj | -0.014 |
ittens | -0.011 |
omed | -0.010 |
inc | -0.010 |
fing | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
aj | +0.025 |
ittens | +0.021 |
omed | +0.020 |
atmeal | +0.020 |
igs | +0.019 |
Neg logit contributions | |
baby | -0.011 |
tered | -0.010 |
generation | -0.010 |
Welcome | -0.009 |
decides | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -5.05e-03 |
Pos logit contributions | |
baby | +0.011 |
tered | +0.011 |
generation | +0.010 |
decides | +0.010 |
infant | +0.010 |
Neg logit contributions | |
aj | -0.017 |
ittens | -0.013 |
omed | -0.013 |
fing | -0.012 |
igs | -0.012 |
Token | little |
Token ID | 1310 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
aj | +0.011 |
ittens | +0.009 |
omed | +0.008 |
inc | +0.008 |
atmeal | +0.008 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.006 |
infant | -0.005 |
decides | -0.005 |
Token | boy |
Token ID | 2933 |
Feature activation | +6.58e-03 |
Pos logit contributions | |
tered | +0.002 |
baby | +0.002 |
generation | +0.002 |
decides | +0.002 |
infant | +0.002 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.006 |
inc | -0.006 |
atmeal | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
baby | +0.009 |
tered | +0.009 |
generation | +0.008 |
decides | +0.008 |
infant | +0.008 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.010 |
omed | -0.009 |
atmeal | -0.009 |
inc | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -6.29e-03 |
Pos logit contributions | |
generation | +0.044 |
tered | +0.044 |
baby | +0.043 |
Whoever | +0.042 |
Welcome | +0.041 |
Neg logit contributions | |
aj | -0.039 |
ittens | -0.029 |
omed | -0.026 |
igs | -0.024 |
uddle | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | -4.80e-03 |
Pos logit contributions | |
aj | +0.015 |
ittens | +0.012 |
omed | +0.012 |
atmeal | +0.012 |
fing | +0.012 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.005 |
infant | -0.005 |
decides | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
aj | +0.010 |
ittens | +0.008 |
omed | +0.008 |
atmeal | +0.007 |
igs | +0.007 |
Neg logit contributions | |
baby | -0.006 |
tered | -0.006 |
generation | -0.005 |
decides | -0.005 |
infant | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
tered | +0.003 |
baby | +0.003 |
generation | +0.003 |
decides | +0.003 |
Welcome | +0.003 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.006 |
omed | -0.006 |
inc | -0.005 |
atmeal | -0.005 |
Token | wear |
Token ID | 5806 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
aj | +0.008 |
ittens | +0.007 |
omed | +0.006 |
inc | +0.006 |
atmeal | +0.006 |
Neg logit contributions | |
baby | -0.004 |
tered | -0.004 |
generation | -0.004 |
decides | -0.003 |
infant | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
aj | +0.107 |
atmeal | +0.093 |
ittens | +0.092 |
omed | +0.092 |
ode | +0.090 |
Neg logit contributions | |
baby | -0.025 |
tered | -0.021 |
ear | -0.019 |
generation | -0.014 |
infant | -0.013 |
Token | dress |
Token ID | 6576 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
aj | +0.099 |
omed | +0.093 |
Johnny | +0.091 |
ounds | +0.091 |
apes | +0.089 |
Neg logit contributions | |
baby | -0.071 |
ear | -0.059 |
vows | -0.051 |
gift | -0.051 |
infant | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-03 |
Pos logit contributions | |
aj | +0.060 |
ittens | +0.050 |
omed | +0.049 |
fing | +0.048 |
igs | +0.048 |
Neg logit contributions | |
tered | -0.030 |
baby | -0.029 |
generation | -0.025 |
infant | -0.023 |
decides | -0.022 |
Token | She |
Token ID | 1375 |
Feature activation | +8.81e-03 |
Pos logit contributions | |
aj | +0.003 |
ittens | +0.002 |
omed | +0.002 |
atmeal | +0.002 |
inc | +0.002 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
baby | +0.011 |
generation | +0.011 |
tered | +0.011 |
Welcome | +0.010 |
infant | +0.010 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.014 |
omed | -0.013 |
inc | -0.013 |
atmeal | -0.013 |
Token | at |
Token ID | 379 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
aj | +0.036 |
ittens | +0.031 |
atmeal | +0.030 |
Johnny | +0.028 |
omed | +0.028 |
Neg logit contributions | |
baby | -0.018 |
tered | -0.017 |
decides | -0.015 |
infant | -0.015 |
generation | -0.014 |
Token | saw |
Token ID | 2497 |
Feature activation | +9.65e-03 |
Pos logit contributions | |
aj | +0.029 |
ittens | +0.024 |
omed | +0.023 |
atmeal | +0.022 |
igs | +0.021 |
Neg logit contributions | |
baby | -0.019 |
tered | -0.018 |
generation | -0.017 |
decides | -0.016 |
infant | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
tered | +0.013 |
baby | +0.013 |
generation | +0.012 |
decides | +0.012 |
Welcome | +0.012 |
Neg logit contributions | |
aj | -0.018 |
ittens | -0.014 |
omed | -0.013 |
inc | -0.013 |
Johnny | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
aj | +0.022 |
ittens | +0.018 |
omed | +0.018 |
inc | +0.017 |
atmeal | +0.017 |
Neg logit contributions | |
baby | -0.011 |
tered | -0.010 |
generation | -0.010 |
infant | -0.009 |
decides | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
aj | +0.047 |
ittens | +0.041 |
igs | +0.038 |
omed | +0.038 |
fing | +0.037 |
Neg logit contributions | |
baby | -0.011 |
tered | -0.011 |
decides | -0.009 |
generation | -0.009 |
Welcome | -0.007 |
Token | 8 |
Token ID | 807 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
aj | +0.029 |
ittens | +0.024 |
omed | +0.022 |
uddle | +0.022 |
atmeal | +0.022 |
Neg logit contributions | |
baby | -0.018 |
tered | -0.017 |
generation | -0.016 |
infant | -0.015 |
decides | -0.014 |
Token | o |
Token ID | 267 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
aj | +0.017 |
ittens | +0.013 |
omed | +0.012 |
inc | +0.011 |
fing | +0.011 |
Neg logit contributions | |
baby | -0.019 |
tered | -0.019 |
generation | -0.018 |
infant | -0.017 |
decides | -0.017 |
Token | â |
Token ID | 22940 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
aj | +0.085 |
underwear | +0.065 |
Linda | +0.063 |
vest | +0.062 |
endant | +0.059 |
Neg logit contributions | |
tered | -0.089 |
lder | -0.088 |
generation | -0.085 |
five | -0.082 |
Welcome | -0.081 |
Token | € |
Token ID | 26391 |
Feature activation | -6.42e-02 |
Pos logit contributions | |
aj | +0.026 |
ittens | +0.020 |
omed | +0.019 |
igs | +0.019 |
uddle | +0.019 |
Neg logit contributions | |
tered | -0.018 |
generation | -0.017 |
baby | -0.017 |
Welcome | -0.016 |
infant | -0.015 |
Token | ™ |
Token ID | 8151 |
Feature activation | +5.65e-03 |
Pos logit contributions | |
aj | +0.102 |
fing | +0.092 |
ey | +0.087 |
igs | +0.084 |
omed | +0.082 |
Neg logit contributions | |
tered | -0.083 |
generation | -0.083 |
Welcome | -0.082 |
baby | -0.080 |
lder | -0.079 |
Token | clock |
Token ID | 15750 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
baby | +0.008 |
tered | +0.008 |
generation | +0.007 |
decides | +0.007 |
infant | +0.007 |
Neg logit contributions | |
aj | -0.010 |
ittens | -0.008 |
omed | -0.008 |
inc | -0.007 |
atmeal | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
baby | +0.006 |
tered | +0.005 |
generation | +0.005 |
decides | +0.005 |
infant | +0.005 |
Neg logit contributions | |
aj | -0.007 |
ittens | -0.005 |
omed | -0.005 |
inc | -0.005 |
atmeal | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
aj | +0.111 |
ittens | +0.094 |
fing | +0.092 |
omed | +0.088 |
atmeal | +0.087 |
Neg logit contributions | |
tered | -0.038 |
baby | -0.035 |
from | -0.028 |
generation | -0.026 |
other | -0.026 |
Token | color |
Token ID | 3124 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
tered | +0.036 |
baby | +0.035 |
generation | +0.033 |
ancy | +0.033 |
Whoever | +0.031 |
Neg logit contributions | |
aj | -0.035 |
ittens | -0.027 |
igs | -0.025 |
atmeal | -0.025 |
vest | -0.025 |
Token | with |
Token ID | 351 |
Feature activation | -3.76e-03 |
Pos logit contributions | |
aj | +0.061 |
ittens | +0.049 |
omed | +0.048 |
fing | +0.048 |
inc | +0.046 |
Neg logit contributions | |
baby | -0.029 |
tered | -0.027 |
generation | -0.022 |
infant | -0.022 |
decides | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
aj | +0.008 |
ittens | +0.007 |
omed | +0.007 |
atmeal | +0.006 |
inc | +0.006 |
Neg logit contributions | |
baby | -0.004 |
tered | -0.004 |
generation | -0.004 |
infant | -0.003 |
decides | -0.003 |
Token | cr |
Token ID | 1067 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
aj | +0.091 |
omed | +0.081 |
fing | +0.078 |
ivering | +0.078 |
atmeal | +0.077 |
Neg logit contributions | |
baby | -0.076 |
ear | -0.064 |
infant | -0.062 |
other | -0.059 |
person | -0.057 |
Token | ay |
Token ID | 323 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
aj | +0.093 |
fing | +0.078 |
atmeal | +0.073 |
ittens | +0.073 |
omed | +0.072 |
Neg logit contributions | |
tered | -0.048 |
baby | -0.043 |
generation | -0.040 |
ancy | -0.038 |
vows | -0.037 |
Token | ons |
Token ID | 684 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
aj | +0.078 |
unatt | +0.056 |
fing | +0.055 |
ivering | +0.053 |
uddle | +0.053 |
Neg logit contributions | |
baby | -0.099 |
tered | -0.098 |
ped | -0.091 |
ends | -0.091 |
wants | -0.091 |
Token | . |
Token ID | 13 |
Feature activation | -8.01e-03 |
Pos logit contributions | |
aj | +0.078 |
ittens | +0.066 |
omed | +0.064 |
Johnny | +0.063 |
fing | +0.062 |
Neg logit contributions | |
baby | -0.032 |
tered | -0.031 |
generation | -0.025 |
infant | -0.025 |
y | -0.023 |
Token | One |
Token ID | 1881 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
aj | +0.018 |
ittens | +0.015 |
omed | +0.014 |
inc | +0.014 |
atmeal | +0.014 |
Neg logit contributions | |
baby | -0.008 |
tered | -0.008 |
generation | -0.008 |
Welcome | -0.007 |
infant | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -5.81e-04 |
Pos logit contributions | |
aj | +0.004 |
ittens | +0.004 |
omed | +0.004 |
inc | +0.003 |
atmeal | +0.003 |
Neg logit contributions | |
baby | -0.002 |
tered | -0.002 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
aj | +0.001 |
ittens | +0.001 |
omed | +0.001 |
atmeal | +0.001 |
inc | +0.001 |
Neg logit contributions | |
baby | -0.001 |
tered | -0.001 |
generation | -0.001 |
decides | -0.001 |
infant | -0.001 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
baby | +0.004 |
tered | +0.004 |
generation | +0.004 |
decides | +0.003 |
infant | +0.003 |
Neg logit contributions | |
aj | -0.008 |
ittens | -0.006 |
omed | -0.006 |
atmeal | -0.006 |
inc | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
generation | +0.014 |
baby | +0.014 |
tered | +0.014 |
decides | +0.013 |
Whoever | +0.013 |
Neg logit contributions | |
aj | -0.023 |
ittens | -0.019 |
omed | -0.018 |
inc | -0.017 |
Johnny | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +2.14e-04 |
Pos logit contributions | |
tered | +0.010 |
baby | +0.010 |
generation | +0.010 |
decides | +0.009 |
infant | +0.009 |
Neg logit contributions | |
aj | -0.012 |
ittens | -0.009 |
omed | -0.008 |
atmeal | -0.008 |
inc | -0.008 |
Token | � |
Token ID | 6184 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
baby | +0.000 |
tered | +0.000 |
generation | +0.000 |
decides | +0.000 |
infant | +0.000 |
Neg logit contributions | |
aj | -0.000 |
ittens | -0.000 |
omed | -0.000 |
atmeal | -0.000 |
inc | -0.000 |
Token | � |
Token ID | 95 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
aj | +0.054 |
ittens | +0.041 |
omed | +0.039 |
inations | +0.038 |
light | +0.038 |
Neg logit contributions | |
tered | -0.047 |
baby | -0.044 |
generation | -0.042 |
Whoever | -0.042 |
Welcome | -0.042 |
Token | € |
Token ID | 26391 |
Feature activation | -6.74e-02 |
Pos logit contributions | |
aj | +0.062 |
ittens | +0.053 |
igs | +0.049 |
omed | +0.048 |
inations | +0.046 |
Neg logit contributions | |
tered | -0.038 |
generation | -0.035 |
Welcome | -0.034 |
Whoever | -0.034 |
Give | -0.033 |
Token | � |
Token ID | 129 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
aj | +0.114 |
igs | +0.100 |
ode | +0.096 |
inations | +0.095 |
fing | +0.094 |
Neg logit contributions | |
Welcome | -0.078 |
wants | -0.077 |
Give | -0.076 |
baby | -0.075 |
lder | -0.074 |
Token | � |
Token ID | 241 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
aj | +0.026 |
ittens | +0.021 |
omed | +0.020 |
atmeal | +0.020 |
igs | +0.019 |
Neg logit contributions | |
tered | -0.016 |
baby | -0.015 |
generation | -0.015 |
decides | -0.014 |
Welcome | -0.013 |
Token | Thank |
Token ID | 10449 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
baby | +0.025 |
tered | +0.025 |
generation | +0.024 |
infant | +0.023 |
decides | +0.023 |
Neg logit contributions | |
aj | -0.035 |
ittens | -0.029 |
omed | -0.026 |
inc | -0.026 |
fing | -0.026 |
Token | you |
Token ID | 345 |
Feature activation | -2.38e-03 |
Pos logit contributions | |
aj | +0.012 |
ittens | +0.009 |
omed | +0.009 |
inc | +0.009 |
atmeal | +0.009 |
Neg logit contributions | |
baby | -0.010 |
tered | -0.010 |
generation | -0.009 |
Welcome | -0.009 |
decides | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
aj | +0.005 |
ittens | +0.004 |
omed | +0.004 |
atmeal | +0.003 |
inc | +0.003 |
Neg logit contributions | |
baby | -0.003 |
tered | -0.003 |
generation | -0.003 |
decides | -0.003 |
infant | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +7.38e-04 |
Pos logit contributions | |
aj | +0.052 |
ittens | +0.041 |
omed | +0.040 |
fing | +0.040 |
atmeal | +0.040 |
Neg logit contributions | |
baby | -0.035 |
tered | -0.032 |
infant | -0.028 |
Welcome | -0.027 |
decides | -0.026 |
Token | Lisa |
Token ID | 15378 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
baby | +0.001 |
tered | +0.001 |
generation | +0.001 |
decides | +0.001 |
infant | +0.001 |
Neg logit contributions | |
aj | -0.002 |
ittens | -0.001 |
omed | -0.001 |
inc | -0.001 |
atmeal | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
aj | +0.033 |
ittens | +0.027 |
omed | +0.026 |
atmeal | +0.025 |
fing | +0.025 |
Neg logit contributions | |
baby | -0.021 |
tered | -0.020 |
generation | -0.019 |
decides | -0.019 |
Welcome | -0.018 |
Token | I |
Token ID | 314 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
tered | +0.008 |
baby | +0.008 |
generation | +0.008 |
decides | +0.007 |
infant | +0.007 |
Neg logit contributions | |
aj | -0.014 |
ittens | -0.011 |
omed | -0.011 |
inc | -0.010 |
atmeal | -0.010 |
Token | â |
Token ID | 22940 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
aj | +0.073 |
ittens | +0.064 |
igs | +0.059 |
atmeal | +0.058 |
omed | +0.058 |
Neg logit contributions | |
baby | -0.025 |
decides | -0.023 |
wants | -0.022 |
tered | -0.022 |
generation | -0.021 |
Token | € |
Token ID | 26391 |
Feature activation | -5.71e-02 |
Pos logit contributions | |
aj | +0.046 |
ittens | +0.036 |
igs | +0.034 |
uddle | +0.033 |
omed | +0.032 |
Neg logit contributions | |
tered | -0.032 |
generation | -0.030 |
Welcome | -0.029 |
baby | -0.028 |
five | -0.028 |
Token | ™ |
Token ID | 8151 |
Feature activation | +6.11e-03 |
Pos logit contributions | |
aj | +0.083 |
igs | +0.069 |
fing | +0.068 |
atmeal | +0.065 |
ode | +0.064 |
Neg logit contributions | |
Welcome | -0.083 |
baby | -0.081 |
wants | -0.078 |
Give | -0.078 |
tered | -0.076 |
Token | m |
Token ID | 76 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
baby | +0.010 |
tered | +0.010 |
generation | +0.010 |
decides | +0.009 |
infant | +0.009 |
Neg logit contributions | |
aj | -0.010 |
ittens | -0.008 |
omed | -0.007 |
inc | -0.007 |
atmeal | -0.007 |
Token | swinging |
Token ID | 25635 |
Feature activation | -5.99e-03 |
Pos logit contributions | |
aj | +0.042 |
ittens | +0.033 |
atmeal | +0.032 |
omed | +0.032 |
fing | +0.032 |
Neg logit contributions | |
baby | -0.036 |
tered | -0.033 |
infant | -0.030 |
wants | -0.029 |
Welcome | -0.029 |
Token | ! |
Token ID | 0 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
aj | +0.011 |
ittens | +0.009 |
omed | +0.009 |
atmeal | +0.008 |
igs | +0.008 |
Neg logit contributions | |
baby | -0.008 |
tered | -0.008 |
generation | -0.007 |
decides | -0.007 |
infant | -0.007 |
Token | â |
Token ID | 22940 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
tered | +0.008 |
baby | +0.008 |
generation | +0.007 |
decides | +0.006 |
infant | +0.006 |
Neg logit contributions | |
aj | -0.016 |
ittens | -0.013 |
omed | -0.012 |
inc | -0.012 |
atmeal | -0.012 |