TOP ACTIVATIONS
MAX = 0.190

We have different likes and disl ikes . We can be
Tim my learned that sometimes accidents happen , and we can
too . He knew that accidents happen sometimes .
said it was okay , accidents happen . They cleaned up
her it was okay and accidents happen . They cleaned up
this time she understood that accidents can happen and sometimes things
. Tim my learned that accidents can happen and it 's
is now ? That 's what we call pol ishing ."
Mom my ! Look what I found on the porch
. Tim learned that sometimes accidents happen , but it 's
She also learned that sometimes accidents happen and it 's okay
with the chores can prevent accidents and save things we love
" It 's OK , accidents happen . We all make
on , Lily learned that accidents happen and that it 's
the truth . She says accidents happen and they can fix
But he also learned that accidents can happen and it 's
of our things , but accidents happen . She also said
him it was okay , accidents happen . They cleaned up
" It 's okay , accidents happen . Let 's go
of the story is that accidents happen , but it 's

MIN ACTIVATIONS
MIN = -0.204

new home with the fan ci est king in the land
the brav est and boun ci est bunny in the whole
to put on her fan ci est sunglasses .
she always wore her fan ci est dress to the museum
will buy you the fan ci est dress in the store
dressed up in her fan ci est clothes and asked her
the daughter found the fan ci est dress she had ever
and put it in a pouch around her shoulder for later
the apple in his little pouch and carried it home .
" You can have this pouch full of coins !"
. It was a small pouch with a shiny penny in
crab proudly put in his pouch . The
with a baby in her pouch . The baby k ang
the k ang aroo 's pouch was a surprise - two
in his mom my 's pouch . He loved to hop
out of its mother 's pouch and cried .
clown s juggling and ac rob ats doing flips . But
was very comfortable in his pouch , where he slept and
with a baby in her pouch . They wanted to pet
her doll next to the pouch and reached out her hand

INTERVAL 0.091 - 0.190
CONTAINS 2.988%

his wings after playing . <|endoftext|> Once upon a time ,
to Lily that it 's okay if things get broken sometimes
but he likes to chase things . He sees the bright
. He and his mom my spent a few hours playing
do not complain anymore . <|endoftext|> L ily and Ben were

INTERVAL -0.007 - 0.091
CONTAINS 56.615%

her . Lily was happy and fell asleep with her duck
much as she wanted , as long as she did not
realized that Rocky was right . She had been foolish and
't know what to do . Suddenly ,
together , looking for beautiful colors , and having lots of

INTERVAL -0.106 - -0.007
CONTAINS 40.070%

. Mama smiles and says they can pick it . She
. He was glad he made such an impressive bird c
at first , but then she smiled and said , "
light in a window . She smelled something good . She
man with the dangerous pistol had to be avoided , but

INTERVAL -0.204 - -0.106
CONTAINS 0.327%

day , a little boy named Tim was very eager to
time there were two birds named Steve and Joe . Steve
there was a little crab named Sam . Sam loved to
He waved the jar around and made them laugh
Lily said , showing her basket . They kept
Token We
Token ID775
Feature activation-5.03e-02

Pos logit contributions
ires+0.030
olving+0.029
 footsteps+0.028
 prayers+0.028
 accomplishments+0.028
Neg logit contributions
c-0.031
bar-0.030
 named-0.028
 bank-0.027
rob-0.026
Token have
Token ID423
Feature activation-2.40e-02

Pos logit contributions
c+0.093
bar+0.091
 named+0.085
rob+0.082
 bank+0.079
Neg logit contributions
ires-0.067
olving-0.065
 accomplishments-0.062
inner-0.061
 prayers-0.061
Token different
Token ID1180
Feature activation-2.95e-03

Pos logit contributions
c+0.041
bar+0.039
 named+0.036
rob+0.036
ah+0.035
Neg logit contributions
ires-0.036
olving-0.036
 footsteps-0.035
 prayers-0.035
 accomplishments-0.034
Token likes
Token ID7832
Feature activation+5.83e-02

Pos logit contributions
c+0.006
bar+0.006
 named+0.006
 bank+0.005
rob+0.005
Neg logit contributions
ires-0.004
olving-0.003
iders-0.003
 accomplishments-0.003
inner-0.003
Token and
Token ID290
Feature activation+1.19e-02

Pos logit contributions
ires+0.092
olving+0.091
iders+0.088
 accomplishments+0.088
 footsteps+0.087
Neg logit contributions
c-0.095
bar-0.089
 named-0.089
 bank-0.081
ah-0.077
Token disl
Token ID19621
Feature activation+1.89e-01

Pos logit contributions
ires+0.017
olving+0.016
iders+0.016
inner+0.015
 accomplishments+0.015
Neg logit contributions
c-0.022
bar-0.021
 named-0.021
 bank-0.019
 pouch-0.018
Tokenikes
Token ID7938
Feature activation+9.20e-03

Pos logit contributions
 footsteps+0.237
 prayers+0.226
olving+0.219
 accomplishments+0.212
 accidents+0.206
Neg logit contributions
rob-0.339
c-0.337
bar-0.331
ah-0.298
ci-0.292
Token.
Token ID13
Feature activation+2.13e-02

Pos logit contributions
ires+0.014
olving+0.014
 accomplishments+0.014
iders+0.014
 footsteps+0.014
Neg logit contributions
c-0.015
bar-0.015
 named-0.014
 bank-0.013
ah-0.013
Token We
Token ID775
Feature activation-4.89e-02

Pos logit contributions
ires+0.032
olving+0.030
 footsteps+0.030
 prayers+0.030
iders+0.029
Neg logit contributions
c-0.037
bar-0.035
 named-0.033
 bank-0.032
ah-0.032
Token can
Token ID460
Feature activation+5.60e-02

Pos logit contributions
c+0.089
bar+0.086
 named+0.082
rob+0.077
 bank+0.076
Neg logit contributions
ires-0.067
olving-0.065
 accomplishments-0.063
 footsteps-0.062
 prayers-0.062
Token be
Token ID307
Feature activation+1.09e-02

Pos logit contributions
ires+0.084
olving+0.082
 accomplishments+0.080
iders+0.079
 footsteps+0.079
Neg logit contributions
c-0.095
bar-0.093
 named-0.090
 bank-0.084
ah-0.080
Token Tim
Token ID5045
Feature activation+3.41e-02

Pos logit contributions
ires+0.019
 footsteps+0.018
olving+0.018
 prayers+0.018
iders+0.017
Neg logit contributions
c-0.024
bar-0.023
 bank-0.021
rob-0.021
ah-0.021
Tokenmy
Token ID1820
Feature activation+1.09e-01

Pos logit contributions
olving+0.054
ires+0.053
ps+0.052
 footsteps+0.051
 accidents+0.051
Neg logit contributions
bar-0.050
c-0.048
rob-0.043
 named-0.042
 pouch-0.042
Token learned
Token ID4499
Feature activation+3.76e-03

Pos logit contributions
 prayers+0.149
 words+0.142
ps+0.142
olving+0.142
 footsteps+0.142
Neg logit contributions
bar-0.187
c-0.178
rob-0.166
 pouch-0.151
ah-0.149
Token that
Token ID326
Feature activation-2.49e-02

Pos logit contributions
ires+0.006
olving+0.006
 footsteps+0.006
 accomplishments+0.006
 prayers+0.006
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
 bank-0.005
ah-0.005
Token sometimes
Token ID3360
Feature activation+2.40e-02

Pos logit contributions
c+0.036
bar+0.035
 named+0.033
 bank+0.030
rob+0.029
Neg logit contributions
ires-0.044
olving-0.043
 accomplishments-0.042
iders-0.042
 footsteps-0.041
Token accidents
Token ID17390
Feature activation+1.86e-01

Pos logit contributions
ires+0.039
olving+0.038
 accomplishments+0.037
 footsteps+0.037
iders+0.036
Neg logit contributions
c-0.039
bar-0.037
 named-0.036
 bank-0.033
rob-0.032
Token happen
Token ID1645
Feature activation+1.00e-01

Pos logit contributions
 footsteps+0.216
ires+0.202
iders+0.201
 prayers+0.194
 accomplishments+0.192
Neg logit contributions
c-0.352
bar-0.346
 named-0.343
 bank-0.326
 brought-0.307
Token,
Token ID11
Feature activation-1.92e-03

Pos logit contributions
 footsteps+0.199
inner+0.196
iders+0.190
 prayers+0.190
ires+0.187
Neg logit contributions
c-0.118
 named-0.113
bar-0.106
 bank-0.091
 one-0.087
Token and
Token ID290
Feature activation+9.68e-03

Pos logit contributions
c+0.003
bar+0.003
 named+0.003
 bank+0.002
rob+0.002
Neg logit contributions
ires-0.003
olving-0.003
 accomplishments-0.003
 footsteps-0.003
 prayers-0.003
Token we
Token ID356
Feature activation-5.52e-02

Pos logit contributions
ires+0.016
olving+0.016
 accidents+0.015
 prayers+0.015
 accomplishments+0.015
Neg logit contributions
c-0.015
bar-0.014
 named-0.014
rob-0.013
ah-0.013
Token can
Token ID460
Feature activation+4.85e-02

Pos logit contributions
c+0.109
bar+0.105
 named+0.100
rob+0.099
ah+0.094
Neg logit contributions
ires-0.067
olving-0.067
 prayers-0.063
 accomplishments-0.063
 progress-0.061
Token too
Token ID1165
Feature activation+3.27e-03

Pos logit contributions
c+0.071
bar+0.068
 named+0.065
 bank+0.060
rob+0.059
Neg logit contributions
ires-0.068
olving-0.066
 accomplishments-0.064
 footsteps-0.064
 prayers-0.064
Token.
Token ID13
Feature activation+2.25e-02

Pos logit contributions
ires+0.005
olving+0.005
 footsteps+0.005
iders+0.005
 accomplishments+0.005
Neg logit contributions
c-0.006
bar-0.005
 named-0.005
 bank-0.005
ah-0.005
Token He
Token ID679
Feature activation+2.12e-02

Pos logit contributions
ires+0.035
olving+0.032
 footsteps+0.032
 prayers+0.032
iders+0.031
Neg logit contributions
c-0.037
bar-0.036
 bank-0.033
 named-0.033
rob-0.033
Token knew
Token ID2993
Feature activation+4.32e-02

Pos logit contributions
 prayers+0.030
ires+0.030
 clearly+0.029
 words+0.029
olving+0.029
Neg logit contributions
bar-0.034
c-0.033
rob-0.028
bank-0.028
 pouch-0.028
Token that
Token ID326
Feature activation-2.43e-02

Pos logit contributions
ires+0.069
olving+0.067
 prayers+0.065
 footsteps+0.065
 accomplishments+0.064
Neg logit contributions
c-0.070
bar-0.066
 named-0.062
 bank-0.060
rob-0.059
Token accidents
Token ID17390
Feature activation+1.86e-01

Pos logit contributions
c+0.038
bar+0.036
 named+0.035
 bank+0.032
rob+0.031
Neg logit contributions
ires-0.041
olving-0.039
 accomplishments-0.038
 footsteps-0.038
 prayers-0.038
Token happen
Token ID1645
Feature activation+9.82e-02

Pos logit contributions
ires+0.210
 footsteps+0.203
iders+0.190
 accomplishments+0.189
olving+0.183
Neg logit contributions
c-0.374
 named-0.363
bar-0.354
 bank-0.339
 brought-0.331
Token sometimes
Token ID3360
Feature activation+2.21e-02

Pos logit contributions
 footsteps+0.180
ires+0.176
inner+0.174
olving+0.173
 prayers+0.172
Neg logit contributions
c-0.135
 named-0.127
bar-0.120
 bank-0.105
 one-0.100
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
ires+0.038
iders+0.037
inner+0.036
olving+0.036
 accomplishments+0.035
Neg logit contributions
c-0.034
 named-0.032
bar-0.031
 bank-0.029
bank-0.026
Token
Token ID198
Feature activation+3.71e-03

Pos logit contributions
ires+0.024
olving+0.023
 prayers+0.023
 footsteps+0.023
 accomplishments+0.022
Neg logit contributions
c-0.026
bar-0.025
 named-0.024
 bank-0.023
rob-0.023
Token
Token ID198
Feature activation+2.33e-03

Pos logit contributions
ires+0.005
olving+0.005
 accomplishments+0.005
 footsteps+0.005
 prayers+0.005
Neg logit contributions
c-0.007
bar-0.006
 named-0.006
 bank-0.006
rob-0.006
Token said
Token ID531
Feature activation-6.17e-02

Pos logit contributions
 accidents+0.026
 prayers+0.026
 footsteps+0.026
ires+0.026
olving+0.025
Neg logit contributions
c-0.019
bar-0.019
ah-0.017
rob-0.016
 bank-0.015
Token it
Token ID340
Feature activation+1.57e-02

Pos logit contributions
 named+0.074
c+0.067
bar+0.065
 +0.050
ah+0.050
Neg logit contributions
ires-0.132
iders-0.127
inner-0.124
olving-0.122
 accomplishments-0.122
Token was
Token ID373
Feature activation-8.49e-03

Pos logit contributions
ires+0.036
 accomplishments+0.033
olving+0.032
 progress+0.032
iring+0.032
Neg logit contributions
c-0.019
 named-0.016
bar-0.015
 bank-0.015
ah-0.014
Token okay
Token ID8788
Feature activation+1.01e-01

Pos logit contributions
c+0.019
 named+0.018
bar+0.018
ah+0.016
 bank+0.016
Neg logit contributions
ires-0.009
iders-0.008
olving-0.008
inner-0.008
 accomplishments-0.008
Token,
Token ID11
Feature activation-8.89e-05

Pos logit contributions
ires+0.228
inner+0.218
ieve+0.208
 accomplishments+0.208
 progress+0.207
Neg logit contributions
c-0.114
 named-0.113
 one-0.093
bar-0.089
ah-0.084
Token accidents
Token ID17390
Feature activation+1.83e-01

Pos logit contributions
c+0.000
bar+0.000
 named+0.000
 bank+0.000
ah+0.000
Neg logit contributions
ires-0.000
olving-0.000
 accomplishments-0.000
inner-0.000
iders-0.000
Token happen
Token ID1645
Feature activation+9.74e-02

Pos logit contributions
ires+0.212
 footsteps+0.188
 accomplishments+0.179
 prayers+0.175
 Deal+0.174
Neg logit contributions
c-0.365
 named-0.359
bar-0.356
 made-0.341
 brought-0.329
Token.
Token ID13
Feature activation+1.13e-02

Pos logit contributions
 footsteps+0.176
ires+0.175
inner+0.174
 prayers+0.171
 accomplishments+0.169
Neg logit contributions
c-0.132
 named-0.122
bar-0.120
 one-0.103
 bank-0.098
Token They
Token ID1119
Feature activation-3.87e-02

Pos logit contributions
ires+0.017
olving+0.017
 footsteps+0.016
 prayers+0.016
 accomplishments+0.016
Neg logit contributions
c-0.019
bar-0.018
 named-0.017
 bank-0.016
rob-0.016
Token cleaned
Token ID20750
Feature activation+1.70e-02

Pos logit contributions
c+0.061
bar+0.060
rob+0.060
bank+0.056
 pouch+0.051
Neg logit contributions
 prayers-0.058
 footsteps-0.056
 concentrate-0.055
 clearly-0.054
ps-0.053
Token up
Token ID510
Feature activation+4.34e-02

Pos logit contributions
ires+0.025
olving+0.024
 accomplishments+0.023
inner+0.023
iders+0.023
Neg logit contributions
c-0.031
 named-0.028
bar-0.028
 bank-0.026
rob-0.025
Token her
Token ID607
Feature activation+6.38e-02

Pos logit contributions
c+0.132
 named+0.124
bar+0.120
 bank+0.110
ah+0.105
Neg logit contributions
ires-0.160
olving-0.157
iders-0.153
 accomplishments-0.150
inner-0.147
Token it
Token ID340
Feature activation+1.14e-02

Pos logit contributions
ires+0.112
olving+0.106
iders+0.105
 accomplishments+0.103
 footsteps+0.103
Neg logit contributions
c-0.094
 named-0.089
bar-0.089
 bank-0.079
ah-0.076
Token was
Token ID373
Feature activation-1.41e-02

Pos logit contributions
ires+0.020
olving+0.019
 accomplishments+0.019
 footsteps+0.018
iders+0.018
Neg logit contributions
c-0.017
bar-0.016
 named-0.016
 bank-0.014
ah-0.014
Token okay
Token ID8788
Feature activation+1.01e-01

Pos logit contributions
c+0.029
bar+0.029
 named+0.027
rob+0.026
 bank+0.026
Neg logit contributions
ires-0.016
olving-0.016
 prayers-0.015
 accomplishments-0.015
 accidents-0.015
Token and
Token ID290
Feature activation+1.04e-02

Pos logit contributions
ires+0.207
inner+0.196
olving+0.191
 accomplishments+0.189
ieve+0.185
Neg logit contributions
c-0.133
 named-0.130
bar-0.109
ah-0.099
 one-0.098
Token accidents
Token ID17390
Feature activation+1.83e-01

Pos logit contributions
ires+0.016
 accidents+0.016
 prayers+0.016
olving+0.016
 footsteps+0.015
Neg logit contributions
c-0.017
bar-0.016
rob-0.015
ah-0.015
 named-0.014
Token happen
Token ID1645
Feature activation+9.61e-02

Pos logit contributions
ires+0.202
 footsteps+0.180
 accomplishments+0.172
 prayers+0.169
olving+0.165
Neg logit contributions
c-0.386
bar-0.373
 named-0.367
 bank-0.345
bank-0.335
Token.
Token ID13
Feature activation+1.24e-02

Pos logit contributions
ires+0.161
 footsteps+0.158
inner+0.155
olving+0.155
 prayers+0.154
Neg logit contributions
c-0.146
bar-0.137
 named-0.134
 bank-0.118
ah-0.112
Token They
Token ID1119
Feature activation-3.79e-02

Pos logit contributions
ires+0.018
 footsteps+0.018
 prayers+0.018
olving+0.017
 accidents+0.017
Neg logit contributions
bar-0.021
c-0.021
rob-0.019
ah-0.019
 bank-0.019
Token cleaned
Token ID20750
Feature activation+1.55e-02

Pos logit contributions
rob+0.061
c+0.061
bar+0.060
bank+0.053
 pouch+0.050
Neg logit contributions
 prayers-0.057
 footsteps-0.055
 concentrate-0.053
olving-0.051
ps-0.051
Token up
Token ID510
Feature activation+4.27e-02

Pos logit contributions
ires+0.021
olving+0.020
 accomplishments+0.019
iders+0.019
inner+0.019
Neg logit contributions
c-0.030
bar-0.028
 named-0.027
 bank-0.026
rob-0.025
Token this
Token ID428
Feature activation+8.94e-03

Pos logit contributions
c+0.055
bar+0.052
 named+0.051
 bank+0.046
ah+0.045
Neg logit contributions
ires-0.057
olving-0.056
 accomplishments-0.054
iders-0.054
inner-0.053
Token time
Token ID640
Feature activation+5.06e-02

Pos logit contributions
ires+0.014
olving+0.014
iders+0.013
 footsteps+0.013
 accomplishments+0.013
Neg logit contributions
c-0.015
bar-0.014
 named-0.014
ah-0.012
 bank-0.012
Token she
Token ID673
Feature activation-3.51e-02

Pos logit contributions
ires+0.095
iders+0.089
olving+0.089
inner+0.088
 accomplishments+0.088
Neg logit contributions
c-0.070
 named-0.065
bar-0.065
 bank-0.056
ah-0.053
Token understood
Token ID7247
Feature activation+4.19e-02

Pos logit contributions
bar+0.054
c+0.053
rob+0.047
 named+0.046
 bank+0.045
Neg logit contributions
olving-0.055
ires-0.055
 prayers-0.054
 accomplishments-0.053
 accidents-0.052
Token that
Token ID326
Feature activation-2.26e-02

Pos logit contributions
ires+0.072
inner+0.069
iders+0.068
olving+0.066
 accomplishments+0.066
Neg logit contributions
c-0.065
 named-0.064
bar-0.057
 bank-0.053
 pouch-0.049
Token accidents
Token ID17390
Feature activation+1.83e-01

Pos logit contributions
c+0.034
 named+0.032
bar+0.031
 bank+0.028
ah+0.026
Neg logit contributions
ires-0.040
inner-0.037
iders-0.037
olving-0.037
 accomplishments-0.036
Token can
Token ID460
Feature activation+5.18e-02

Pos logit contributions
ires+0.216
 footsteps+0.201
iders+0.187
 accomplishments+0.180
 Deal+0.179
Neg logit contributions
c-0.363
 named-0.344
bar-0.335
 made-0.333
 brought-0.329
Token happen
Token ID1645
Feature activation+1.04e-01

Pos logit contributions
ires+0.067
iders+0.061
olving+0.061
 accomplishments+0.061
 prayers+0.060
Neg logit contributions
c-0.101
bar-0.101
 named-0.093
 bank-0.090
ah-0.086
Token and
Token ID290
Feature activation+9.45e-03

Pos logit contributions
inner+0.190
ires+0.188
iders+0.187
 footsteps+0.187
ps+0.183
Neg logit contributions
c-0.140
 named-0.125
bar-0.120
 one-0.111
 bank-0.106
Token sometimes
Token ID3360
Feature activation+2.60e-02

Pos logit contributions
ires+0.017
olving+0.016
iders+0.016
 accomplishments+0.016
 footsteps+0.016
Neg logit contributions
c-0.014
bar-0.013
 named-0.013
 bank-0.012
ah-0.011
Token things
Token ID1243
Feature activation+1.12e-01

Pos logit contributions
ires+0.050
inner+0.048
iders+0.047
olving+0.046
iring+0.046
Neg logit contributions
c-0.035
 named-0.032
bar-0.030
 bank-0.029
 pouch-0.026
Token.
Token ID13
Feature activation+8.10e-03

Pos logit contributions
ires+0.009
olving+0.008
iders+0.008
 accomplishments+0.008
 footsteps+0.008
Neg logit contributions
c-0.010
bar-0.009
 named-0.009
 bank-0.008
ah-0.008
Token Tim
Token ID5045
Feature activation+2.76e-02

Pos logit contributions
ires+0.013
olving+0.013
 footsteps+0.012
 prayers+0.012
 accomplishments+0.012
Neg logit contributions
c-0.013
bar-0.012
 named-0.012
 bank-0.011
ah-0.011
Tokenmy
Token ID1820
Feature activation+1.03e-01

Pos logit contributions
 accidents+0.036
olving+0.035
ps+0.035
 footsteps+0.034
 words+0.033
Neg logit contributions
bar-0.047
 bank-0.043
c-0.043
rob-0.042
bank-0.041
Token learned
Token ID4499
Feature activation+3.59e-03

Pos logit contributions
 accidents+0.130
 prayers+0.126
 words+0.123
 footsteps+0.122
ps+0.119
Neg logit contributions
bar-0.188
rob-0.175
c-0.172
bank-0.155
rol-0.153
Token that
Token ID326
Feature activation-2.19e-02

Pos logit contributions
ires+0.005
olving+0.005
 footsteps+0.005
 accidents+0.005
 prayers+0.005
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
 bank-0.005
ah-0.005
Token accidents
Token ID17390
Feature activation+1.83e-01

Pos logit contributions
c+0.031
bar+0.030
 named+0.029
 bank+0.026
rob+0.025
Neg logit contributions
ires-0.040
olving-0.038
 accomplishments-0.037
iders-0.037
 footsteps-0.037
Token can
Token ID460
Feature activation+5.37e-02

Pos logit contributions
 footsteps+0.239
ires+0.227
iders+0.222
 accomplishments+0.217
 prayers+0.216
Neg logit contributions
c-0.316
bar-0.307
 named-0.303
 bank-0.285
 made-0.283
Token happen
Token ID1645
Feature activation+1.06e-01

Pos logit contributions
ires+0.063
olving+0.060
 accomplishments+0.058
 footsteps+0.057
 prayers+0.057
Neg logit contributions
c-0.110
bar-0.108
 named-0.103
 bank-0.098
ah-0.095
Token and
Token ID290
Feature activation+8.87e-03

Pos logit contributions
inner+0.224
 footsteps+0.221
iders+0.216
 prayers+0.213
Done+0.208
Neg logit contributions
c-0.107
 named-0.101
bar-0.097
 one-0.090
 bank-0.079
Token it
Token ID340
Feature activation+1.17e-02

Pos logit contributions
ires+0.015
olving+0.015
 accomplishments+0.014
 footsteps+0.014
 prayers+0.014
Neg logit contributions
c-0.014
bar-0.013
 named-0.012
 bank-0.011
ah-0.011
Token's
Token ID338
Feature activation-4.21e-02

Pos logit contributions
ires+0.026
 accomplishments+0.026
 footsteps+0.026
inner+0.026
olving+0.025
Neg logit contributions
c-0.012
bar-0.011
 named-0.010
 bank-0.009
lers-0.008
Token is
Token ID318
Feature activation+2.48e-02

Pos logit contributions
ires+0.046
olving+0.045
 accomplishments+0.043
 footsteps+0.043
 prayers+0.043
Neg logit contributions
c-0.049
bar-0.047
 named-0.045
rob-0.043
ah-0.041
Token now
Token ID783
Feature activation+1.59e-02

Pos logit contributions
ires+0.037
olving+0.036
 accomplishments+0.035
 footsteps+0.035
 prayers+0.034
Neg logit contributions
c-0.042
bar-0.041
 named-0.039
 bank-0.036
rob-0.036
Token?
Token ID30
Feature activation+3.94e-03

Pos logit contributions
ires+0.025
olving+0.024
iders+0.024
 footsteps+0.023
 accomplishments+0.023
Neg logit contributions
c-0.026
bar-0.026
 named-0.025
 bank-0.023
ah-0.022
Token That
Token ID1320
Feature activation-7.99e-03

Pos logit contributions
ires+0.006
olving+0.006
 accomplishments+0.006
 footsteps+0.006
 prayers+0.006
Neg logit contributions
c-0.007
bar-0.006
 named-0.006
 bank-0.006
ah-0.005
Token's
Token ID338
Feature activation-3.31e-02

Pos logit contributions
c+0.015
bar+0.014
 named+0.014
rob+0.013
 bank+0.013
Neg logit contributions
ires-0.011
olving-0.011
 prayers-0.010
 accomplishments-0.010
 progress-0.010
Token what
Token ID644
Feature activation+1.83e-01

Pos logit contributions
c+0.065
 named+0.062
bar+0.062
 bank+0.056
ah+0.055
Neg logit contributions
ires-0.041
olving-0.040
 accomplishments-0.040
 footsteps-0.039
iders-0.039
Token we
Token ID356
Feature activation-4.95e-02

Pos logit contributions
ires+0.312
olving+0.300
 accomplishments+0.294
iders+0.294
 footsteps+0.291
Neg logit contributions
c-0.277
 named-0.261
bar-0.260
 bank-0.225
ah-0.222
Token call
Token ID869
Feature activation-1.75e-02

Pos logit contributions
c+0.084
bar+0.080
 named+0.078
 bank+0.072
ah+0.070
Neg logit contributions
ires-0.076
olving-0.073
 accomplishments-0.071
 footsteps-0.071
iders-0.070
Token pol
Token ID755
Feature activation+1.02e-03

Pos logit contributions
c+0.026
 named+0.025
bar+0.025
 bank+0.022
ah+0.021
Neg logit contributions
ires-0.030
olving-0.030
 accomplishments-0.029
iders-0.028
 progress-0.027
Tokenishing
Token ID3929
Feature activation+4.50e-02

Pos logit contributions
ires+0.001
olving+0.001
 footsteps+0.001
 accomplishments+0.001
 prayers+0.001
Neg logit contributions
c-0.002
bar-0.002
 named-0.002
 bank-0.002
ah-0.002
Token."
Token ID526
Feature activation-3.48e-02

Pos logit contributions
ires+0.071
olving+0.069
 accomplishments+0.067
 footsteps+0.067
 prayers+0.066
Neg logit contributions
c-0.073
bar-0.070
 named-0.067
 bank-0.062
rob-0.060
Token
Token ID241
Feature activation+4.79e-02

Pos logit contributions
c+0.022
bar+0.020
 named+0.020
 bank+0.018
ah+0.018
Neg logit contributions
ires-0.018
olving-0.017
 footsteps-0.017
 accomplishments-0.017
iders-0.017
TokenMom
Token ID29252
Feature activation+6.87e-02

Pos logit contributions
ires+0.063
olving+0.058
iders+0.056
 accomplishments+0.055
 footsteps+0.055
Neg logit contributions
c-0.090
bar-0.088
 named-0.084
 bank-0.082
rob-0.079
Tokenmy
Token ID1820
Feature activation+1.21e-01

Pos logit contributions
ires+0.126
olving+0.123
 accomplishments+0.119
 footsteps+0.119
 prayers+0.118
Neg logit contributions
c-0.093
bar-0.089
 named-0.085
 bank-0.077
rob-0.076
Token!
Token ID0
Feature activation+2.71e-02

Pos logit contributions
ires+0.215
olving+0.209
 accomplishments+0.204
 footsteps+0.203
iders+0.201
Neg logit contributions
c-0.177
bar-0.168
 named-0.162
 bank-0.146
ah-0.143
Token Look
Token ID6803
Feature activation+3.28e-02

Pos logit contributions
ires+0.043
olving+0.041
 accomplishments+0.040
 footsteps+0.040
 prayers+0.040
Neg logit contributions
c-0.044
bar-0.042
 named-0.041
 bank-0.038
rob-0.037
Token what
Token ID644
Feature activation+1.83e-01

Pos logit contributions
ires+0.055
olving+0.055
iders+0.054
 accomplishments+0.053
 footsteps+0.052
Neg logit contributions
c-0.050
bar-0.048
 named-0.047
ah-0.042
 bank-0.041
Token I
Token ID314
Feature activation-2.24e-02

Pos logit contributions
ires+0.276
olving+0.268
 prayers+0.261
 footsteps+0.260
 accomplishments+0.257
Neg logit contributions
c-0.304
bar-0.292
 named-0.279
 bank-0.263
rob-0.260
Token found
Token ID1043
Feature activation+8.59e-03

Pos logit contributions
c+0.029
bar+0.028
 named+0.026
 bank+0.024
rob+0.023
Neg logit contributions
ires-0.043
olving-0.042
 accomplishments-0.041
 footsteps-0.041
 prayers-0.040
Token on
Token ID319
Feature activation-7.71e-02

Pos logit contributions
ires+0.014
olving+0.013
 accomplishments+0.013
 footsteps+0.013
iders+0.013
Neg logit contributions
c-0.014
bar-0.013
 named-0.013
 bank-0.012
rob-0.011
Token the
Token ID262
Feature activation-5.63e-03

Pos logit contributions
c+0.119
bar+0.113
 named+0.109
 bank+0.100
rob+0.097
Neg logit contributions
ires-0.130
olving-0.126
 accomplishments-0.123
 footsteps-0.122
iders-0.121
Token porch
Token ID33179
Feature activation-9.48e-03

Pos logit contributions
c+0.010
bar+0.009
 named+0.009
 bank+0.008
ah+0.008
Neg logit contributions
ires-0.008
olving-0.008
 accomplishments-0.008
 footsteps-0.008
 prayers-0.008
Token.
Token ID13
Feature activation+9.90e-03

Pos logit contributions
ires+0.108
 prayers+0.102
 footsteps+0.102
olving+0.101
 accomplishments+0.100
Neg logit contributions
c-0.112
bar-0.110
 named-0.102
 bank-0.099
ah-0.091
Token Tim
Token ID5045
Feature activation+3.15e-02

Pos logit contributions
ires+0.015
olving+0.014
 prayers+0.014
 accomplishments+0.013
 accidents+0.013
Neg logit contributions
c-0.017
bar-0.016
 named-0.015
 bank-0.015
rob-0.015
Token learned
Token ID4499
Feature activation+1.62e-03

Pos logit contributions
ires+0.054
olving+0.052
 accomplishments+0.051
 footsteps+0.051
 prayers+0.050
Neg logit contributions
c-0.048
bar-0.045
 named-0.044
 bank-0.040
ah-0.039
Token that
Token ID326
Feature activation-2.29e-02

Pos logit contributions
ires+0.003
olving+0.003
 accomplishments+0.003
 footsteps+0.003
iders+0.003
Neg logit contributions
c-0.002
bar-0.002
 named-0.002
 bank-0.002
rob-0.002
Token sometimes
Token ID3360
Feature activation+2.51e-02

Pos logit contributions
c+0.033
bar+0.032
 named+0.031
 bank+0.028
rob+0.027
Neg logit contributions
ires-0.040
olving-0.039
iders-0.038
 footsteps-0.038
 accomplishments-0.038
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
ires+0.035
olving+0.034
iders+0.033
 footsteps+0.032
 accomplishments+0.032
Neg logit contributions
c-0.046
bar-0.044
 named-0.043
 bank-0.040
rob-0.039
Token happen
Token ID1645
Feature activation+1.05e-01

Pos logit contributions
 footsteps+0.216
ires+0.211
iders+0.205
abies+0.194
 prayers+0.191
Neg logit contributions
bar-0.336
c-0.335
 named-0.319
 bank-0.312
 brought-0.290
Token,
Token ID11
Feature activation-1.57e-04

Pos logit contributions
 footsteps+0.219
inner+0.214
iders+0.213
 prayers+0.211
ires+0.209
Neg logit contributions
c-0.107
bar-0.101
 named-0.099
 bank-0.084
 one-0.083
Token but
Token ID475
Feature activation-3.49e-02

Pos logit contributions
c+0.000
bar+0.000
 named+0.000
 bank+0.000
ah+0.000
Neg logit contributions
ires-0.000
olving-0.000
 accomplishments-0.000
 footsteps-0.000
 prayers-0.000
Token it
Token ID340
Feature activation+9.50e-03

Pos logit contributions
c+0.057
bar+0.054
 named+0.053
 bank+0.048
rob+0.047
Neg logit contributions
ires-0.056
olving-0.054
 accomplishments-0.052
 footsteps-0.052
 prayers-0.051
Token's
Token ID338
Feature activation-4.48e-02

Pos logit contributions
ires+0.021
 footsteps+0.021
olving+0.021
 accomplishments+0.021
iders+0.020
Neg logit contributions
c-0.010
bar-0.009
 named-0.008
 bank-0.007
ah-0.006
Token She
Token ID1375
Feature activation-8.83e-03

Pos logit contributions
iders+0.025
ps+0.024
ires+0.024
 accomplishments+0.024
olving+0.024
Neg logit contributions
c-0.018
 named-0.016
bar-0.016
 pouch-0.013
 bank-0.013
Token also
Token ID635
Feature activation-8.78e-02

Pos logit contributions
c+0.013
bar+0.013
 named+0.012
rob+0.011
 bank+0.011
Neg logit contributions
ires-0.015
olving-0.014
 prayers-0.014
 accomplishments-0.014
 accidents-0.014
Token learned
Token ID4499
Feature activation+2.72e-03

Pos logit contributions
bar+0.145
c+0.139
rob+0.137
ah+0.126
 bank+0.125
Neg logit contributions
olving-0.137
 prayers-0.132
ires-0.131
 accomplishments-0.126
 progress-0.125
Token that
Token ID326
Feature activation-2.14e-02

Pos logit contributions
ires+0.005
olving+0.005
iders+0.005
 accomplishments+0.005
inner+0.005
Neg logit contributions
c-0.004
 named-0.003
bar-0.003
 bank-0.003
ah-0.003
Token sometimes
Token ID3360
Feature activation+2.58e-02

Pos logit contributions
c+0.031
bar+0.029
 named+0.029
 bank+0.025
ah+0.023
Neg logit contributions
ires-0.038
inner-0.037
iders-0.037
olving-0.036
 accomplishments-0.036
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
ires+0.035
inner+0.034
iders+0.033
olving+0.033
 accomplishments+0.031
Neg logit contributions
c-0.048
 named-0.046
bar-0.045
 bank-0.042
 pouch-0.039
Token happen
Token ID1645
Feature activation+1.05e-01

Pos logit contributions
 footsteps+0.210
ires+0.207
iders+0.198
 accomplishments+0.191
abies+0.190
Neg logit contributions
c-0.345
 named-0.323
bar-0.322
 bank-0.306
 called-0.299
Token and
Token ID290
Feature activation+9.20e-03

Pos logit contributions
inner+0.220
 footsteps+0.218
iders+0.214
ires+0.211
 prayers+0.208
Neg logit contributions
c-0.111
 named-0.102
bar-0.092
 one-0.083
 bank-0.078
Token it
Token ID340
Feature activation+1.08e-02

Pos logit contributions
ires+0.015
olving+0.015
 accomplishments+0.014
 footsteps+0.014
 prayers+0.014
Neg logit contributions
c-0.014
bar-0.014
 named-0.013
 bank-0.012
rob-0.012
Token's
Token ID338
Feature activation-4.27e-02

Pos logit contributions
ires+0.024
 footsteps+0.023
 accomplishments+0.023
inner+0.023
iders+0.023
Neg logit contributions
c-0.012
bar-0.010
 named-0.009
 bank-0.008
lers-0.007
Token okay
Token ID8788
Feature activation+1.03e-01

Pos logit contributions
c+0.078
bar+0.074
 named+0.073
 bank+0.067
ah+0.064
Neg logit contributions
ires-0.060
olving-0.057
iders-0.057
 footsteps-0.057
inner-0.056
Token with
Token ID351
Feature activation-5.52e-02

Pos logit contributions
ires+0.043
olving+0.042
 accomplishments+0.041
 footsteps+0.041
iders+0.040
Neg logit contributions
c-0.048
bar-0.045
 named-0.045
 bank-0.041
ah-0.039
Token the
Token ID262
Feature activation-4.14e-03

Pos logit contributions
c+0.090
 named+0.085
bar+0.084
 bank+0.076
 pouch+0.072
Neg logit contributions
ires-0.087
iders-0.085
inner-0.084
olving-0.084
 accomplishments-0.081
Token chores
Token ID46173
Feature activation+1.70e-02

Pos logit contributions
 bank+0.006
c+0.006
bar+0.005
 named+0.005
 one+0.005
Neg logit contributions
iders-0.007
ires-0.007
olving-0.007
abies-0.007
iring-0.006
Token can
Token ID460
Feature activation+5.54e-02

Pos logit contributions
ires+0.026
olving+0.025
 accomplishments+0.024
 footsteps+0.024
 prayers+0.024
Neg logit contributions
c-0.029
bar-0.028
 named-0.027
 bank-0.025
rob-0.024
Token prevent
Token ID2948
Feature activation+7.03e-03

Pos logit contributions
ires+0.077
olving+0.075
 footsteps+0.072
 accomplishments+0.072
 prayers+0.071
Neg logit contributions
c-0.100
bar-0.096
 named-0.094
 bank-0.086
rob-0.086
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
ires+0.011
olving+0.011
iders+0.011
inner+0.011
 accomplishments+0.011
Neg logit contributions
c-0.011
bar-0.011
 named-0.010
 bank-0.010
ah-0.009
Token and
Token ID290
Feature activation+1.33e-02

Pos logit contributions
ires+0.310
iders+0.290
 accomplishments+0.289
 footsteps+0.289
 prayers+0.284
Neg logit contributions
c-0.268
bar-0.262
 bank-0.247
 named-0.239
bank-0.217
Token save
Token ID3613
Feature activation+2.93e-02

Pos logit contributions
ires+0.019
iders+0.019
inner+0.018
olving+0.018
 accomplishments+0.018
Neg logit contributions
c-0.023
bar-0.023
 named-0.022
 bank-0.021
bank-0.019
Token things
Token ID1243
Feature activation+1.11e-01

Pos logit contributions
ires+0.050
olving+0.050
iders+0.050
 accomplishments+0.049
inner+0.049
Neg logit contributions
c-0.043
 named-0.039
bar-0.039
 bank-0.037
 pouch-0.032
Token we
Token ID356
Feature activation-4.97e-02

Pos logit contributions
 footsteps+0.199
ires+0.192
 accomplishments+0.189
 prayers+0.189
iders+0.187
Neg logit contributions
c-0.153
bar-0.149
 named-0.138
 bank-0.137
 pouch-0.116
Token love
Token ID1842
Feature activation+1.32e-01

Pos logit contributions
c+0.079
bar+0.074
 named+0.074
 bank+0.068
ah+0.064
Neg logit contributions
ires-0.082
olving-0.079
 footsteps-0.078
 accomplishments-0.077
iders-0.077
Token "
Token ID366
Feature activation-3.10e-02

Pos logit contributions
c+0.003
bar+0.003
 named+0.003
 bank+0.003
rob+0.003
Neg logit contributions
ires-0.002
olving-0.002
 accomplishments-0.002
 footsteps-0.002
 prayers-0.002
TokenIt
Token ID1026
Feature activation+1.45e-02

Pos logit contributions
c+0.061
bar+0.060
 named+0.058
 bank+0.058
rob+0.054
Neg logit contributions
ires-0.036
olving-0.034
 accomplishments-0.033
inner-0.032
iders-0.032
Token's
Token ID338
Feature activation-4.60e-02

Pos logit contributions
ires+0.031
olving+0.029
 footsteps+0.029
 accomplishments+0.029
iders+0.029
Neg logit contributions
c-0.017
bar-0.015
 named-0.015
 bank-0.013
ah-0.013
Token OK
Token ID7477
Feature activation+9.43e-02

Pos logit contributions
c+0.092
bar+0.089
 named+0.086
 bank+0.081
rob+0.079
Neg logit contributions
ires-0.057
olving-0.055
 accomplishments-0.053
 footsteps-0.052
 prayers-0.052
Token,
Token ID11
Feature activation-1.95e-03

Pos logit contributions
ires+0.191
inner+0.179
iders+0.178
olving+0.176
 accomplishments+0.174
Neg logit contributions
c-0.123
 named-0.121
bar-0.108
ah-0.098
 one-0.091
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
 named+0.003
c+0.003
bar+0.003
ah+0.003
 bank+0.002
Neg logit contributions
ires-0.003
iders-0.003
olving-0.003
inner-0.003
 accomplishments-0.003
Token happen
Token ID1645
Feature activation+9.58e-02

Pos logit contributions
ires+0.165
 footsteps+0.162
olving+0.143
 accomplishments+0.142
 prayers+0.136
Neg logit contributions
c-0.404
 named-0.385
bar-0.382
 bank-0.356
ah-0.348
Token.
Token ID13
Feature activation+1.25e-02

Pos logit contributions
 footsteps+0.180
ires+0.176
olving+0.172
inner+0.170
 accomplishments+0.169
Neg logit contributions
c-0.124
 named-0.117
bar-0.108
 bank-0.094
 one-0.090
Token We
Token ID775
Feature activation-5.56e-02

Pos logit contributions
ires+0.019
olving+0.018
 accomplishments+0.018
 prayers+0.018
 footsteps+0.018
Neg logit contributions
c-0.021
bar-0.020
 named-0.019
 bank-0.018
rob-0.018
Token all
Token ID477
Feature activation-9.43e-02

Pos logit contributions
c+0.099
bar+0.097
 named+0.091
rob+0.091
 bank+0.085
Neg logit contributions
olving-0.076
ires-0.076
 prayers-0.073
 accomplishments-0.072
 footsteps-0.071
Token make
Token ID787
Feature activation-2.99e-02

Pos logit contributions
c+0.159
bar+0.150
 named+0.148
 bank+0.135
ah+0.130
Neg logit contributions
ires-0.149
olving-0.141
iders-0.138
 accomplishments-0.138
 footsteps-0.137
Token on
Token ID319
Feature activation-7.73e-02

Pos logit contributions
olving+0.028
ires+0.028
 accidents+0.027
 prayers+0.026
 accomplishments+0.026
Neg logit contributions
c-0.033
bar-0.032
 bank-0.031
bank-0.031
rob-0.028
Token,
Token ID11
Feature activation+1.79e-03

Pos logit contributions
c+0.123
bar+0.120
 named+0.111
 bank+0.105
rob+0.103
Neg logit contributions
ires-0.126
olving-0.124
 accomplishments-0.120
 prayers-0.118
 footsteps-0.118
Token Lily
Token ID20037
Feature activation+1.04e-02

Pos logit contributions
ires+0.003
olving+0.003
 accomplishments+0.003
 footsteps+0.003
 prayers+0.003
Neg logit contributions
c-0.003
bar-0.003
 named-0.003
 bank-0.002
rob-0.002
Token learned
Token ID4499
Feature activation+3.34e-03

Pos logit contributions
ires+0.020
olving+0.020
 footsteps+0.019
 accomplishments+0.019
iders+0.019
Neg logit contributions
c-0.013
bar-0.012
 named-0.012
 bank-0.011
ah-0.010
Token that
Token ID326
Feature activation-2.26e-02

Pos logit contributions
ires+0.006
olving+0.006
iders+0.006
 accomplishments+0.006
inner+0.006
Neg logit contributions
c-0.004
 named-0.004
bar-0.004
 bank-0.003
ah-0.003
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
c+0.031
bar+0.029
 named+0.029
 bank+0.024
 pouch+0.022
Neg logit contributions
ires-0.042
inner-0.040
iders-0.040
olving-0.039
 footsteps-0.039
Token happen
Token ID1645
Feature activation+1.05e-01

Pos logit contributions
 footsteps+0.226
ires+0.215
iders+0.208
 accomplishments+0.205
abies+0.204
Neg logit contributions
c-0.329
 named-0.312
bar-0.304
 made-0.289
 bank-0.288
Token and
Token ID290
Feature activation+9.40e-03

Pos logit contributions
 footsteps+0.210
inner+0.204
 prayers+0.200
 accomplishments+0.192
ps+0.192
Neg logit contributions
c-0.129
 named-0.120
bar-0.103
 one-0.095
 called-0.089
Token that
Token ID326
Feature activation-2.33e-02

Pos logit contributions
ires+0.016
olving+0.016
 accomplishments+0.015
 footsteps+0.015
iders+0.015
Neg logit contributions
c-0.014
bar-0.014
 named-0.013
 bank-0.012
rob-0.011
Token it
Token ID340
Feature activation+9.78e-03

Pos logit contributions
c+0.038
bar+0.035
 named+0.035
 bank+0.031
rob+0.029
Neg logit contributions
ires-0.038
inner-0.036
iders-0.036
 accomplishments-0.036
olving-0.035
Token's
Token ID338
Feature activation-4.27e-02

Pos logit contributions
 footsteps+0.020
ires+0.020
 accomplishments+0.020
olving+0.019
inner+0.019
Neg logit contributions
c-0.012
bar-0.010
 named-0.010
 bank-0.009
rob-0.008
Token the
Token ID262
Feature activation-4.07e-03

Pos logit contributions
c+0.045
 named+0.043
bar+0.042
 bank+0.038
ah+0.036
Neg logit contributions
ires-0.058
olving-0.058
iders-0.057
inner-0.055
 accomplishments-0.055
Token truth
Token ID3872
Feature activation+4.64e-02

Pos logit contributions
 named+0.008
 bank+0.008
c+0.008
bar+0.008
rob+0.008
Neg logit contributions
ires-0.004
iders-0.004
abies-0.004
olving-0.004
iring-0.004
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
ires+0.072
olving+0.069
 accomplishments+0.068
 footsteps+0.067
 progress+0.066
Neg logit contributions
c-0.079
bar-0.074
 named-0.073
 bank-0.066
ah-0.065
Token She
Token ID1375
Feature activation-1.03e-02

Pos logit contributions
ires+0.017
olving+0.016
 footsteps+0.016
 prayers+0.016
iders+0.016
Neg logit contributions
c-0.020
bar-0.019
 named-0.018
 bank-0.017
ah-0.017
Token says
Token ID1139
Feature activation-5.73e-02

Pos logit contributions
c+0.014
 named+0.013
bar+0.012
 bank+0.011
rob+0.011
Neg logit contributions
olving-0.019
ires-0.019
 accomplishments-0.019
iders-0.019
 footsteps-0.018
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
c+0.061
 named+0.060
bar+0.057
ah+0.045
 bank+0.044
Neg logit contributions
ires-0.123
olving-0.119
 accomplishments-0.117
inner-0.117
iders-0.117
Token happen
Token ID1645
Feature activation+9.88e-02

Pos logit contributions
 footsteps+0.205
ires+0.205
 accomplishments+0.193
 prayers+0.187
olving+0.186
Neg logit contributions
 named-0.352
c-0.347
bar-0.331
rob-0.318
 called-0.317
Token and
Token ID290
Feature activation+1.00e-02

Pos logit contributions
 footsteps+0.194
inner+0.188
 prayers+0.187
ires+0.186
 accomplishments+0.185
Neg logit contributions
c-0.119
 named-0.115
bar-0.101
 one-0.091
 bank-0.087
Token they
Token ID484
Feature activation-7.57e-02

Pos logit contributions
ires+0.016
olving+0.016
 accomplishments+0.016
 footsteps+0.015
iders+0.015
Neg logit contributions
c-0.016
bar-0.015
 named-0.015
 bank-0.013
rob-0.013
Token can
Token ID460
Feature activation+4.64e-02

Pos logit contributions
c+0.124
 named+0.118
bar+0.116
 bank+0.108
ah+0.102
Neg logit contributions
ires-0.123
iders-0.117
olving-0.117
 accomplishments-0.114
 footsteps-0.113
Token fix
Token ID4259
Feature activation+5.04e-02

Pos logit contributions
ires+0.071
olving+0.068
 accomplishments+0.067
iders+0.067
 footsteps+0.066
Neg logit contributions
c-0.078
bar-0.078
 named-0.075
 bank-0.070
ah-0.066
Token But
Token ID887
Feature activation-1.70e-02

Pos logit contributions
ires+0.033
 prayers+0.031
olving+0.031
 footsteps+0.030
iders+0.029
Neg logit contributions
c-0.042
bar-0.041
rob-0.039
 bank-0.039
ah-0.038
Token he
Token ID339
Feature activation-1.17e-02

Pos logit contributions
c+0.027
bar+0.026
 named+0.025
 bank+0.023
rob+0.023
Neg logit contributions
ires-0.027
olving-0.027
 accomplishments-0.026
 footsteps-0.026
 prayers-0.026
Token also
Token ID635
Feature activation-8.86e-02

Pos logit contributions
c+0.018
bar+0.017
 named+0.017
 bank+0.015
ah+0.015
Neg logit contributions
ires-0.020
olving-0.019
 footsteps-0.019
 accomplishments-0.019
iders-0.019
Token learned
Token ID4499
Feature activation-4.05e-03

Pos logit contributions
c+0.138
bar+0.132
 named+0.127
 bank+0.116
rob+0.114
Neg logit contributions
ires-0.147
olving-0.143
 accomplishments-0.139
 footsteps-0.138
 prayers-0.137
Token that
Token ID326
Feature activation-2.64e-02

Pos logit contributions
c+0.006
bar+0.006
 named+0.006
 bank+0.005
ah+0.005
Neg logit contributions
ires-0.007
olving-0.007
iders-0.007
 accomplishments-0.007
inner-0.007
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
c+0.037
bar+0.036
 named+0.036
 bank+0.031
bank+0.029
Neg logit contributions
ires-0.047
iders-0.045
inner-0.045
olving-0.044
 accomplishments-0.044
Token can
Token ID460
Feature activation+4.10e-02

Pos logit contributions
 footsteps+0.240
ires+0.231
 accomplishments+0.217
iders+0.215
 prayers+0.214
Neg logit contributions
c-0.322
bar-0.306
 named-0.305
 bank-0.288
 made-0.276
Token happen
Token ID1645
Feature activation+9.27e-02

Pos logit contributions
ires+0.051
olving+0.047
iders+0.046
 accomplishments+0.046
inner+0.046
Neg logit contributions
c-0.081
bar-0.080
 named-0.075
 bank-0.073
ah-0.069
Token and
Token ID290
Feature activation+7.93e-03

Pos logit contributions
 footsteps+0.171
inner+0.167
iders+0.163
 prayers+0.163
ires+0.160
Neg logit contributions
c-0.120
 named-0.114
bar-0.108
 bank-0.097
 one-0.095
Token it
Token ID340
Feature activation+5.91e-03

Pos logit contributions
ires+0.012
iders+0.012
inner+0.012
olving+0.012
 accomplishments+0.012
Neg logit contributions
c-0.013
bar-0.012
 named-0.012
 bank-0.011
bank-0.010
Token's
Token ID338
Feature activation-4.87e-02

Pos logit contributions
ires+0.011
 footsteps+0.011
 accomplishments+0.011
inner+0.011
iders+0.011
Neg logit contributions
c-0.008
bar-0.007
 named-0.007
 bank-0.006
lers-0.006
Token of
Token ID286
Feature activation+3.19e-02

Pos logit contributions
 footsteps+0.144
 accomplishments+0.141
 progress+0.140
iders+0.139
 prayers+0.139
Neg logit contributions
c-0.057
 named-0.054
bar-0.052
 called-0.032
 pouch-0.028
Token our
Token ID674
Feature activation-6.04e-03

Pos logit contributions
inner+0.054
ires+0.050
iders+0.049
 accomplishments+0.048
 footsteps+0.048
Neg logit contributions
c-0.051
 named-0.049
bar-0.041
 bank-0.041
 one-0.038
Token things
Token ID1243
Feature activation+1.10e-01

Pos logit contributions
c+0.009
 one+0.007
 named+0.007
lers+0.007
 bank+0.007
Neg logit contributions
iders-0.012
inner-0.011
resp-0.011
overed-0.010
bling-0.010
Token,
Token ID11
Feature activation-1.63e-03

Pos logit contributions
ires+0.179
olving+0.172
 footsteps+0.169
 accomplishments+0.168
 prayers+0.166
Neg logit contributions
c-0.176
bar-0.169
 named-0.163
 bank-0.150
rob-0.141
Token but
Token ID475
Feature activation-3.58e-02

Pos logit contributions
c+0.002
bar+0.002
 named+0.002
 bank+0.002
ah+0.002
Neg logit contributions
ires-0.003
olving-0.003
 accomplishments-0.003
 footsteps-0.003
iders-0.003
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
c+0.059
bar+0.056
 named+0.053
rob+0.051
ah+0.051
Neg logit contributions
ires-0.058
olving-0.056
 accidents-0.055
 accomplishments-0.053
 footsteps-0.053
Token happen
Token ID1645
Feature activation+1.04e-01

Pos logit contributions
 footsteps+0.215
ires+0.215
 Deal+0.199
 prayers+0.191
 accomplishments+0.189
Neg logit contributions
c-0.329
 made-0.322
 named-0.322
bar-0.317
 brought-0.308
Token.
Token ID13
Feature activation+6.52e-03

Pos logit contributions
 footsteps+0.187
ires+0.182
inner+0.181
 prayers+0.180
olving+0.179
Neg logit contributions
c-0.143
 named-0.134
bar-0.129
 one-0.111
 bank-0.108
Token She
Token ID1375
Feature activation-8.36e-03

Pos logit contributions
ires+0.010
 footsteps+0.009
olving+0.009
 accidents+0.009
 prayers+0.009
Neg logit contributions
c-0.012
bar-0.011
rob-0.011
ah-0.011
 named-0.010
Token also
Token ID635
Feature activation-8.79e-02

Pos logit contributions
bar+0.012
c+0.012
rob+0.011
bank+0.011
 pouch+0.010
Neg logit contributions
 prayers-0.014
ires-0.014
 accidents-0.013
olving-0.013
ps-0.013
Token said
Token ID531
Feature activation-5.97e-02

Pos logit contributions
bar+0.138
c+0.130
rob+0.125
 pouch+0.119
ah+0.118
Neg logit contributions
olving-0.139
ires-0.139
 accidents-0.138
 prayers-0.137
 forgiveness-0.132
Token him
Token ID683
Feature activation+1.21e-01

Pos logit contributions
bar+0.118
c+0.117
 named+0.117
 bank+0.099
ah+0.096
Neg logit contributions
ires-0.147
iders-0.147
olving-0.145
 accomplishments-0.141
inner-0.138
Token it
Token ID340
Feature activation+1.01e-02

Pos logit contributions
ires+0.226
iders+0.212
olving+0.212
inner+0.208
 accomplishments+0.206
Neg logit contributions
 named-0.164
c-0.160
bar-0.157
 bank-0.136
ah-0.129
Token was
Token ID373
Feature activation-1.08e-02

Pos logit contributions
ires+0.023
 accomplishments+0.021
olving+0.020
iders+0.020
inner+0.020
Neg logit contributions
c-0.012
bar-0.011
 named-0.010
 bank-0.009
ah-0.008
Token okay
Token ID8788
Feature activation+1.03e-01

Pos logit contributions
c+0.025
bar+0.024
 named+0.023
 bank+0.022
ah+0.022
Neg logit contributions
ires-0.010
olving-0.010
 accomplishments-0.009
 footsteps-0.009
iders-0.009
Token,
Token ID11
Feature activation-2.68e-03

Pos logit contributions
ires+0.223
inner+0.215
 accomplishments+0.208
 progress+0.208
iders+0.202
Neg logit contributions
 named-0.132
c-0.128
bar-0.111
ah-0.097
 one-0.094
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
c+0.004
bar+0.004
 named+0.004
rob+0.004
 bank+0.004
Neg logit contributions
ires-0.004
olving-0.004
 footsteps-0.004
 accidents-0.004
 prayers-0.004
Token happen
Token ID1645
Feature activation+1.04e-01

Pos logit contributions
ires+0.212
 footsteps+0.196
 Deal+0.188
iders+0.187
 accomplishments+0.187
Neg logit contributions
 named-0.346
bar-0.345
c-0.341
 made-0.333
 bank-0.317
Token.
Token ID13
Feature activation+4.76e-03

Pos logit contributions
 footsteps+0.187
ires+0.187
 prayers+0.183
inner+0.183
olving+0.181
Neg logit contributions
c-0.139
bar-0.133
 named-0.132
 one-0.109
 bank-0.107
Token They
Token ID1119
Feature activation-3.67e-02

Pos logit contributions
ires+0.008
olving+0.007
 footsteps+0.007
 accidents+0.007
 prayers+0.007
Neg logit contributions
c-0.008
bar-0.007
rob-0.007
ah-0.007
 named-0.007
Token cleaned
Token ID20750
Feature activation+2.05e-02

Pos logit contributions
c+0.057
rob+0.055
bar+0.053
bank+0.050
 pouch+0.049
Neg logit contributions
 footsteps-0.058
 prayers-0.056
olving-0.056
 accidents-0.056
ires-0.054
Token up
Token ID510
Feature activation+4.84e-02

Pos logit contributions
ires+0.027
olving+0.026
 accomplishments+0.026
 footsteps+0.025
iders+0.025
Neg logit contributions
c-0.039
bar-0.037
 named-0.036
 bank-0.034
rob-0.033
Token "
Token ID366
Feature activation-2.22e-02

Pos logit contributions
c+0.007
bar+0.006
 named+0.006
 bank+0.006
ah+0.006
Neg logit contributions
ires-0.005
olving-0.005
 accomplishments-0.005
 footsteps-0.005
iders-0.005
TokenIt
Token ID1026
Feature activation+1.94e-02

Pos logit contributions
c+0.044
bar+0.042
 named+0.041
 bank+0.039
ah+0.038
Neg logit contributions
ires-0.028
olving-0.027
iders-0.025
 accidents-0.025
 accomplishments-0.025
Token's
Token ID338
Feature activation-4.63e-02

Pos logit contributions
ires+0.044
olving+0.043
 accomplishments+0.042
 footsteps+0.042
iders+0.041
Neg logit contributions
c-0.019
bar-0.018
 named-0.017
 bank-0.014
ah-0.013
Token okay
Token ID8788
Feature activation+1.04e-01

Pos logit contributions
c+0.098
bar+0.095
 named+0.093
 bank+0.085
ah+0.084
Neg logit contributions
ires-0.053
olving-0.050
 accomplishments-0.049
 footsteps-0.049
iders-0.048
Token,
Token ID11
Feature activation-2.67e-03

Pos logit contributions
ires+0.214
olving+0.206
inner+0.206
iders+0.202
 accomplishments+0.201
Neg logit contributions
 named-0.125
c-0.121
bar-0.115
ah-0.096
 bank-0.093
Token accidents
Token ID17390
Feature activation+1.82e-01

Pos logit contributions
bar+0.003
 named+0.003
c+0.003
 bank+0.003
ah+0.003
Neg logit contributions
ires-0.005
olving-0.005
iders-0.005
 accomplishments-0.005
inner-0.005
Token happen
Token ID1645
Feature activation+1.03e-01

Pos logit contributions
 footsteps+0.207
ires+0.193
 accomplishments+0.188
 prayers+0.181
iders+0.179
Neg logit contributions
 named-0.344
bar-0.332
c-0.328
 made-0.316
 bank-0.309
Token.
Token ID13
Feature activation+2.41e-03

Pos logit contributions
 footsteps+0.201
olving+0.194
inner+0.193
ires+0.193
 prayers+0.193
Neg logit contributions
 named-0.120
c-0.120
bar-0.111
 one-0.094
 bank-0.093
Token Let
Token ID3914
Feature activation-8.77e-03

Pos logit contributions
ires+0.004
olving+0.004
 accomplishments+0.003
 footsteps+0.003
 prayers+0.003
Neg logit contributions
c-0.004
bar-0.004
 named-0.004
 bank-0.003
ah-0.003
Token's
Token ID338
Feature activation-4.51e-02

Pos logit contributions
bar+0.012
c+0.012
rob+0.012
 named+0.011
 pouch+0.011
Neg logit contributions
 accidents-0.015
 happen-0.015
ires-0.014
 progress-0.014
 footsteps-0.014
Token go
Token ID467
Feature activation+4.16e-02

Pos logit contributions
c+0.077
 named+0.076
bar+0.075
 bank+0.069
ah+0.064
Neg logit contributions
ires-0.070
iders-0.065
olving-0.065
 accomplishments-0.064
 footsteps-0.063
Token of
Token ID286
Feature activation+3.00e-02

Pos logit contributions
ires+0.032
inner+0.030
olving+0.030
 words+0.029
 accomplishments+0.029
Neg logit contributions
c-0.045
bar-0.045
 bank-0.041
 named-0.040
rob-0.039
Token the
Token ID262
Feature activation-5.71e-03

Pos logit contributions
ires+0.041
olving+0.040
 accidents+0.039
 footsteps+0.039
 accomplishments+0.039
Neg logit contributions
bar-0.054
c-0.053
 bank-0.048
ah-0.046
 pouch-0.046
Token story
Token ID1621
Feature activation+2.02e-02

Pos logit contributions
c+0.011
bar+0.011
 named+0.011
 bank+0.010
ah+0.010
Neg logit contributions
ires-0.007
olving-0.007
 accomplishments-0.006
iders-0.006
 footsteps-0.006
Token is
Token ID318
Feature activation-8.58e-03

Pos logit contributions
ires+0.029
 footsteps+0.029
 accomplishments+0.028
olving+0.028
 progress+0.027
Neg logit contributions
c-0.035
 named-0.033
bar-0.033
 bank-0.030
ah-0.030
Token that
Token ID326
Feature activation-2.51e-02

Pos logit contributions
c+0.016
bar+0.015
rob+0.015
 bank+0.014
ah+0.013
Neg logit contributions
ires-0.013
olving-0.012
 accomplishments-0.012
 accidents-0.011
 prayers-0.011
Token accidents
Token ID17390
Feature activation+1.81e-01

Pos logit contributions
c+0.039
bar+0.037
 named+0.037
 bank+0.032
ah+0.030
Neg logit contributions
ires-0.042
olving-0.040
inner-0.040
iders-0.040
 footsteps-0.039
Token happen
Token ID1645
Feature activation+1.05e-01

Pos logit contributions
 footsteps+0.197
ires+0.190
iders+0.184
abies+0.172
 prayers+0.170
Neg logit contributions
c-0.351
bar-0.343
 named-0.343
 bank-0.327
 brought-0.313
Token,
Token ID11
Feature activation-3.89e-03

Pos logit contributions
 footsteps+0.204
inner+0.199
ires+0.198
 prayers+0.197
iders+0.195
Neg logit contributions
c-0.126
 named-0.122
bar-0.114
 bank-0.098
 one-0.094
Token but
Token ID475
Feature activation-4.21e-02

Pos logit contributions
c+0.006
bar+0.006
 named+0.005
 bank+0.005
ah+0.005
Neg logit contributions
ires-0.007
olving-0.006
 accomplishments-0.006
 footsteps-0.006
iders-0.006
Token it
Token ID340
Feature activation+1.04e-02

Pos logit contributions
c+0.074
bar+0.070
 named+0.067
 bank+0.063
ah+0.063
Neg logit contributions
ires-0.063
olving-0.061
 accomplishments-0.059
 accidents-0.058
 footsteps-0.058
Token's
Token ID338
Feature activation-4.59e-02

Pos logit contributions
ires+0.023
 footsteps+0.022
olving+0.022
 accomplishments+0.022
iders+0.021
Neg logit contributions
c-0.011
bar-0.010
 named-0.009
 bank-0.008
ah-0.008
Token new
Token ID649
Feature activation+4.63e-02

Pos logit contributions
ires+0.076
olving+0.075
 accomplishments+0.073
 prayers+0.072
 footsteps+0.072
Neg logit contributions
c-0.078
bar-0.076
 named-0.073
rob-0.067
 bank-0.066
Token home
Token ID1363
Feature activation-1.21e-02

Pos logit contributions
ires+0.067
olving+0.066
 accomplishments+0.066
 footsteps+0.064
 prayers+0.064
Neg logit contributions
c-0.078
bar-0.077
 named-0.073
rob-0.070
ah-0.068
Token with
Token ID351
Feature activation-6.82e-02

Pos logit contributions
c+0.022
bar+0.021
 named+0.020
 bank+0.019
ah+0.018
Neg logit contributions
ires-0.017
olving-0.017
 accomplishments-0.016
 footsteps-0.016
iders-0.016
Token the
Token ID262
Feature activation-2.19e-02

Pos logit contributions
c+0.117
bar+0.113
 named+0.108
 bank+0.101
rob+0.099
Neg logit contributions
ires-0.102
olving-0.099
 footsteps-0.096
 accomplishments-0.096
 prayers-0.095
Token fan
Token ID4336
Feature activation-4.74e-02

Pos logit contributions
c+0.034
bar+0.032
 named+0.032
 bank+0.030
ah+0.029
Neg logit contributions
ires-0.037
iders-0.037
olving-0.035
abies-0.034
inner-0.033
Tokenci
Token ID979
Feature activation-2.04e-01

Pos logit contributions
c+0.087
bar+0.085
 named+0.082
rob+0.079
 bank+0.076
Neg logit contributions
ires-0.060
olving-0.060
 accomplishments-0.057
 footsteps-0.057
 prayers-0.057
Tokenest
Token ID395
Feature activation-3.65e-03

Pos logit contributions
c+0.331
bar+0.327
 named+0.316
rob+0.294
 bank+0.288
Neg logit contributions
ires-0.300
olving-0.299
 accomplishments-0.291
 prayers-0.290
 footsteps-0.289
Token king
Token ID5822
Feature activation+1.07e-02

Pos logit contributions
c+0.006
 named+0.006
bar+0.006
 bank+0.005
ah+0.005
Neg logit contributions
ires-0.006
iders-0.006
olving-0.005
inner-0.005
iring-0.005
Token in
Token ID287
Feature activation-2.73e-02

Pos logit contributions
ires+0.017
olving+0.016
 accomplishments+0.016
 footsteps+0.016
 prayers+0.016
Neg logit contributions
c-0.017
bar-0.017
 named-0.016
 bank-0.015
rob-0.015
Token the
Token ID262
Feature activation-2.22e-02

Pos logit contributions
c+0.047
bar+0.047
 named+0.042
rob+0.041
 bank+0.041
Neg logit contributions
ires-0.041
olving-0.039
 footsteps-0.039
 accomplishments-0.038
 prayers-0.038
Token land
Token ID1956
Feature activation+1.18e-02

Pos logit contributions
c+0.036
bar+0.035
 named+0.033
rob+0.031
 bank+0.030
Neg logit contributions
ires-0.034
olving-0.034
 accomplishments-0.033
 footsteps-0.033
 prayers-0.033
Token the
Token ID262
Feature activation-1.39e-02

Pos logit contributions
ires+0.068
olving+0.068
 progress+0.067
 accomplishments+0.065
 accidents+0.064
Neg logit contributions
c-0.083
bar-0.081
rob-0.076
 bank-0.074
 named-0.072
Token brav
Token ID49025
Feature activation-4.26e-02

Pos logit contributions
c+0.020
bar+0.020
 named+0.019
 bank+0.017
ah+0.017
Neg logit contributions
ires-0.025
olving-0.024
iders-0.023
 footsteps-0.023
 accomplishments-0.023
Tokenest
Token ID395
Feature activation-2.25e-03

Pos logit contributions
c+0.067
bar+0.063
 named+0.061
 bank+0.056
ah+0.055
Neg logit contributions
ires-0.071
olving-0.069
 accomplishments-0.067
 footsteps-0.067
iders-0.067
Token and
Token ID290
Feature activation+2.63e-03

Pos logit contributions
c+0.003
 named+0.003
bar+0.003
ah+0.003
 bank+0.003
Neg logit contributions
ires-0.004
olving-0.004
iders-0.004
inner-0.004
 footsteps-0.004
Token boun
Token ID31283
Feature activation-8.07e-02

Pos logit contributions
 accidents+0.003
olving+0.003
 progress+0.003
ires+0.003
 accomplishments+0.003
Neg logit contributions
c-0.005
bar-0.005
 named-0.005
 bank-0.005
rob-0.005
Tokenci
Token ID979
Feature activation-2.04e-01

Pos logit contributions
bar+0.123
c+0.122
 named+0.116
 bank+0.114
bank+0.106
Neg logit contributions
ires-0.131
olving-0.124
inner-0.120
 accomplishments-0.120
iders-0.118
Tokenest
Token ID395
Feature activation-2.32e-03

Pos logit contributions
c+0.338
bar+0.331
 named+0.317
 bank+0.292
rob+0.291
Neg logit contributions
ires-0.299
olving-0.295
 accomplishments-0.290
 footsteps-0.284
 progress-0.283
Token bunny
Token ID44915
Feature activation-4.60e-02

Pos logit contributions
c+0.004
 named+0.003
bar+0.003
 bank+0.003
ah+0.003
Neg logit contributions
ires-0.004
iders-0.004
olving-0.004
inner-0.004
 prayers-0.003
Token in
Token ID287
Feature activation-2.33e-02

Pos logit contributions
c+0.077
bar+0.074
 named+0.069
rob+0.068
 bank+0.067
Neg logit contributions
ires-0.067
olving-0.065
 accomplishments-0.064
iders-0.062
 footsteps-0.062
Token the
Token ID262
Feature activation-1.44e-02

Pos logit contributions
c+0.041
bar+0.041
rob+0.037
 bank+0.036
 named+0.036
Neg logit contributions
ires-0.033
olving-0.032
 footsteps-0.031
 accomplishments-0.031
 progress-0.031
Token whole
Token ID2187
Feature activation+1.92e-02

Pos logit contributions
bar+0.023
c+0.023
 named+0.022
rob+0.020
 bank+0.020
Neg logit contributions
ires-0.023
olving-0.022
 accomplishments-0.022
 progress-0.022
 footsteps-0.022
Token to
Token ID284
Feature activation-1.23e-02

Pos logit contributions
c+0.035
bar+0.034
 named+0.033
 bank+0.030
ah+0.028
Neg logit contributions
ires-0.047
olving-0.046
 accomplishments-0.044
 footsteps-0.044
iders-0.044
Token put
Token ID1234
Feature activation-3.96e-02

Pos logit contributions
c+0.022
bar+0.021
 named+0.020
rob+0.019
ah+0.019
Neg logit contributions
ires-0.017
olving-0.017
 prayers-0.016
 accomplishments-0.016
 footsteps-0.016
Token on
Token ID319
Feature activation-7.98e-02

Pos logit contributions
bar+0.068
c+0.067
 named+0.063
 bank+0.060
bank+0.060
Neg logit contributions
ires-0.058
 prayers-0.053
 progress-0.053
 accomplishments-0.052
olving-0.052
Token her
Token ID607
Feature activation+5.48e-02

Pos logit contributions
c+0.144
bar+0.139
 named+0.134
 bank+0.125
rob+0.122
Neg logit contributions
ires-0.113
olving-0.109
 accomplishments-0.106
 footsteps-0.105
 prayers-0.104
Token fan
Token ID4336
Feature activation-3.84e-02

Pos logit contributions
ires+0.085
olving+0.084
iders+0.081
 footsteps+0.080
 accomplishments+0.079
Neg logit contributions
c-0.093
bar-0.088
 named-0.087
 bank-0.080
 pouch-0.077
Tokenci
Token ID979
Feature activation-2.01e-01

Pos logit contributions
bar+0.036
c+0.036
 named+0.033
rob+0.032
ah+0.030
Neg logit contributions
olving-0.078
ires-0.076
iders-0.075
 accomplishments-0.075
 footsteps-0.074
Tokenest
Token ID395
Feature activation+2.84e-03

Pos logit contributions
bar+0.335
c+0.333
 named+0.319
rob+0.312
 pouch+0.301
Neg logit contributions
olving-0.272
ires-0.270
 prayers-0.269
 footsteps-0.266
 accomplishments-0.265
Token sunglasses
Token ID36251
Feature activation-9.24e-03

Pos logit contributions
ires+0.005
olving+0.004
iders+0.004
 accomplishments+0.004
 footsteps+0.004
Neg logit contributions
c-0.005
bar-0.005
 named-0.004
 bank-0.004
ah-0.004
Token.
Token ID13
Feature activation+5.03e-03

Pos logit contributions
c+0.016
bar+0.015
 named+0.015
rob+0.014
 bank+0.014
Neg logit contributions
ires-0.013
olving-0.013
inner-0.012
 accomplishments-0.012
iders-0.012
Token
Token ID198
Feature activation+3.67e-03

Pos logit contributions
ires+0.009
olving+0.009
 accomplishments+0.009
iders+0.009
 footsteps+0.009
Neg logit contributions
c-0.007
 named-0.007
bar-0.006
 bank-0.006
 pouch-0.005
Token
Token ID198
Feature activation+3.99e-03

Pos logit contributions
ires+0.005
olving+0.005
 accomplishments+0.005
 footsteps+0.005
iders+0.005
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
 bank-0.006
ah-0.005
Token she
Token ID673
Feature activation-3.73e-02

Pos logit contributions
c+0.003
bar+0.003
 named+0.003
rob+0.003
 bank+0.003
Neg logit contributions
ires-0.003
olving-0.003
 accomplishments-0.003
 footsteps-0.002
 accidents-0.002
Token always
Token ID1464
Feature activation-5.41e-03

Pos logit contributions
c+0.051
bar+0.050
 named+0.044
 bank+0.042
rob+0.041
Neg logit contributions
olving-0.068
ires-0.067
 accomplishments-0.065
 prayers-0.064
iders-0.063
Token wore
Token ID12408
Feature activation-4.87e-02

Pos logit contributions
bar+0.008
c+0.008
 bank+0.007
rob+0.007
 named+0.007
Neg logit contributions
olving-0.009
 prayers-0.009
ires-0.008
 footsteps-0.008
 accomplishments-0.008
Token her
Token ID607
Feature activation+5.55e-02

Pos logit contributions
c+0.080
 named+0.074
bar+0.071
 bank+0.065
rob+0.062
Neg logit contributions
ires-0.079
iders-0.078
inner-0.077
olving-0.077
iring-0.073
Token fan
Token ID4336
Feature activation-3.80e-02

Pos logit contributions
ires+0.079
olving+0.075
iders+0.074
 footsteps+0.073
inner+0.072
Neg logit contributions
c-0.102
 named-0.095
bar-0.095
 bank-0.088
ah-0.084
Tokenci
Token ID979
Feature activation-2.01e-01

Pos logit contributions
c+0.057
bar+0.053
 named+0.051
 bank+0.047
ah+0.045
Neg logit contributions
ires-0.068
olving-0.065
 footsteps-0.063
 accomplishments-0.063
iders-0.063
Tokenest
Token ID395
Feature activation+4.87e-03

Pos logit contributions
c+0.323
bar+0.310
 named+0.299
 bank+0.275
rob+0.269
Neg logit contributions
ires-0.321
olving-0.312
 accomplishments-0.303
 footsteps-0.302
 prayers-0.299
Token dress
Token ID6576
Feature activation-5.13e-02

Pos logit contributions
ires+0.007
iders+0.007
olving+0.007
inner+0.007
 accomplishments+0.006
Neg logit contributions
c-0.009
 named-0.008
bar-0.008
 bank-0.008
ah-0.007
Token to
Token ID284
Feature activation-1.01e-02

Pos logit contributions
c+0.083
bar+0.079
 named+0.077
 bank+0.070
ah+0.068
Neg logit contributions
ires-0.083
olving-0.079
 footsteps-0.079
 accomplishments-0.078
 prayers-0.077
Token the
Token ID262
Feature activation-8.65e-03

Pos logit contributions
c+0.018
bar+0.018
 named+0.017
 bank+0.016
ah+0.015
Neg logit contributions
ires-0.014
olving-0.014
 accomplishments-0.013
 footsteps-0.013
iders-0.013
Token museum
Token ID13257
Feature activation+7.98e-02

Pos logit contributions
c+0.013
 named+0.013
 bank+0.013
bar+0.011
 gir+0.010
Neg logit contributions
iders-0.015
ires-0.014
olving-0.014
abies-0.014
ps-0.013
Token will
Token ID481
Feature activation-2.11e-02

Pos logit contributions
c+0.024
bar+0.024
 named+0.022
rob+0.021
 bank+0.021
Neg logit contributions
olving-0.015
ires-0.014
 accomplishments-0.014
 prayers-0.014
inner-0.014
Token buy
Token ID2822
Feature activation+9.14e-03

Pos logit contributions
c+0.036
bar+0.035
 named+0.034
 bank+0.031
ah+0.031
Neg logit contributions
ires-0.031
olving-0.030
 accomplishments-0.029
 footsteps-0.029
iders-0.029
Token you
Token ID345
Feature activation+3.70e-02

Pos logit contributions
ires+0.013
olving+0.013
 footsteps+0.013
 accomplishments+0.013
 prayers+0.012
Neg logit contributions
c-0.016
bar-0.015
 named-0.015
 bank-0.014
ah-0.014
Token the
Token ID262
Feature activation-1.31e-02

Pos logit contributions
ires+0.054
olving+0.051
 accomplishments+0.050
 footsteps+0.050
 prayers+0.049
Neg logit contributions
c-0.064
bar-0.063
 named-0.060
 bank-0.056
rob-0.055
Token fan
Token ID4336
Feature activation-4.01e-02

Pos logit contributions
c+0.022
 named+0.021
bar+0.020
 bank+0.019
 pouch+0.018
Neg logit contributions
ires-0.021
iders-0.021
olving-0.020
 accomplishments-0.019
iring-0.019
Tokenci
Token ID979
Feature activation-2.00e-01

Pos logit contributions
c+0.066
bar+0.064
 named+0.061
rob+0.058
 bank+0.057
Neg logit contributions
ires-0.060
olving-0.059
 accomplishments-0.057
 prayers-0.056
iders-0.056
Tokenest
Token ID395
Feature activation+3.22e-03

Pos logit contributions
bar+0.347
c+0.339
 named+0.326
rob+0.310
 pouch+0.306
Neg logit contributions
ires-0.269
olving-0.267
 accomplishments-0.262
 prayers-0.261
 progress-0.255
Token dress
Token ID6576
Feature activation-5.18e-02

Pos logit contributions
ires+0.005
olving+0.005
 accomplishments+0.005
 footsteps+0.004
 prayers+0.004
Neg logit contributions
c-0.006
bar-0.005
 named-0.005
 bank-0.005
rob-0.005
Token in
Token ID287
Feature activation-1.79e-02

Pos logit contributions
c+0.087
bar+0.083
 named+0.081
 bank+0.075
rob+0.073
Neg logit contributions
ires-0.079
olving-0.076
 accomplishments-0.074
iders-0.073
inner-0.073
Token the
Token ID262
Feature activation-1.31e-02

Pos logit contributions
c+0.031
bar+0.030
 named+0.028
rob+0.028
 bank+0.027
Neg logit contributions
ires-0.027
olving-0.025
 accomplishments-0.025
 progress-0.024
 footsteps-0.024
Token store
Token ID3650
Feature activation-5.54e-02

Pos logit contributions
bar+0.022
c+0.022
 named+0.021
rob+0.019
ah+0.019
Neg logit contributions
ires-0.019
olving-0.019
 prayers-0.018
 footsteps-0.018
 accomplishments-0.018
Token dressed
Token ID12049
Feature activation-4.01e-02

Pos logit contributions
c+0.006
bar+0.006
rob+0.005
ah+0.005
 named+0.005
Neg logit contributions
ires-0.004
 footsteps-0.004
 prayers-0.004
 progress-0.004
 accidents-0.004
Token up
Token ID510
Feature activation+4.48e-02

Pos logit contributions
c+0.063
 named+0.059
bar+0.058
 bank+0.055
 pouch+0.051
Neg logit contributions
ires-0.067
olving-0.067
iders-0.065
 footsteps-0.062
 accomplishments-0.062
Token in
Token ID287
Feature activation-1.51e-02

Pos logit contributions
ires+0.067
olving+0.065
 accomplishments+0.063
 footsteps+0.062
iders+0.062
Neg logit contributions
c-0.078
bar-0.074
 named-0.073
 bank-0.067
ah-0.065
Token her
Token ID607
Feature activation+5.40e-02

Pos logit contributions
c+0.026
bar+0.025
 named+0.024
 bank+0.022
ah+0.022
Neg logit contributions
ires-0.023
olving-0.022
 accomplishments-0.021
 footsteps-0.021
iders-0.021
Token fan
Token ID4336
Feature activation-3.98e-02

Pos logit contributions
ires+0.083
olving+0.080
iders+0.077
 accomplishments+0.077
 footsteps+0.077
Neg logit contributions
c-0.093
bar-0.088
 named-0.086
 bank-0.080
 pouch-0.076
Tokenci
Token ID979
Feature activation-2.00e-01

Pos logit contributions
c+0.069
bar+0.069
 named+0.065
rob+0.065
ah+0.062
Neg logit contributions
olving-0.052
ires-0.050
 footsteps-0.050
 accomplishments-0.050
 prayers-0.049
Tokenest
Token ID395
Feature activation+3.32e-03

Pos logit contributions
bar+0.347
c+0.342
 named+0.330
rob+0.324
 pouch+0.302
Neg logit contributions
 footsteps-0.262
 prayers-0.261
ires-0.256
olving-0.254
 accomplishments-0.250
Token clothes
Token ID8242
Feature activation-6.94e-03

Pos logit contributions
ires+0.005
olving+0.005
iders+0.005
inner+0.004
 accomplishments+0.004
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
 bank-0.005
ah-0.005
Token and
Token ID290
Feature activation+4.53e-03

Pos logit contributions
c+0.013
bar+0.012
 named+0.012
rob+0.011
 bank+0.011
Neg logit contributions
ires-0.009
olving-0.009
 accomplishments-0.009
 footsteps-0.009
inner-0.009
Token asked
Token ID1965
Feature activation-6.68e-02

Pos logit contributions
ires+0.008
olving+0.008
 footsteps+0.007
 accomplishments+0.007
 prayers+0.007
Neg logit contributions
c-0.007
bar-0.006
 named-0.006
 bank-0.006
ah-0.006
Token her
Token ID607
Feature activation+5.40e-02

Pos logit contributions
 named+0.089
c+0.088
bar+0.076
 bank+0.071
 one+0.066
Neg logit contributions
ires-0.123
inner-0.122
iders-0.122
olving-0.118
 accomplishments-0.114
Token the
Token ID262
Feature activation-1.20e-02

Pos logit contributions
 footsteps+0.002
 prayers+0.002
olving+0.002
 downstairs+0.002
 what+0.002
Neg logit contributions
rob-0.002
bar-0.002
c-0.002
ah-0.002
bank-0.002
Token daughter
Token ID4957
Feature activation-3.01e-02

Pos logit contributions
c+0.021
 named+0.021
bar+0.020
 bank+0.019
 pouch+0.018
Neg logit contributions
ires-0.018
iders-0.017
olving-0.017
 accomplishments-0.015
ps-0.015
Token found
Token ID1043
Feature activation+5.27e-03

Pos logit contributions
bar+0.041
rob+0.041
c+0.041
ah+0.038
bank+0.034
Neg logit contributions
 prayers-0.049
olving-0.049
 footsteps-0.048
ires-0.047
 accomplishments-0.047
Token the
Token ID262
Feature activation-1.21e-02

Pos logit contributions
ires+0.008
olving+0.008
 footsteps+0.007
 accomplishments+0.007
 prayers+0.007
Neg logit contributions
c-0.009
bar-0.009
 named-0.008
 bank-0.008
ah-0.008
Token fan
Token ID4336
Feature activation-4.05e-02

Pos logit contributions
c+0.020
bar+0.019
 named+0.019
 bank+0.018
 pouch+0.017
Neg logit contributions
ires-0.019
iders-0.019
olving-0.018
 accomplishments-0.017
 footsteps-0.017
Tokenci
Token ID979
Feature activation-1.99e-01

Pos logit contributions
c+0.069
bar+0.066
 named+0.064
 bank+0.059
rob+0.058
Neg logit contributions
ires-0.061
olving-0.059
 accomplishments-0.057
 footsteps-0.057
 prayers-0.056
Tokenest
Token ID395
Feature activation+3.96e-03

Pos logit contributions
c+0.321
bar+0.320
 named+0.307
rob+0.287
 pouch+0.281
Neg logit contributions
ires-0.292
olving-0.289
 accomplishments-0.283
 footsteps-0.281
 progress-0.277
Token dress
Token ID6576
Feature activation-5.21e-02

Pos logit contributions
ires+0.007
iders+0.006
olving+0.006
 accomplishments+0.006
 prayers+0.006
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
 bank-0.006
ah-0.005
Token she
Token ID673
Feature activation-3.85e-02

Pos logit contributions
c+0.091
bar+0.087
 named+0.084
 bank+0.078
rob+0.076
Neg logit contributions
ires-0.077
olving-0.074
 accomplishments-0.072
 footsteps-0.072
 prayers-0.071
Token had
Token ID550
Feature activation-4.52e-02

Pos logit contributions
c+0.047
bar+0.046
 named+0.041
 bank+0.038
rob+0.037
Neg logit contributions
ires-0.077
olving-0.075
 accomplishments-0.074
 prayers-0.072
iders-0.072
Token ever
Token ID1683
Feature activation+1.65e-02

Pos logit contributions
c+0.078
bar+0.076
 named+0.071
 bank+0.067
ah+0.066
Neg logit contributions
ires-0.067
olving-0.065
 accomplishments-0.063
iders-0.061
 footsteps-0.061
Token and
Token ID290
Feature activation+4.18e-03

Pos logit contributions
c+0.011
 named+0.011
bar+0.011
rob+0.010
ah+0.010
Neg logit contributions
ires-0.008
olving-0.008
inner-0.007
iders-0.007
 accidents-0.007
Token put
Token ID1234
Feature activation-4.84e-02

Pos logit contributions
ires+0.007
olving+0.006
 accidents+0.006
 prayers+0.006
 progress+0.006
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
rob-0.006
ah-0.006
Token it
Token ID340
Feature activation+2.91e-03

Pos logit contributions
c+0.078
bar+0.076
 named+0.074
 bank+0.068
rob+0.067
Neg logit contributions
ires-0.075
olving-0.072
 accomplishments-0.069
 progress-0.069
inner-0.069
Token in
Token ID287
Feature activation-2.73e-02

Pos logit contributions
ires+0.005
olving+0.005
 accomplishments+0.005
 footsteps+0.005
 prayers+0.005
Neg logit contributions
c-0.005
bar-0.004
 named-0.004
 bank-0.004
ah-0.004
Token a
Token ID257
Feature activation+1.72e-02

Pos logit contributions
c+0.050
bar+0.048
 named+0.046
rob+0.043
 bank+0.043
Neg logit contributions
ires-0.038
olving-0.037
 footsteps-0.036
 accomplishments-0.036
 progress-0.035
Token pouch
Token ID36594
Feature activation-1.97e-01

Pos logit contributions
inner+0.024
 progress+0.023
 accomplishments+0.023
olving+0.023
 footsteps+0.023
Neg logit contributions
rob-0.028
c-0.027
bar-0.027
 named-0.026
ah-0.025
Token around
Token ID1088
Feature activation+9.29e-03

Pos logit contributions
rob+0.402
c+0.391
bar+0.367
 named+0.367
ah+0.363
Neg logit contributions
ires-0.207
olving-0.203
ble-0.191
iring-0.190
inner-0.190
Token her
Token ID607
Feature activation+5.04e-02

Pos logit contributions
ires+0.014
olving+0.013
 accomplishments+0.013
 footsteps+0.013
 prayers+0.013
Neg logit contributions
c-0.016
bar-0.015
 named-0.015
 bank-0.014
rob-0.014
Token shoulder
Token ID8163
Feature activation-6.19e-02

Pos logit contributions
ires+0.082
olving+0.079
 accomplishments+0.076
iders+0.076
 footsteps+0.076
Neg logit contributions
c-0.082
bar-0.078
 named-0.075
 bank-0.070
 pouch-0.067
Token for
Token ID329
Feature activation-3.52e-02

Pos logit contributions
c+0.116
bar+0.113
 named+0.109
rob+0.105
 bank+0.101
Neg logit contributions
ires-0.078
olving-0.077
 footsteps-0.073
 accomplishments-0.073
 prayers-0.072
Token later
Token ID1568
Feature activation+4.30e-02

Pos logit contributions
c+0.056
 named+0.055
bar+0.054
 bank+0.049
ah+0.046
Neg logit contributions
ires-0.056
iders-0.054
olving-0.053
inner-0.052
 accomplishments-0.051
Token the
Token ID262
Feature activation-1.59e-02

Pos logit contributions
c+0.074
bar+0.072
 named+0.070
 bank+0.064
rob+0.062
Neg logit contributions
ires-0.069
olving-0.066
 accomplishments-0.064
 progress-0.064
 footsteps-0.063
Token apple
Token ID17180
Feature activation-1.61e-02

Pos logit contributions
c+0.024
bar+0.023
 named+0.022
 bank+0.020
ah+0.019
Neg logit contributions
ires-0.028
olving-0.027
 accomplishments-0.026
 footsteps-0.026
 prayers-0.026
Token in
Token ID287
Feature activation-2.30e-02

Pos logit contributions
c+0.026
bar+0.025
 named+0.024
 bank+0.022
ah+0.021
Neg logit contributions
ires-0.026
olving-0.025
 accomplishments-0.025
 footsteps-0.025
 prayers-0.024
Token his
Token ID465
Feature activation+2.86e-02

Pos logit contributions
c+0.040
bar+0.038
 named+0.036
rob+0.036
ah+0.034
Neg logit contributions
olving-0.032
 footsteps-0.032
ires-0.032
 progress-0.032
 accomplishments-0.031
Token little
Token ID1310
Feature activation-2.16e-03

Pos logit contributions
 prayers+0.048
ires+0.048
 footsteps+0.048
olving+0.047
 accomplishments+0.047
Neg logit contributions
bar-0.039
rob-0.039
c-0.038
 named-0.036
ah-0.036
Token pouch
Token ID36594
Feature activation-1.96e-01

Pos logit contributions
rob+0.003
bar+0.003
c+0.003
 named+0.003
ah+0.003
Neg logit contributions
 footsteps-0.003
 progress-0.003
 prayers-0.003
olving-0.003
 accomplishments-0.003
Token and
Token ID290
Feature activation+1.58e-03

Pos logit contributions
c+0.367
rob+0.352
bar+0.345
 named+0.343
ah+0.334
Neg logit contributions
olving-0.240
ires-0.239
 accomplishments-0.219
iring-0.216
ble-0.215
Token carried
Token ID5281
Feature activation-5.41e-02

Pos logit contributions
olving+0.003
 prayers+0.003
ires+0.003
 accomplishments+0.003
 footsteps+0.003
Neg logit contributions
c-0.002
bar-0.002
rob-0.002
 named-0.002
ah-0.002
Token it
Token ID340
Feature activation+3.62e-03

Pos logit contributions
c+0.086
bar+0.083
 named+0.079
 bank+0.072
rob+0.072
Neg logit contributions
ires-0.087
olving-0.084
 accomplishments-0.083
 footsteps-0.082
 progress-0.082
Token home
Token ID1363
Feature activation-9.84e-03

Pos logit contributions
ires+0.007
olving+0.007
 footsteps+0.007
 prayers+0.007
iders+0.007
Neg logit contributions
c-0.005
bar-0.005
 named-0.004
 bank-0.004
 pouch-0.004
Token.
Token ID13
Feature activation+6.58e-03

Pos logit contributions
c+0.018
bar+0.017
 named+0.016
 bank+0.015
ah+0.015
Neg logit contributions
ires-0.014
olving-0.014
 footsteps-0.013
 accomplishments-0.013
 prayers-0.013
Token "
Token ID366
Feature activation-2.50e-02

Pos logit contributions
c+0.014
bar+0.013
 named+0.013
 bank+0.012
rob+0.012
Neg logit contributions
ires-0.009
olving-0.009
 accomplishments-0.009
 footsteps-0.009
 prayers-0.008
TokenYou
Token ID1639
Feature activation+2.16e-02

Pos logit contributions
c+0.045
bar+0.043
 named+0.041
ah+0.038
rob+0.037
Neg logit contributions
ires-0.037
olving-0.036
 footsteps-0.035
 accomplishments-0.035
 prayers-0.035
Token can
Token ID460
Feature activation+4.50e-02

Pos logit contributions
ires+0.037
olving+0.036
 accomplishments+0.035
 footsteps+0.035
 prayers+0.034
Neg logit contributions
c-0.033
bar-0.031
 named-0.030
 bank-0.028
rob-0.027
Token have
Token ID423
Feature activation-2.85e-02

Pos logit contributions
ires+0.064
olving+0.062
 accomplishments+0.059
 footsteps+0.059
 prayers+0.058
Neg logit contributions
c-0.082
bar-0.078
 named-0.076
 bank-0.070
rob-0.070
Token this
Token ID428
Feature activation+1.79e-03

Pos logit contributions
c+0.054
bar+0.053
rob+0.052
ah+0.050
 named+0.049
Neg logit contributions
 accidents-0.035
 happen-0.033
 footsteps-0.033
 progress-0.032
 prayers-0.032
Token pouch
Token ID36594
Feature activation-1.95e-01

Pos logit contributions
ires+0.003
olving+0.003
 accomplishments+0.003
 footsteps+0.003
 prayers+0.003
Neg logit contributions
c-0.003
bar-0.003
 named-0.003
 bank-0.002
rob-0.002
Token full
Token ID1336
Feature activation-9.55e-02

Pos logit contributions
c+0.308
bar+0.295
 named+0.283
 bank+0.261
rob+0.258
Neg logit contributions
ires-0.316
olving-0.307
 accomplishments-0.297
 footsteps-0.295
iders-0.293
Token of
Token ID286
Feature activation+2.25e-02

Pos logit contributions
c+0.154
bar+0.147
 named+0.140
rob+0.133
 bank+0.131
Neg logit contributions
ires-0.153
olving-0.148
 accomplishments-0.143
 footsteps-0.142
 prayers-0.142
Token coins
Token ID10796
Feature activation-4.11e-02

Pos logit contributions
ires+0.029
olving+0.028
 accomplishments+0.027
 footsteps+0.027
 prayers+0.027
Neg logit contributions
c-0.043
bar-0.042
 named-0.040
ah-0.038
 bank-0.038
Token!"
Token ID2474
Feature activation-5.92e-02

Pos logit contributions
c+0.072
bar+0.069
 named+0.066
rob+0.064
 bank+0.062
Neg logit contributions
ires-0.059
olving-0.057
 accomplishments-0.054
iders-0.053
 prayers-0.053
Token
Token ID198
Feature activation-2.22e-03

Pos logit contributions
c+0.097
bar+0.093
 named+0.089
 bank+0.083
rob+0.081
Neg logit contributions
ires-0.093
olving-0.090
 accomplishments-0.088
 footsteps-0.088
 prayers-0.087
Token.
Token ID13
Feature activation+7.25e-03

Pos logit contributions
c+0.050
bar+0.048
 named+0.046
 bank+0.042
ah+0.040
Neg logit contributions
ires-0.052
 accomplishments-0.050
olving-0.050
 prayers-0.049
 footsteps-0.049
Token It
Token ID632
Feature activation+5.40e-03

Pos logit contributions
ires+0.012
olving+0.012
 accomplishments+0.012
iders+0.011
 progress+0.011
Neg logit contributions
c-0.011
bar-0.011
 named-0.011
 bank-0.009
 pouch-0.009
Token was
Token ID373
Feature activation-1.56e-02

Pos logit contributions
olving+0.007
ires+0.007
 footsteps+0.007
iders+0.007
 accidents+0.007
Neg logit contributions
bar-0.010
c-0.010
 named-0.009
rob-0.009
 bank-0.008
Token a
Token ID257
Feature activation+1.68e-02

Pos logit contributions
c+0.025
bar+0.024
 named+0.024
 bank+0.021
ah+0.021
Neg logit contributions
ires-0.025
 accomplishments-0.024
olving-0.024
inner-0.023
iders-0.023
Token small
Token ID1402
Feature activation-1.32e-02

Pos logit contributions
ires+0.026
olving+0.024
 accomplishments+0.023
iders+0.023
 footsteps+0.023
Neg logit contributions
c-0.029
bar-0.028
 named-0.028
 bank-0.026
ah-0.025
Token pouch
Token ID36594
Feature activation-1.95e-01

Pos logit contributions
c+0.022
bar+0.021
 named+0.020
rob+0.020
 bank+0.018
Neg logit contributions
olving-0.020
 footsteps-0.019
ires-0.019
 accomplishments-0.019
 progress-0.019
Token with
Token ID351
Feature activation-6.59e-02

Pos logit contributions
c+0.352
bar+0.330
rob+0.326
 named+0.315
 bank+0.306
Neg logit contributions
ires-0.262
olving-0.257
inner-0.247
iders-0.246
iring-0.243
Token a
Token ID257
Feature activation+1.64e-02

Pos logit contributions
c+0.120
bar+0.115
 named+0.111
rob+0.109
ah+0.105
Neg logit contributions
ires-0.089
 footsteps-0.087
olving-0.087
 progress-0.083
ps-0.083
Token shiny
Token ID22441
Feature activation+1.51e-02

Pos logit contributions
ires+0.022
olving+0.022
 footsteps+0.021
 accomplishments+0.021
 prayers+0.021
Neg logit contributions
c-0.030
bar-0.028
 named-0.027
rob-0.026
ah-0.025
Token penny
Token ID26369
Feature activation-8.57e-02

Pos logit contributions
ires+0.021
olving+0.020
 accomplishments+0.019
 footsteps+0.019
 progress+0.019
Neg logit contributions
c-0.028
bar-0.026
 named-0.025
rob-0.025
 bank-0.023
Token in
Token ID287
Feature activation-2.29e-02

Pos logit contributions
c+0.145
bar+0.138
 named+0.134
rob+0.125
 bank+0.125
Neg logit contributions
ires-0.126
olving-0.122
iders-0.117
inner-0.116
 accidents-0.115
Token crab
Token ID32202
Feature activation-2.22e-02

Pos logit contributions
c+0.032
bar+0.031
 named+0.029
 bank+0.027
rob+0.027
Neg logit contributions
ires-0.031
olving-0.029
 accomplishments-0.029
inner-0.028
 prayers-0.028
Token proudly
Token ID23017
Feature activation-2.21e-02

Pos logit contributions
c+0.029
bar+0.028
 named+0.026
rob+0.024
 bank+0.024
Neg logit contributions
ires-0.040
olving-0.040
 accomplishments-0.038
iders-0.038
 prayers-0.038
Token put
Token ID1234
Feature activation-4.23e-02

Pos logit contributions
c+0.029
bar+0.028
 named+0.026
 bank+0.024
rob+0.024
Neg logit contributions
ires-0.041
olving-0.041
 accomplishments-0.039
 footsteps-0.039
 prayers-0.039
Token in
Token ID287
Feature activation-1.72e-02

Pos logit contributions
bar+0.072
c+0.071
 named+0.067
rob+0.063
ah+0.063
Neg logit contributions
ires-0.060
olving-0.058
 accomplishments-0.055
ps-0.055
 progress-0.054
Token his
Token ID465
Feature activation+3.18e-02

Pos logit contributions
c+0.030
bar+0.029
 named+0.027
rob+0.026
ah+0.026
Neg logit contributions
ires-0.024
olving-0.024
 accomplishments-0.024
 footsteps-0.023
 progress-0.023
Token pouch
Token ID36594
Feature activation-1.94e-01

Pos logit contributions
ires+0.053
 accomplishments+0.051
olving+0.051
 prayers+0.051
 footsteps+0.050
Neg logit contributions
c-0.048
bar-0.047
 named-0.044
rob-0.041
ah-0.040
Token.
Token ID13
Feature activation+9.40e-03

Pos logit contributions
rob+0.395
c+0.391
 named+0.373
bar+0.370
ah+0.370
Neg logit contributions
ires-0.204
olving-0.197
iring-0.186
 accomplishments-0.182
ble-0.176
Token
Token ID220
Feature activation-8.14e-02

Pos logit contributions
ires+0.014
 prayers+0.012
olving+0.012
 footsteps+0.012
 accomplishments+0.012
Neg logit contributions
c-0.017
bar-0.016
 named-0.015
 bank-0.015
ah-0.015
Token
Token ID198
Feature activation+3.83e-03

Pos logit contributions
c+0.106
bar+0.099
 named+0.097
 bank+0.078
 pouch+0.077
Neg logit contributions
 accomplishments-0.155
 accidents-0.155
 footsteps-0.154
olving-0.154
 prayers-0.152
Token
Token ID198
Feature activation+4.08e-03

Pos logit contributions
ires+0.006
olving+0.006
 footsteps+0.006
 accomplishments+0.006
 prayers+0.006
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
 bank-0.005
rob-0.005
TokenThe
Token ID464
Feature activation-1.44e-02

Pos logit contributions
ires+0.005
olving+0.005
 accomplishments+0.005
 footsteps+0.005
iders+0.005
Neg logit contributions
c-0.008
bar-0.008
 named-0.007
 bank-0.007
rob-0.007
Token with
Token ID351
Feature activation-6.13e-02

Pos logit contributions
c+0.123
bar+0.120
 named+0.112
rob+0.107
 bank+0.106
Neg logit contributions
ires-0.103
olving-0.100
 footsteps-0.097
 accomplishments-0.096
iders-0.094
Token a
Token ID257
Feature activation+1.96e-02

Pos logit contributions
c+0.115
bar+0.110
 named+0.106
 bank+0.100
rob+0.099
Neg logit contributions
ires-0.082
olving-0.079
 footsteps-0.078
 accomplishments-0.075
 prayers-0.075
Token baby
Token ID5156
Feature activation-4.06e-02

Pos logit contributions
 footsteps+0.022
 prayers+0.022
olving+0.022
 progress+0.022
 words+0.021
Neg logit contributions
c-0.037
bar-0.036
rob-0.035
 named-0.034
bank-0.032
Token in
Token ID287
Feature activation-1.69e-02

Pos logit contributions
bar+0.067
c+0.066
rob+0.058
 bank+0.058
 named+0.058
Neg logit contributions
 footsteps-0.058
ires-0.057
 accidents-0.056
ps-0.055
olving-0.055
Token her
Token ID607
Feature activation+5.37e-02

Pos logit contributions
bar+0.029
c+0.028
 named+0.026
 bank+0.026
rob+0.026
Neg logit contributions
ires-0.024
 footsteps-0.024
olving-0.023
 prayers-0.023
 progress-0.022
Token pouch
Token ID36594
Feature activation-1.94e-01

Pos logit contributions
ires+0.075
 prayers+0.072
 footsteps+0.071
 name+0.069
 words+0.068
Neg logit contributions
bar-0.092
rob-0.090
ah-0.082
c-0.082
bank-0.079
Token.
Token ID13
Feature activation+7.54e-03

Pos logit contributions
rob+0.441
c+0.407
bar+0.401
ah+0.397
 bank+0.383
Neg logit contributions
olving-0.160
ires-0.158
ble-0.154
iring-0.153
ps-0.135
Token The
Token ID383
Feature activation-2.04e-02

Pos logit contributions
ires+0.013
olving+0.012
 accomplishments+0.012
 footsteps+0.012
iders+0.012
Neg logit contributions
c-0.012
bar-0.011
 named-0.011
 bank-0.010
ah-0.010
Token baby
Token ID5156
Feature activation-4.00e-02

Pos logit contributions
bar+0.038
c+0.038
 named+0.035
rob+0.033
ah+0.032
Neg logit contributions
ires-0.027
 footsteps-0.027
 progress-0.026
 prayers-0.026
ps-0.026
Token k
Token ID479
Feature activation-6.77e-02

Pos logit contributions
bar+0.063
c+0.061
rob+0.055
 bank+0.055
 named+0.055
Neg logit contributions
ires-0.059
 accidents-0.058
 footsteps-0.058
 prayers-0.057
olving-0.056
Tokenang
Token ID648
Feature activation-1.44e-01

Pos logit contributions
 bank+0.079
bar+0.077
bank+0.074
c+0.072
 named+0.070
Neg logit contributions
ires-0.127
iring-0.124
iders-0.122
 accidents-0.115
ble-0.114
Token the
Token ID262
Feature activation-1.54e-02

Pos logit contributions
ires+0.070
olving+0.067
 progress+0.067
ps+0.066
 footsteps+0.066
Neg logit contributions
c-0.104
bar-0.096
 named-0.094
rob-0.093
 bank-0.091
Token k
Token ID479
Feature activation-7.03e-02

Pos logit contributions
c+0.024
bar+0.024
 named+0.023
rob+0.022
ah+0.021
Neg logit contributions
 footsteps-0.023
 progress-0.023
ires-0.022
 prayers-0.022
olving-0.021
Tokenang
Token ID648
Feature activation-1.46e-01

Pos logit contributions
 bank+0.092
bank+0.086
 named+0.081
bar+0.078
 gir+0.077
Neg logit contributions
iring-0.114
aps-0.113
ires-0.113
iders-0.104
ymes-0.103
Tokenaroo
Token ID38049
Feature activation-7.24e-02

Pos logit contributions
c+0.231
bar+0.229
rob+0.224
 bank+0.217
 named+0.203
Neg logit contributions
ires-0.208
ble-0.203
iring-0.194
ps-0.193
iders-0.190
Token's
Token ID338
Feature activation-4.96e-02

Pos logit contributions
bar+0.089
c+0.085
rob+0.083
 named+0.076
ah+0.073
Neg logit contributions
olving-0.129
ires-0.129
 footsteps-0.127
 progress-0.124
 accomplishments-0.124
Token pouch
Token ID36594
Feature activation-1.92e-01

Pos logit contributions
c+0.082
bar+0.078
 named+0.076
rob+0.071
ah+0.069
Neg logit contributions
ires-0.077
olving-0.075
 footsteps-0.074
 prayers-0.073
 accomplishments-0.073
Token was
Token ID373
Feature activation-1.77e-02

Pos logit contributions
c+0.296
bar+0.281
 named+0.272
rob+0.268
ah+0.255
Neg logit contributions
ires-0.304
olving-0.299
 footsteps-0.283
 accomplishments-0.281
iders-0.281
Token a
Token ID257
Feature activation+1.78e-02

Pos logit contributions
c+0.029
bar+0.028
 named+0.027
 bank+0.025
ah+0.024
Neg logit contributions
ires-0.028
olving-0.027
 accomplishments-0.027
iders-0.026
 footsteps-0.026
Token surprise
Token ID5975
Feature activation+1.60e-02

Pos logit contributions
ires+0.026
olving+0.026
 accomplishments+0.025
 footsteps+0.025
 prayers+0.025
Neg logit contributions
c-0.031
bar-0.029
 named-0.028
 bank-0.026
rob-0.026
Token -
Token ID532
Feature activation+4.65e-02

Pos logit contributions
ires+0.024
olving+0.023
 accomplishments+0.023
 footsteps+0.022
iders+0.022
Neg logit contributions
c-0.027
bar-0.026
 named-0.026
 bank-0.024
ah-0.023
Token two
Token ID734
Feature activation-6.80e-02

Pos logit contributions
ires+0.080
olving+0.077
iders+0.077
 accomplishments+0.075
inner+0.073
Neg logit contributions
c-0.071
bar-0.068
 named-0.067
 bank-0.059
 pouch-0.058
Token in
Token ID287
Feature activation-1.86e-02

Pos logit contributions
ires+0.094
olving+0.089
 accomplishments+0.085
 footsteps+0.084
iders+0.084
Neg logit contributions
c-0.122
bar-0.118
 named-0.111
 bank-0.106
rob-0.104
Token his
Token ID465
Feature activation+3.24e-02

Pos logit contributions
c+0.034
bar+0.033
 named+0.031
 bank+0.030
ah+0.029
Neg logit contributions
ires-0.026
olving-0.025
 footsteps-0.024
 accomplishments-0.024
 prayers-0.024
Token mom
Token ID1995
Feature activation+1.31e-02

Pos logit contributions
ires+0.048
 footsteps+0.045
 prayers+0.045
olving+0.044
 progress+0.043
Neg logit contributions
bar-0.055
c-0.051
rob-0.050
ah-0.050
 named-0.048
Tokenmy
Token ID1820
Feature activation+9.29e-02

Pos logit contributions
ires+0.014
 shapes+0.013
iring+0.013
 accidents+0.013
olving+0.013
Neg logit contributions
rob-0.023
bar-0.023
ah-0.023
boat-0.020
 bank-0.020
Token's
Token ID338
Feature activation-4.73e-02

Pos logit contributions
ires+0.080
olving+0.079
iring+0.073
 accidents+0.073
 words+0.073
Neg logit contributions
bar-0.193
rob-0.191
ah-0.186
c-0.179
 named-0.166
Token pouch
Token ID36594
Feature activation-1.92e-01

Pos logit contributions
ah+0.097
bar+0.095
rob+0.093
c+0.089
 named+0.084
Neg logit contributions
 footsteps-0.054
ires-0.051
 prayers-0.050
olving-0.048
 progress-0.047
Token.
Token ID13
Feature activation+4.74e-03

Pos logit contributions
rob+0.426
bar+0.407
c+0.405
ah+0.403
 bank+0.372
Neg logit contributions
ires-0.185
iring-0.172
olving-0.160
ble-0.157
abies-0.152
Token He
Token ID679
Feature activation+4.40e-03

Pos logit contributions
ires+0.008
olving+0.008
 prayers+0.007
 footsteps+0.007
iring+0.007
Neg logit contributions
c-0.007
bar-0.007
rob-0.007
ah-0.006
 named-0.006
Token loved
Token ID6151
Feature activation+8.61e-02

Pos logit contributions
ires+0.005
 prayers+0.005
olving+0.005
 accomplishments+0.004
iders+0.004
Neg logit contributions
bar-0.009
c-0.008
rob-0.008
ah-0.007
 bank-0.007
Token to
Token ID284
Feature activation-1.15e-02

Pos logit contributions
ires+0.128
olving+0.125
 prayers+0.122
 accidents+0.122
 footsteps+0.119
Neg logit contributions
c-0.147
bar-0.144
 named-0.128
ah-0.126
rob-0.124
Token hop
Token ID1725
Feature activation+7.49e-03

Pos logit contributions
bar+0.022
c+0.022
rob+0.020
ah+0.020
 named+0.019
Neg logit contributions
 prayers-0.013
ires-0.013
 footsteps-0.013
olving-0.013
 accomplishments-0.013
Token out
Token ID503
Feature activation+3.30e-03

Pos logit contributions
c+0.083
bar+0.077
 named+0.076
 bank+0.071
rob+0.071
Neg logit contributions
ires-0.073
olving-0.071
 footsteps-0.069
 prayers-0.067
 accidents-0.067
Token of
Token ID286
Feature activation+1.93e-02

Pos logit contributions
ires+0.006
olving+0.006
 accomplishments+0.005
iders+0.005
inner+0.005
Neg logit contributions
c-0.005
bar-0.005
 named-0.005
 bank-0.004
ah-0.004
Token its
Token ID663
Feature activation-1.58e-02

Pos logit contributions
 footsteps+0.028
ires+0.027
olving+0.026
ps+0.026
 prayers+0.026
Neg logit contributions
c-0.035
bar-0.034
 named-0.031
ah-0.030
rob-0.030
Token mother
Token ID2802
Feature activation-2.26e-02

Pos logit contributions
c+0.023
rob+0.023
bar+0.022
ah+0.021
 named+0.021
Neg logit contributions
 footsteps-0.025
olving-0.025
ires-0.025
 prayers-0.025
ps-0.024
Token's
Token ID338
Feature activation-4.93e-02

Pos logit contributions
c+0.027
bar+0.027
 named+0.024
rob+0.024
ah+0.023
Neg logit contributions
 footsteps-0.042
ires-0.042
olving-0.042
 prayers-0.041
 progress-0.040
Token pouch
Token ID36594
Feature activation-1.91e-01

Pos logit contributions
c+0.078
bar+0.074
rob+0.073
 named+0.070
ah+0.070
Neg logit contributions
 footsteps-0.078
olving-0.076
 prayers-0.076
ires-0.074
 accomplishments-0.073
Token and
Token ID290
Feature activation+2.92e-03

Pos logit contributions
c+0.367
bar+0.351
rob+0.351
 named+0.339
ah+0.333
Neg logit contributions
olving-0.221
ires-0.220
ps-0.209
 footsteps-0.206
iring-0.202
Token cried
Token ID16896
Feature activation-7.23e-02

Pos logit contributions
 footsteps+0.005
 accidents+0.004
ps+0.004
 prayers+0.004
 words+0.004
Neg logit contributions
c-0.005
bar-0.004
ah-0.004
rob-0.004
bank-0.004
Token.
Token ID13
Feature activation+9.77e-03

Pos logit contributions
 named+0.102
c+0.101
bar+0.100
 bank+0.085
ah+0.082
Neg logit contributions
ires-0.133
inner-0.128
iders-0.127
olving-0.124
 accomplishments-0.123
Token
Token ID198
Feature activation+2.21e-03

Pos logit contributions
ires+0.015
 footsteps+0.014
olving+0.014
 prayers+0.014
 accomplishments+0.013
Neg logit contributions
c-0.017
bar-0.016
 named-0.015
rob-0.015
 bank-0.014
Token
Token ID198
Feature activation+2.62e-03

Pos logit contributions
ires+0.003
olving+0.003
 accomplishments+0.003
 footsteps+0.003
 prayers+0.003
Neg logit contributions
c-0.004
bar-0.004
 named-0.003
 bank-0.003
ah-0.003
Token clown
Token ID25573
Feature activation+7.78e-03

Pos logit contributions
ires+0.025
olving+0.025
 accomplishments+0.024
iders+0.024
inner+0.023
Neg logit contributions
c-0.025
bar-0.024
 named-0.023
 bank-0.021
rob-0.021
Tokens
Token ID82
Feature activation-4.22e-02

Pos logit contributions
ires+0.018
olving+0.018
 accomplishments+0.017
 prayers+0.017
 footsteps+0.017
Neg logit contributions
c-0.008
bar-0.007
 named-0.007
ah-0.006
 bank-0.006
Token juggling
Token ID48097
Feature activation-2.63e-02

Pos logit contributions
 named+0.058
c+0.056
bar+0.055
 bank+0.049
ah+0.047
Neg logit contributions
ires-0.077
iders-0.076
olving-0.075
 accomplishments-0.075
inner-0.075
Token and
Token ID290
Feature activation-6.56e-04

Pos logit contributions
c+0.044
bar+0.043
 named+0.041
 bank+0.038
rob+0.037
Neg logit contributions
ires-0.040
olving-0.039
 accomplishments-0.038
 footsteps-0.038
 prayers-0.037
Token ac
Token ID936
Feature activation-2.24e-02

Pos logit contributions
c+0.001
bar+0.001
 named+0.001
 pouch+0.001
 bank+0.001
Neg logit contributions
 footsteps-0.001
ires-0.001
olving-0.001
 prayers-0.001
 progress-0.001
Tokenrob
Token ID22609
Feature activation-1.90e-01

Pos logit contributions
c+0.012
bar+0.012
 named+0.011
 bank+0.008
 pouch+0.006
Neg logit contributions
ires-0.057
iders-0.056
olving-0.056
inner-0.056
 accomplishments-0.055
Tokenats
Token ID1381
Feature activation-2.61e-02

Pos logit contributions
bar+0.302
c+0.291
 named+0.278
 bank+0.272
 pouch+0.264
Neg logit contributions
ires-0.322
 accomplishments-0.293
olving-0.292
ps-0.286
iders-0.278
Token doing
Token ID1804
Feature activation+4.88e-02

Pos logit contributions
c+0.043
bar+0.041
 named+0.040
 bank+0.037
ah+0.036
Neg logit contributions
ires-0.042
olving-0.040
 accomplishments-0.039
 prayers-0.039
 footsteps-0.039
Token flips
Token ID45971
Feature activation+1.79e-02

Pos logit contributions
ires+0.067
olving+0.065
 accomplishments+0.062
iders+0.062
 footsteps+0.062
Neg logit contributions
c-0.090
bar-0.086
 named-0.084
 bank-0.078
ah-0.076
Token.
Token ID13
Feature activation+2.81e-03

Pos logit contributions
ires+0.031
olving+0.030
 accomplishments+0.030
 prayers+0.030
iders+0.029
Neg logit contributions
c-0.027
bar-0.026
 named-0.025
ah-0.023
 bank-0.022
Token But
Token ID887
Feature activation-3.00e-02

Pos logit contributions
ires+0.005
 footsteps+0.004
olving+0.004
 prayers+0.004
 accomplishments+0.004
Neg logit contributions
c-0.004
bar-0.004
 named-0.004
rob-0.004
ah-0.004
Token was
Token ID373
Feature activation-1.36e-02

Pos logit contributions
ires+0.033
olving+0.031
inner+0.029
 accomplishments+0.029
ps+0.029
Neg logit contributions
bar-0.046
c-0.043
 bank-0.040
rob-0.039
 named-0.039
Token very
Token ID845
Feature activation-4.43e-02

Pos logit contributions
bar+0.025
c+0.024
 bank+0.023
rob+0.023
ah+0.022
Neg logit contributions
ires-0.017
iring-0.016
ble-0.015
 name-0.015
 footsteps-0.015
Token comfortable
Token ID6792
Feature activation-1.81e-02

Pos logit contributions
c+0.090
bar+0.087
 named+0.081
 bank+0.079
rob+0.078
Neg logit contributions
ires-0.055
olving-0.050
 accomplishments-0.048
 prayers-0.047
 footsteps-0.047
Token in
Token ID287
Feature activation-1.84e-02

Pos logit contributions
c+0.036
bar+0.036
ah+0.032
rob+0.032
 named+0.032
Neg logit contributions
ires-0.020
olving-0.020
iring-0.019
 accomplishments-0.019
iders-0.019
Token his
Token ID465
Feature activation+3.29e-02

Pos logit contributions
c+0.031
bar+0.031
 named+0.028
ah+0.027
 bank+0.027
Neg logit contributions
ires-0.027
 footsteps-0.027
olving-0.026
 prayers-0.026
 progress-0.025
Token pouch
Token ID36594
Feature activation-1.90e-01

Pos logit contributions
ires+0.053
 prayers+0.051
olving+0.050
 footsteps+0.050
 accomplishments+0.049
Neg logit contributions
bar-0.051
c-0.049
 named-0.046
ah-0.045
rob-0.045
Token,
Token ID11
Feature activation-6.41e-03

Pos logit contributions
rob+0.395
c+0.381
bar+0.380
ah+0.374
 named+0.344
Neg logit contributions
ires-0.187
iring-0.180
olving-0.175
ble-0.168
abies-0.155
Token where
Token ID810
Feature activation+3.88e-02

Pos logit contributions
c+0.011
bar+0.010
rob+0.009
 bank+0.009
ah+0.009
Neg logit contributions
ires-0.010
 accidents-0.009
olving-0.009
 footsteps-0.009
 accomplishments-0.009
Token he
Token ID339
Feature activation-2.49e-02

Pos logit contributions
ires+0.064
olving+0.063
 prayers+0.062
 accidents+0.061
 footsteps+0.061
Neg logit contributions
c-0.060
bar-0.056
 named-0.053
rob-0.051
 bank-0.050
Token slept
Token ID21256
Feature activation+5.71e-02

Pos logit contributions
c+0.033
bar+0.032
 named+0.030
 bank+0.027
rob+0.026
Neg logit contributions
ires-0.047
olving-0.046
 accomplishments-0.044
 footsteps-0.044
 prayers-0.044
Token and
Token ID290
Feature activation+1.61e-04

Pos logit contributions
ires+0.081
olving+0.078
 accomplishments+0.075
 footsteps+0.074
 prayers+0.074
Neg logit contributions
c-0.104
bar-0.100
 named-0.096
 bank-0.089
ah-0.088
Token with
Token ID351
Feature activation-6.14e-02

Pos logit contributions
bar+0.131
c+0.130
rob+0.123
ah+0.118
 bank+0.117
Neg logit contributions
ires-0.078
olving-0.073
 footsteps-0.071
iders-0.070
ble-0.069
Token a
Token ID257
Feature activation+1.91e-02

Pos logit contributions
c+0.120
bar+0.114
 named+0.110
rob+0.108
 bank+0.106
Neg logit contributions
ires-0.076
 footsteps-0.075
olving-0.070
 words-0.069
 progress-0.069
Token baby
Token ID5156
Feature activation-3.99e-02

Pos logit contributions
ble+0.022
 name+0.021
 words+0.021
 footsteps+0.021
 prayers+0.021
Neg logit contributions
c-0.036
bar-0.035
rob-0.034
 named-0.033
bank-0.031
Token in
Token ID287
Feature activation-1.67e-02

Pos logit contributions
bar+0.068
c+0.067
rob+0.060
 bank+0.060
 named+0.060
Neg logit contributions
 footsteps-0.054
ires-0.053
ps-0.052
 accidents-0.052
olving-0.050
Token her
Token ID607
Feature activation+5.49e-02

Pos logit contributions
bar+0.030
c+0.028
rob+0.027
 named+0.027
 bank+0.027
Neg logit contributions
ires-0.023
 footsteps-0.022
 words-0.022
ps-0.021
olving-0.021
Token pouch
Token ID36594
Feature activation-1.89e-01

Pos logit contributions
ires+0.070
 name+0.067
 footsteps+0.065
 prayers+0.063
 words+0.063
Neg logit contributions
rob-0.101
bar-0.099
ah-0.092
bank-0.090
c-0.086
Token.
Token ID13
Feature activation+1.90e-03

Pos logit contributions
rob+0.458
c+0.420
bar+0.410
ah+0.410
 bank+0.397
Neg logit contributions
ble-0.146
ires-0.137
iring-0.135
olving-0.124
ps-0.116
Token They
Token ID1119
Feature activation-3.54e-02

Pos logit contributions
ires+0.002
 footsteps+0.002
 prayers+0.002
inner+0.002
 words+0.002
Neg logit contributions
bar-0.004
c-0.004
 named-0.003
rob-0.003
ah-0.003
Token wanted
Token ID2227
Feature activation+2.28e-02

Pos logit contributions
c+0.054
bar+0.052
rob+0.049
 bank+0.042
bank+0.042
Neg logit contributions
ires-0.057
 footsteps-0.056
 prayers-0.054
 words-0.053
olving-0.053
Token to
Token ID284
Feature activation-9.52e-03

Pos logit contributions
 footsteps+0.033
ires+0.033
 prayers+0.032
 accidents+0.032
olving+0.031
Neg logit contributions
c-0.039
bar-0.038
 named-0.035
rob-0.035
ah-0.033
Token pet
Token ID4273
Feature activation-1.69e-02

Pos logit contributions
c+0.018
bar+0.018
rob+0.017
 named+0.016
ah+0.016
Neg logit contributions
 footsteps-0.011
ires-0.011
 happen-0.011
 progress-0.011
olving-0.011
Token her
Token ID607
Feature activation+6.06e-02

Pos logit contributions
c+0.061
bar+0.060
 named+0.057
 bank+0.054
bank+0.053
Neg logit contributions
ires-0.051
ps-0.048
 footsteps-0.047
olving-0.047
 prayers-0.046
Token doll
Token ID3654
Feature activation-3.73e-02

Pos logit contributions
ires+0.085
olving+0.083
iders+0.080
 accomplishments+0.079
inner+0.078
Neg logit contributions
c-0.115
bar-0.108
 named-0.107
 bank-0.098
 pouch-0.097
Token next
Token ID1306
Feature activation+7.79e-02

Pos logit contributions
c+0.059
bar+0.054
 named+0.052
 bank+0.047
 pouch+0.046
Neg logit contributions
ires-0.069
 accomplishments-0.065
olving-0.065
 progress-0.064
 prayers-0.064
Token to
Token ID284
Feature activation-7.46e-03

Pos logit contributions
ires+0.127
olving+0.124
 accomplishments+0.121
 prayers+0.120
 footsteps+0.120
Neg logit contributions
c-0.124
bar-0.119
 named-0.114
rob-0.107
 bank-0.105
Token the
Token ID262
Feature activation-5.85e-03

Pos logit contributions
 named+0.010
c+0.009
bar+0.009
 bank+0.008
ah+0.008
Neg logit contributions
ires-0.014
olving-0.014
iders-0.014
inner-0.014
 accomplishments-0.013
Token pouch
Token ID36594
Feature activation-1.88e-01

Pos logit contributions
c+0.008
bar+0.008
 named+0.008
 bank+0.008
 pouch+0.007
Neg logit contributions
ires-0.011
olving-0.010
iders-0.010
 accomplishments-0.010
inner-0.010
Token and
Token ID290
Feature activation+1.18e-02

Pos logit contributions
c+0.374
rob+0.374
bar+0.360
ah+0.348
 named+0.343
Neg logit contributions
ires-0.209
olving-0.202
iring-0.186
 footsteps-0.186
ble-0.184
Token reached
Token ID4251
Feature activation-3.38e-02

Pos logit contributions
ires+0.020
 prayers+0.020
 footsteps+0.019
olving+0.019
 accidents+0.019
Neg logit contributions
c-0.017
bar-0.017
rob-0.015
ah-0.015
 named-0.015
Token out
Token ID503
Feature activation+8.73e-03

Pos logit contributions
c+0.055
bar+0.054
 named+0.050
rob+0.049
 bank+0.047
Neg logit contributions
ires-0.055
olving-0.051
 footsteps-0.051
 accomplishments-0.050
 prayers-0.050
Token her
Token ID607
Feature activation+5.78e-02

Pos logit contributions
ires+0.015
olving+0.015
iders+0.014
inner+0.014
 accomplishments+0.014
Neg logit contributions
c-0.013
 named-0.013
bar-0.013
ah-0.011
 bank-0.011
Token hand
Token ID1021
Feature activation-5.51e-02

Pos logit contributions
ires+0.099
olving+0.097
 accomplishments+0.094
 footsteps+0.094
 prayers+0.093
Neg logit contributions
c-0.087
bar-0.084
 named-0.080
 bank-0.073
rob-0.072
Token his
Token ID465
Feature activation+3.07e-02

Pos logit contributions
c+0.049
bar+0.046
 named+0.044
 bank+0.041
ah+0.039
Neg logit contributions
ires-0.058
olving-0.057
iders-0.055
 accomplishments-0.055
 footsteps-0.055
Token wings
Token ID12098
Feature activation-2.03e-02

Pos logit contributions
inner+0.062
iders+0.061
ires+0.061
olving+0.058
 footsteps+0.058
Neg logit contributions
c-0.041
bar-0.035
 named-0.033
 pouch-0.033
 bank-0.032
Token after
Token ID706
Feature activation+1.55e-02

Pos logit contributions
c+0.034
bar+0.033
 named+0.031
 bank+0.029
ah+0.028
Neg logit contributions
ires-0.032
olving-0.031
 footsteps-0.030
 accomplishments-0.030
iders-0.030
Token playing
Token ID2712
Feature activation+9.97e-02

Pos logit contributions
ires+0.029
iders+0.028
olving+0.028
 footsteps+0.027
 prayers+0.027
Neg logit contributions
bar-0.020
c-0.020
 named-0.019
 bank-0.017
bank-0.016
Token.
Token ID13
Feature activation+1.40e-02

Pos logit contributions
ires+0.162
olving+0.152
 prayers+0.152
 accomplishments+0.148
inner+0.147
Neg logit contributions
c-0.166
 named-0.157
bar-0.154
 bank-0.143
rob-0.132
Token<|endoftext|>
Token ID50256
Feature activation+1.05e-01

Pos logit contributions
ires+0.016
 prayers+0.015
olving+0.015
 accomplishments+0.014
 footsteps+0.014
Neg logit contributions
bar-0.028
c-0.028
 bank-0.027
 named-0.025
rob-0.025
TokenOnce
Token ID7454
Feature activation+3.30e-02

Pos logit contributions
ires+0.190
olving+0.184
 accomplishments+0.184
 prayers+0.180
 footsteps+0.179
Neg logit contributions
c-0.157
 named-0.145
bar-0.137
rob-0.127
 bank-0.123
Token upon
Token ID2402
Feature activation+1.15e-01

Pos logit contributions
ires+0.034
olving+0.032
 accomplishments+0.030
 footsteps+0.029
 prayers+0.029
Neg logit contributions
c-0.072
bar-0.071
 named-0.068
 bank-0.066
rob-0.065
Token a
Token ID257
Feature activation+1.80e-02

Pos logit contributions
olving+0.233
ires+0.233
 accomplishments+0.224
iders+0.224
 prayers+0.220
Neg logit contributions
c-0.150
 named-0.146
bar-0.115
 one-0.112
ah-0.109
Token time
Token ID640
Feature activation+4.06e-02

Pos logit contributions
ires+0.027
olving+0.026
 footsteps+0.025
 accomplishments+0.025
 prayers+0.025
Neg logit contributions
c-0.031
bar-0.029
 named-0.029
ah-0.027
 bank-0.026
Token,
Token ID11
Feature activation-7.34e-03

Pos logit contributions
ires+0.086
 prayers+0.083
 progress+0.083
 accomplishments+0.083
 footsteps+0.082
Neg logit contributions
c-0.046
 named-0.045
bar-0.042
ah-0.035
rob-0.031
Token to
Token ID284
Feature activation-1.52e-02

Pos logit contributions
c+0.142
bar+0.137
 named+0.136
 bank+0.121
ah+0.115
Neg logit contributions
ires-0.172
olving-0.167
iders-0.163
 accomplishments-0.163
inner-0.161
Token Lily
Token ID20037
Feature activation+8.14e-03

Pos logit contributions
c+0.024
bar+0.023
 named+0.023
 bank+0.021
ah+0.020
Neg logit contributions
ires-0.025
olving-0.024
iders-0.024
 accomplishments-0.023
inner-0.023
Token that
Token ID326
Feature activation-3.07e-02

Pos logit contributions
ires+0.014
olving+0.013
iders+0.013
inner+0.013
 accomplishments+0.013
Neg logit contributions
c-0.013
 named-0.012
bar-0.012
 bank-0.011
ah-0.010
Token it
Token ID340
Feature activation+9.26e-03

Pos logit contributions
c+0.045
bar+0.043
 named+0.041
 bank+0.038
rob+0.037
Neg logit contributions
ires-0.054
olving-0.052
 accomplishments-0.051
 footsteps-0.051
 prayers-0.050
Token's
Token ID338
Feature activation-4.73e-02

Pos logit contributions
ires+0.018
 accomplishments+0.017
olving+0.017
 footsteps+0.016
inner+0.016
Neg logit contributions
c-0.013
 named-0.012
bar-0.012
 bank-0.011
ah-0.010
Token okay
Token ID8788
Feature activation+9.60e-02

Pos logit contributions
c+0.080
 named+0.079
bar+0.076
 bank+0.070
 pouch+0.069
Neg logit contributions
ires-0.073
iders-0.069
inner-0.069
 accomplishments-0.067
 footsteps-0.067
Token if
Token ID611
Feature activation+2.70e-02

Pos logit contributions
ires+0.207
inner+0.202
 progress+0.197
ieve+0.197
 accomplishments+0.196
Neg logit contributions
 named-0.111
c-0.108
bar-0.090
ah-0.077
 one-0.077
Token things
Token ID1243
Feature activation+1.08e-01

Pos logit contributions
ires+0.058
iders+0.056
inner+0.056
olving+0.056
 footsteps+0.054
Neg logit contributions
 named-0.026
c-0.026
bar-0.025
 bank-0.021
bank-0.018
Token get
Token ID651
Feature activation+7.30e-03

Pos logit contributions
ires+0.183
 footsteps+0.178
iders+0.174
olving+0.169
 accomplishments+0.167
Neg logit contributions
c-0.157
 named-0.156
bar-0.150
 bank-0.144
 brought-0.131
Token broken
Token ID5445
Feature activation-3.40e-03

Pos logit contributions
ires+0.012
iders+0.012
olving+0.012
inner+0.011
 accomplishments+0.011
Neg logit contributions
c-0.012
bar-0.011
 named-0.011
 bank-0.010
 pouch-0.009
Token sometimes
Token ID3360
Feature activation+1.71e-02

Pos logit contributions
c+0.005
bar+0.005
 named+0.004
 bank+0.004
bank+0.003
Neg logit contributions
ires-0.006
inner-0.006
iders-0.006
 prayers-0.006
 footsteps-0.006
Token but
Token ID475
Feature activation-4.21e-02

Pos logit contributions
c+0.005
bar+0.005
rob+0.005
 named+0.005
 bank+0.005
Neg logit contributions
ires-0.005
 footsteps-0.005
olving-0.005
 accidents-0.005
 prayers-0.005
Token he
Token ID339
Feature activation-2.28e-02

Pos logit contributions
c+0.066
bar+0.063
 named+0.059
 bank+0.056
rob+0.055
Neg logit contributions
ires-0.071
olving-0.068
 footsteps-0.066
 accomplishments-0.066
 prayers-0.065
Token likes
Token ID7832
Feature activation+5.41e-02

Pos logit contributions
 named+0.037
c+0.036
 bank+0.032
bar+0.032
ah+0.031
Neg logit contributions
olving-0.037
 accomplishments-0.036
 footsteps-0.036
ires-0.036
inner-0.035
Token to
Token ID284
Feature activation-1.14e-02

Pos logit contributions
ires+0.092
olving+0.090
 accomplishments+0.088
iders+0.087
 footsteps+0.086
Neg logit contributions
c-0.082
bar-0.078
 named-0.077
 bank-0.069
ah-0.067
Token chase
Token ID15505
Feature activation-1.24e-02

Pos logit contributions
c+0.021
bar+0.020
 named+0.019
rob+0.018
 bank+0.017
Neg logit contributions
ires-0.016
olving-0.016
 footsteps-0.015
 accomplishments-0.015
 prayers-0.015
Token things
Token ID1243
Feature activation+1.05e-01

Pos logit contributions
bar+0.022
c+0.022
 named+0.020
rob+0.020
 bank+0.019
Neg logit contributions
ires-0.017
 footsteps-0.016
 accidents-0.016
 progress-0.016
olving-0.016
Token.
Token ID13
Feature activation+1.35e-02

Pos logit contributions
ires+0.144
olving+0.139
 accomplishments+0.134
 footsteps+0.133
iders+0.132
Neg logit contributions
c-0.195
bar-0.188
 named-0.182
 bank-0.169
rob-0.166
Token He
Token ID679
Feature activation+8.89e-03

Pos logit contributions
ires+0.020
 footsteps+0.019
 prayers+0.018
olving+0.017
 progress+0.017
Neg logit contributions
c-0.024
bar-0.024
rob-0.022
 named-0.022
 bank-0.022
Token sees
Token ID7224
Feature activation+3.26e-02

Pos logit contributions
ires+0.013
olving+0.012
 accomplishments+0.012
 footsteps+0.012
 prayers+0.012
Neg logit contributions
c-0.016
bar-0.015
 named-0.015
 bank-0.014
rob-0.013
Token the
Token ID262
Feature activation-1.18e-02

Pos logit contributions
ires+0.053
olving+0.052
 accomplishments+0.050
iders+0.049
 prayers+0.049
Neg logit contributions
c-0.052
bar-0.050
 named-0.049
 bank-0.044
rob-0.043
Token bright
Token ID6016
Feature activation+1.17e-02

Pos logit contributions
c+0.019
bar+0.018
 named+0.017
 bank+0.016
ah+0.015
Neg logit contributions
ires-0.019
olving-0.018
iders-0.018
 accomplishments-0.018
 prayers-0.018
Token.
Token ID13
Feature activation+4.55e-03

Pos logit contributions
c+0.022
bar+0.021
 named+0.020
 bank+0.019
rob+0.019
Neg logit contributions
ires-0.016
olving-0.016
 accomplishments-0.015
 footsteps-0.015
 prayers-0.015
Token He
Token ID679
Feature activation+6.83e-04

Pos logit contributions
ires+0.008
olving+0.008
 accomplishments+0.008
iders+0.008
 footsteps+0.008
Neg logit contributions
c-0.006
bar-0.006
 named-0.006
 bank-0.005
ah-0.005
Token and
Token ID290
Feature activation+1.47e-04

Pos logit contributions
ires+0.001
olving+0.001
 prayers+0.001
 accomplishments+0.001
 footsteps+0.001
Neg logit contributions
c-0.001
bar-0.001
 named-0.001
rob-0.001
ah-0.001
Token his
Token ID465
Feature activation+3.09e-02

Pos logit contributions
ires+0.000
 footsteps+0.000
olving+0.000
 prayers+0.000
 accomplishments+0.000
Neg logit contributions
c-0.000
bar-0.000
 named-0.000
rob-0.000
 bank-0.000
Token mom
Token ID1995
Feature activation+8.35e-03

Pos logit contributions
ires+0.045
olving+0.043
iders+0.043
inner+0.041
iring+0.040
Neg logit contributions
c-0.054
 named-0.053
bar-0.052
 bank-0.050
 pouch-0.048
Tokenmy
Token ID1820
Feature activation+9.13e-02

Pos logit contributions
olving+0.015
ires+0.014
 footsteps+0.014
inner+0.014
 accomplishments+0.014
Neg logit contributions
c-0.011
bar-0.010
 named-0.010
rob-0.010
 bank-0.010
Token spent
Token ID3377
Feature activation+4.50e-03

Pos logit contributions
olving+0.169
ires+0.168
 footsteps+0.163
 accomplishments+0.163
 prayers+0.162
Neg logit contributions
c-0.118
bar-0.110
 named-0.103
rob-0.095
 bank-0.093
Token a
Token ID257
Feature activation+1.94e-02

Pos logit contributions
 accomplishments+0.006
 progress+0.006
 footsteps+0.006
ires+0.006
olving+0.006
Neg logit contributions
bar-0.009
c-0.008
ah-0.007
 named-0.007
 pouch-0.007
Token few
Token ID1178
Feature activation-9.05e-02

Pos logit contributions
ires+0.029
 accomplishments+0.028
olving+0.028
inner+0.028
 prayers+0.027
Neg logit contributions
c-0.033
bar-0.032
 named-0.030
 bank-0.028
rob-0.027
Token hours
Token ID2250
Feature activation+5.29e-02

Pos logit contributions
c+0.143
bar+0.140
 named+0.131
 bank+0.121
ah+0.119
Neg logit contributions
ires-0.148
olving-0.143
 accomplishments-0.142
 footsteps-0.140
 progress-0.138
Token playing
Token ID2712
Feature activation+9.85e-02

Pos logit contributions
olving+0.070
ires+0.067
 accomplishments+0.067
 progress+0.063
 footsteps+0.063
Neg logit contributions
c-0.097
bar-0.092
rob-0.087
ah-0.085
 named-0.085
Token do
Token ID466
Feature activation+4.60e-02

Pos logit contributions
c+0.049
 named+0.048
bar+0.046
 bank+0.044
ah+0.042
Neg logit contributions
ires-0.049
olving-0.047
iders-0.046
 accomplishments-0.045
 footsteps-0.045
Token not
Token ID407
Feature activation+4.83e-02

Pos logit contributions
ires+0.056
olving+0.055
 footsteps+0.054
iders+0.052
 prayers+0.052
Neg logit contributions
c-0.091
 named-0.087
bar-0.086
 bank-0.079
ah-0.078
Token complain
Token ID13121
Feature activation-3.96e-02

Pos logit contributions
 footsteps+0.057
ires+0.055
olving+0.055
 prayers+0.054
 accomplishments+0.054
Neg logit contributions
c-0.096
bar-0.094
rob-0.088
 named-0.084
 bank-0.082
Token anymore
Token ID7471
Feature activation+6.99e-02

Pos logit contributions
 named+0.051
c+0.046
 one+0.044
bar+0.042
 bank+0.041
Neg logit contributions
iders-0.071
inner-0.071
ires-0.069
 accomplishments-0.069
olving-0.068
Token.
Token ID13
Feature activation+1.87e-02

Pos logit contributions
ires+0.130
inner+0.125
olving+0.123
 progress+0.119
iders+0.119
Neg logit contributions
 named-0.100
c-0.098
bar-0.085
 bank-0.080
ah-0.078
Token<|endoftext|>
Token ID50256
Feature activation+1.14e-01

Pos logit contributions
olving+0.035
ires+0.035
 accomplishments+0.035
iders+0.034
inner+0.034
Neg logit contributions
c-0.024
 named-0.023
bar-0.022
 bank-0.020
 pouch-0.019
TokenL
Token ID43
Feature activation-7.20e-03

Pos logit contributions
 accomplishments+0.205
ires+0.202
olving+0.202
 prayers+0.199
 footsteps+0.196
Neg logit contributions
c-0.173
 named-0.158
bar-0.146
rob-0.143
 pouch-0.131
Tokenily
Token ID813
Feature activation+2.55e-02

Pos logit contributions
c+0.014
bar+0.014
 named+0.013
 bank+0.013
rob+0.012
Neg logit contributions
ires-0.009
inner-0.008
 footsteps-0.008
ps-0.008
olving-0.008
Token and
Token ID290
Feature activation+6.82e-03

Pos logit contributions
ires+0.040
olving+0.039
 accomplishments+0.039
 footsteps+0.038
iders+0.038
Neg logit contributions
c-0.043
 named-0.040
bar-0.039
 bank-0.036
ah-0.035
Token Ben
Token ID3932
Feature activation+1.95e-02

Pos logit contributions
ires+0.008
 footsteps+0.008
 prayers+0.008
olving+0.008
 accidents+0.008
Neg logit contributions
c-0.014
bar-0.013
rob-0.012
 bank-0.012
ah-0.012
Token were
Token ID547
Feature activation-1.45e-03

Pos logit contributions
ires+0.044
iders+0.043
olving+0.043
 accomplishments+0.043
iring+0.043
Neg logit contributions
 named-0.021
c-0.020
 bank-0.016
bar-0.016
ah-0.015
Token her
Token ID607
Feature activation+5.43e-02

Pos logit contributions
c+0.043
 named+0.042
bar+0.041
 bank+0.038
rob+0.036
Neg logit contributions
ires-0.041
olving-0.039
iders-0.038
inner-0.038
 accomplishments-0.037
Token.
Token ID13
Feature activation+6.52e-03

Pos logit contributions
ires+0.103
iders+0.100
inner+0.094
iring+0.091
olving+0.090
Neg logit contributions
c-0.080
 named-0.078
bar-0.073
 bank-0.071
 pouch-0.065
Token Lily
Token ID20037
Feature activation+8.16e-03

Pos logit contributions
ires+0.013
olving+0.013
 prayers+0.012
 footsteps+0.012
 accomplishments+0.012
Neg logit contributions
c-0.008
bar-0.008
 named-0.007
ah-0.007
rob-0.007
Token was
Token ID373
Feature activation-9.48e-03

Pos logit contributions
ires+0.013
olving+0.013
 accomplishments+0.013
 prayers+0.012
 footsteps+0.012
Neg logit contributions
c-0.013
bar-0.012
 named-0.012
 bank-0.011
rob-0.011
Token happy
Token ID3772
Feature activation+5.06e-02

Pos logit contributions
c+0.013
bar+0.013
rob+0.012
 named+0.012
 bank+0.011
Neg logit contributions
ires-0.017
olving-0.016
 footsteps-0.016
 prayers-0.016
 accomplishments-0.016
Token and
Token ID290
Feature activation+5.19e-03

Pos logit contributions
ires+0.095
inner+0.091
olving+0.091
iders+0.091
ps+0.087
Neg logit contributions
 named-0.069
c-0.068
bar-0.064
 bank-0.056
ah-0.054
Token fell
Token ID3214
Feature activation-4.36e-02

Pos logit contributions
ires+0.008
 prayers+0.008
 accidents+0.008
olving+0.008
 accomplishments+0.008
Neg logit contributions
c-0.009
bar-0.008
ah-0.008
rob-0.007
 bank-0.007
Token asleep
Token ID16039
Feature activation+7.94e-02

Pos logit contributions
c+0.081
bar+0.080
 named+0.076
 bank+0.071
 pouch+0.068
Neg logit contributions
ires-0.063
iders-0.058
olving-0.058
 accomplishments-0.057
 prayers-0.056
Token with
Token ID351
Feature activation-6.06e-02

Pos logit contributions
olving+0.107
ires+0.106
 accomplishments+0.105
 footsteps+0.104
 progress+0.101
Neg logit contributions
c-0.145
bar-0.141
 named-0.128
ah-0.125
rob-0.122
Token her
Token ID607
Feature activation+5.45e-02

Pos logit contributions
c+0.110
bar+0.106
 named+0.103
 bank+0.096
rob+0.094
Neg logit contributions
ires-0.085
olving-0.082
 accomplishments-0.079
 footsteps-0.079
 prayers-0.078
Token duck
Token ID22045
Feature activation-8.83e-02

Pos logit contributions
iders+0.085
ires+0.083
inner+0.079
olving+0.079
 footsteps+0.074
Neg logit contributions
c-0.095
 named-0.093
bar-0.088
 pouch-0.083
 bank-0.083
Token much
Token ID881
Feature activation-1.18e-03

Pos logit contributions
ires+0.103
olving+0.100
 footsteps+0.098
iders+0.096
 accomplishments+0.096
Neg logit contributions
c-0.091
 named-0.087
bar-0.086
 bank-0.076
ah-0.075
Token as
Token ID355
Feature activation+6.00e-02

Pos logit contributions
 named+0.002
c+0.002
bar+0.002
 bank+0.001
rob+0.001
Neg logit contributions
olving-0.002
ires-0.002
iders-0.002
iring-0.002
 footsteps-0.002
Token she
Token ID673
Feature activation-3.85e-02

Pos logit contributions
ires+0.103
olving+0.099
 footsteps+0.097
iders+0.097
 accomplishments+0.096
Neg logit contributions
c-0.090
bar-0.086
 named-0.085
 bank-0.075
ah-0.073
Token wanted
Token ID2227
Feature activation+1.75e-02

Pos logit contributions
c+0.049
 named+0.044
bar+0.043
 bank+0.038
ah+0.037
Neg logit contributions
ires-0.077
olving-0.075
 accomplishments-0.073
 footsteps-0.073
iders-0.072
Token,
Token ID11
Feature activation-6.03e-03

Pos logit contributions
ires+0.031
olving+0.030
iders+0.030
 accomplishments+0.030
inner+0.029
Neg logit contributions
c-0.026
bar-0.024
 named-0.024
 bank-0.021
ah-0.020
Token as
Token ID355
Feature activation+5.66e-02

Pos logit contributions
c+0.009
bar+0.008
 named+0.008
rob+0.008
 bank+0.007
Neg logit contributions
ires-0.010
olving-0.010
 footsteps-0.010
 prayers-0.010
 accomplishments-0.010
Token long
Token ID890
Feature activation-5.74e-02

Pos logit contributions
ires+0.085
olving+0.083
 accomplishments+0.081
 prayers+0.080
 footsteps+0.080
Neg logit contributions
c-0.096
bar-0.092
 named-0.087
 bank-0.084
rob-0.082
Token as
Token ID355
Feature activation+5.56e-02

Pos logit contributions
c+0.116
bar+0.111
 named+0.105
 bank+0.101
rob+0.100
Neg logit contributions
ires-0.068
olving-0.066
 accomplishments-0.064
 footsteps-0.064
 prayers-0.062
Token she
Token ID673
Feature activation-4.20e-02

Pos logit contributions
ires+0.097
olving+0.093
 accomplishments+0.090
iders+0.090
 footsteps+0.090
Neg logit contributions
c-0.082
bar-0.079
 named-0.078
 bank-0.068
ah-0.068
Token did
Token ID750
Feature activation+5.64e-03

Pos logit contributions
c+0.053
bar+0.049
 named+0.049
 bank+0.042
ah+0.041
Neg logit contributions
ires-0.083
olving-0.081
 accomplishments-0.079
 footsteps-0.079
iders-0.078
Token not
Token ID407
Feature activation+4.20e-02

Pos logit contributions
ires+0.010
inner+0.009
olving+0.009
iders+0.009
 accomplishments+0.009
Neg logit contributions
c-0.008
 named-0.008
bar-0.008
 bank-0.007
ah-0.007
Token realized
Token ID6939
Feature activation+1.23e-02

Pos logit contributions
c+0.009
 named+0.009
bar+0.009
 bank+0.008
ah+0.008
Neg logit contributions
ires-0.012
olving-0.011
 accomplishments-0.011
 progress-0.011
inner-0.010
Token that
Token ID326
Feature activation-2.92e-02

Pos logit contributions
olving+0.023
ires+0.023
inner+0.022
 accomplishments+0.022
iders+0.022
Neg logit contributions
 named-0.016
c-0.016
bar-0.015
rob-0.013
ah-0.013
Token Rocky
Token ID24534
Feature activation+9.16e-03

Pos logit contributions
c+0.047
bar+0.044
 named+0.043
 bank+0.039
rob+0.038
Neg logit contributions
ires-0.048
olving-0.046
 accomplishments-0.045
 footsteps-0.045
iders-0.045
Token was
Token ID373
Feature activation-1.00e-02

Pos logit contributions
ires+0.019
 footsteps+0.018
olving+0.018
iders+0.017
 accomplishments+0.017
Neg logit contributions
c-0.012
 named-0.011
 bank-0.010
bar-0.009
ah-0.009
Token right
Token ID826
Feature activation-2.83e-02

Pos logit contributions
 named+0.015
c+0.014
bar+0.012
 bank+0.011
 called+0.011
Neg logit contributions
inner-0.019
ires-0.018
 accomplishments-0.018
iders-0.018
abies-0.017
Token.
Token ID13
Feature activation+1.50e-02

Pos logit contributions
c+0.040
 named+0.040
bar+0.036
ah+0.033
 bank+0.033
Neg logit contributions
ires-0.049
inner-0.049
 accomplishments-0.049
iders-0.049
 footsteps-0.048
Token She
Token ID1375
Feature activation-1.05e-02

Pos logit contributions
 accomplishments+0.029
olving+0.029
ires+0.029
inner+0.029
 happen+0.028
Neg logit contributions
c-0.018
 named-0.018
bar-0.017
 pouch-0.015
 bank-0.014
Token had
Token ID550
Feature activation-4.47e-02

Pos logit contributions
c+0.015
bar+0.014
 named+0.013
 bank+0.012
rob+0.012
Neg logit contributions
ires-0.019
olving-0.019
 footsteps-0.018
 accomplishments-0.018
 prayers-0.018
Token been
Token ID587
Feature activation+6.53e-02

Pos logit contributions
c+0.075
bar+0.073
rob+0.069
 named+0.068
ah+0.065
Neg logit contributions
olving-0.067
 footsteps-0.064
 prayers-0.064
ires-0.063
 words-0.062
Token foolish
Token ID19538
Feature activation-1.49e-02

Pos logit contributions
ires+0.075
ps+0.072
olving+0.072
 footsteps+0.071
 accidents+0.069
Neg logit contributions
c-0.132
bar-0.130
ah-0.119
 bank-0.119
rob-0.118
Token and
Token ID290
Feature activation+8.14e-03

Pos logit contributions
 named+0.019
c+0.019
bar+0.018
 bank+0.016
 pouch+0.015
Neg logit contributions
ires-0.028
iders-0.027
inner-0.027
 accomplishments-0.026
olving-0.026
Token't
Token ID470
Feature activation-1.87e-03

Pos logit contributions
ires+0.156
 accomplishments+0.153
olving+0.151
 prayers+0.149
 footsteps+0.147
Neg logit contributions
bar-0.109
c-0.107
 named-0.101
 bank-0.089
ah-0.088
Token know
Token ID760
Feature activation+5.06e-02

Pos logit contributions
c+0.003
 named+0.003
bar+0.003
ah+0.002
 bank+0.002
Neg logit contributions
ires-0.003
 accomplishments-0.003
olving-0.003
 prayers-0.003
iders-0.003
Token what
Token ID644
Feature activation+1.67e-01

Pos logit contributions
inner+0.066
 accomplishments+0.064
ires+0.063
olving+0.060
 progress+0.059
Neg logit contributions
c-0.101
 named-0.101
bar-0.090
 one-0.082
 called-0.082
Token to
Token ID284
Feature activation-1.59e-02

Pos logit contributions
ires+0.322
olving+0.307
 accomplishments+0.304
 footsteps+0.299
 progress+0.298
Neg logit contributions
c-0.233
 named-0.217
bar-0.207
 bank-0.185
ah-0.179
Token do
Token ID466
Feature activation+4.06e-02

Pos logit contributions
c+0.033
 named+0.032
bar+0.032
 bank+0.030
ah+0.029
Neg logit contributions
ires-0.018
olving-0.017
 accomplishments-0.017
 prayers-0.017
iders-0.016
Token.
Token ID13
Feature activation-1.93e-03

Pos logit contributions
 prayers+0.075
ires+0.073
 footsteps+0.072
 accomplishments+0.070
olving+0.069
Neg logit contributions
c-0.054
 named-0.053
bar-0.050
 bank-0.045
bank-0.041
Token
Token ID220
Feature activation-8.62e-02

Pos logit contributions
c+0.003
bar+0.003
 named+0.003
 bank+0.002
ah+0.002
Neg logit contributions
ires-0.003
olving-0.003
 accomplishments-0.003
 footsteps-0.003
iders-0.003
Token
Token ID198
Feature activation+6.01e-04

Pos logit contributions
c+0.125
bar+0.114
 named+0.114
 bank+0.095
ah+0.092
Neg logit contributions
olving-0.151
 accomplishments-0.150
ires-0.149
 footsteps-0.148
 prayers-0.147
Token
Token ID198
Feature activation+1.21e-03

Pos logit contributions
ires+0.001
olving+0.001
 footsteps+0.001
 accomplishments+0.001
iders+0.001
Neg logit contributions
bar-0.001
c-0.001
 named-0.001
 bank-0.001
ah-0.001
TokenSuddenly
Token ID38582
Feature activation+9.89e-03

Pos logit contributions
ires+0.002
olving+0.002
 prayers+0.002
 accomplishments+0.002
ps+0.002
Neg logit contributions
c-0.002
 named-0.002
bar-0.002
 bank-0.002
 pouch-0.002
Token,
Token ID11
Feature activation-8.50e-03

Pos logit contributions
ires+0.019
olving+0.019
 accomplishments+0.018
iders+0.018
inner+0.018
Neg logit contributions
c-0.013
 named-0.012
bar-0.012
 bank-0.010
ah-0.010
Token together
Token ID1978
Feature activation-3.88e-02

Pos logit contributions
ires+0.064
olving+0.062
 accomplishments+0.061
 footsteps+0.060
 prayers+0.059
Neg logit contributions
c-0.060
bar-0.058
 named-0.055
 bank-0.051
rob-0.050
Token,
Token ID11
Feature activation-3.21e-03

Pos logit contributions
c+0.065
bar+0.063
 named+0.060
 bank+0.056
rob+0.056
Neg logit contributions
ires-0.060
olving-0.058
 accomplishments-0.056
 footsteps-0.055
 prayers-0.055
Token looking
Token ID2045
Feature activation+4.53e-02

Pos logit contributions
c+0.005
bar+0.005
 named+0.005
 bank+0.005
rob+0.005
Neg logit contributions
ires-0.005
olving-0.005
 accomplishments-0.005
 footsteps-0.005
 prayers-0.005
Token for
Token ID329
Feature activation-3.02e-02

Pos logit contributions
ires+0.086
olving+0.084
iders+0.083
 footsteps+0.082
 accomplishments+0.082
Neg logit contributions
c-0.059
bar-0.055
 named-0.054
 bank-0.048
ah-0.046
Token beautiful
Token ID4950
Feature activation+4.02e-02

Pos logit contributions
c+0.058
bar+0.056
 named+0.054
 bank+0.050
ah+0.049
Neg logit contributions
ires-0.040
olving-0.038
 accomplishments-0.037
 footsteps-0.037
 prayers-0.036
Token colors
Token ID7577
Feature activation+6.97e-02

Pos logit contributions
ires+0.061
iders+0.060
olving+0.059
inner+0.059
 footsteps+0.056
Neg logit contributions
c-0.071
 named-0.066
bar-0.061
 bank-0.060
ah-0.057
Token,
Token ID11
Feature activation-4.82e-03

Pos logit contributions
ires+0.110
olving+0.106
 footsteps+0.105
 accomplishments+0.104
iders+0.104
Neg logit contributions
c-0.116
bar-0.111
 named-0.106
 bank-0.097
ah-0.095
Token and
Token ID290
Feature activation+4.51e-03

Pos logit contributions
c+0.008
bar+0.007
 named+0.007
 bank+0.007
ah+0.006
Neg logit contributions
ires-0.008
olving-0.008
 accomplishments-0.007
 footsteps-0.007
iders-0.007
Token having
Token ID1719
Feature activation+1.49e-02

Pos logit contributions
olving+0.007
ires+0.007
 accomplishments+0.007
 prayers+0.007
 footsteps+0.007
Neg logit contributions
c-0.007
bar-0.007
 named-0.007
rob-0.007
ah-0.006
Token lots
Token ID6041
Feature activation-5.32e-02

Pos logit contributions
ires+0.020
olving+0.020
 footsteps+0.020
 progress+0.020
 accomplishments+0.020
Neg logit contributions
bar-0.026
c-0.025
 named-0.024
 bank-0.022
rob-0.022
Token of
Token ID286
Feature activation+1.45e-02

Pos logit contributions
c+0.064
 named+0.060
bar+0.053
 bank+0.045
ah+0.044
Neg logit contributions
ires-0.110
iders-0.110
 footsteps-0.108
olving-0.107
abies-0.106
Token.
Token ID13
Feature activation+1.31e-02

Pos logit contributions
c+0.034
bar+0.033
 named+0.031
 bank+0.029
rob+0.029
Neg logit contributions
ires-0.028
olving-0.027
 accomplishments-0.026
 footsteps-0.026
 prayers-0.026
Token Mama
Token ID40084
Feature activation-4.90e-03

Pos logit contributions
ires+0.022
olving+0.022
 accomplishments+0.022
iders+0.021
inner+0.021
Neg logit contributions
c-0.020
 named-0.019
bar-0.018
 bank-0.016
 pouch-0.016
Token smiles
Token ID21845
Feature activation+9.21e-02

Pos logit contributions
 named+0.008
c+0.007
 bank+0.006
bar+0.006
 called+0.006
Neg logit contributions
olving-0.009
 accomplishments-0.009
ires-0.008
 progress-0.008
iring-0.008
Token and
Token ID290
Feature activation+1.38e-02

Pos logit contributions
iders+0.214
inner+0.214
 accomplishments+0.202
ires+0.202
olving+0.199
Neg logit contributions
 named-0.096
c-0.094
 one-0.082
 made-0.071
 offered-0.069
Token says
Token ID1139
Feature activation-5.99e-02

Pos logit contributions
olving+0.026
iders+0.026
inner+0.025
 accomplishments+0.025
iring+0.023
Neg logit contributions
 named-0.019
c-0.017
 pouch-0.016
 gir-0.015
 offered-0.015
Token they
Token ID484
Feature activation-7.07e-02

Pos logit contributions
 named+0.060
c+0.053
bar+0.043
 +0.039
ah+0.038
Neg logit contributions
ires-0.134
iders-0.132
olving-0.131
inner-0.129
 accomplishments-0.128
Token can
Token ID460
Feature activation+5.47e-02

Pos logit contributions
 named+0.101
c+0.101
 bank+0.091
bar+0.084
ah+0.081
Neg logit contributions
ires-0.128
iders-0.126
olving-0.122
iring-0.120
 accidents-0.119
Token pick
Token ID2298
Feature activation+2.55e-02

Pos logit contributions
ires+0.079
olving+0.077
 accomplishments+0.074
 footsteps+0.073
 prayers+0.073
Neg logit contributions
c-0.098
bar-0.094
 named-0.090
 bank-0.084
rob-0.083
Token it
Token ID340
Feature activation+1.18e-02

Pos logit contributions
ires+0.041
olving+0.038
 progress+0.037
 footsteps+0.037
 accomplishments+0.037
Neg logit contributions
c-0.041
bar-0.040
 named-0.039
rob-0.035
 bank-0.035
Token.
Token ID13
Feature activation+1.27e-02

Pos logit contributions
ires+0.017
olving+0.016
 accomplishments+0.016
 footsteps+0.016
 prayers+0.016
Neg logit contributions
c-0.022
bar-0.020
 named-0.020
 bank-0.019
ah-0.018
Token She
Token ID1375
Feature activation-6.35e-03

Pos logit contributions
olving+0.022
ires+0.022
 accomplishments+0.022
iders+0.021
inner+0.021
Neg logit contributions
c-0.018
 named-0.018
bar-0.017
 bank-0.015
 pouch-0.015
Token.
Token ID13
Feature activation+9.78e-03

Pos logit contributions
ires+0.098
iders+0.096
inner+0.093
olving+0.093
 accomplishments+0.090
Neg logit contributions
c-0.091
bar-0.084
 named-0.082
 bank-0.078
 pouch-0.070
Token He
Token ID679
Feature activation+2.38e-03

Pos logit contributions
ires+0.017
 prayers+0.016
 footsteps+0.015
olving+0.015
 progress+0.015
Neg logit contributions
c-0.015
bar-0.014
rob-0.013
ah-0.013
 named-0.013
Token was
Token ID373
Feature activation-1.63e-02

Pos logit contributions
 prayers+0.004
ires+0.004
olving+0.004
 accomplishments+0.004
 footsteps+0.004
Neg logit contributions
bar-0.004
c-0.003
rob-0.003
 bank-0.003
 named-0.003
Token glad
Token ID9675
Feature activation+4.58e-02

Pos logit contributions
c+0.027
bar+0.026
rob+0.025
 bank+0.025
 named+0.024
Neg logit contributions
ires-0.024
olving-0.023
 prayers-0.023
 footsteps-0.023
 progress-0.022
Token he
Token ID339
Feature activation-2.51e-02

Pos logit contributions
ires+0.086
olving+0.084
iders+0.081
 accomplishments+0.081
 footsteps+0.080
Neg logit contributions
c-0.061
bar-0.059
 named-0.057
 bank-0.051
ah-0.049
Token made
Token ID925
Feature activation-9.04e-02

Pos logit contributions
bar+0.032
c+0.032
 named+0.028
 bank+0.027
rob+0.025
Neg logit contributions
ires-0.046
olving-0.046
 accomplishments-0.045
 prayers-0.044
iders-0.044
Token such
Token ID884
Feature activation-1.85e-02

Pos logit contributions
c+0.142
bar+0.133
 named+0.131
 bank+0.118
ah+0.114
Neg logit contributions
ires-0.151
olving-0.148
iders-0.145
 accomplishments-0.141
inner-0.141
Token an
Token ID281
Feature activation-2.22e-02

Pos logit contributions
c+0.028
 named+0.028
bar+0.025
 bank+0.024
 pouch+0.023
Neg logit contributions
iders-0.032
ires-0.032
inner-0.031
olving-0.029
 accomplishments-0.029
Token impressive
Token ID8036
Feature activation+9.26e-03

Pos logit contributions
c+0.047
bar+0.046
 named+0.044
rob+0.043
 bank+0.042
Neg logit contributions
ires-0.024
olving-0.022
 accomplishments-0.022
 footsteps-0.022
 progress-0.022
Token bird
Token ID6512
Feature activation-4.06e-02

Pos logit contributions
ires+0.015
olving+0.015
 accomplishments+0.014
 footsteps+0.014
 prayers+0.014
Neg logit contributions
c-0.015
bar-0.014
 named-0.014
rob-0.013
 bank-0.013
Tokenc
Token ID66
Feature activation-1.31e-01

Pos logit contributions
bar+0.073
c+0.070
rob+0.069
 named+0.067
 bank+0.067
Neg logit contributions
ires-0.050
olving-0.050
 accomplishments-0.049
 accidents-0.048
 footsteps-0.048
Token at
Token ID379
Feature activation-2.36e-02

Pos logit contributions
c+0.103
bar+0.100
 named+0.093
rob+0.093
 bank+0.091
Neg logit contributions
ires-0.067
 footsteps-0.065
olving-0.064
 prayers-0.062
 accidents-0.062
Token first
Token ID717
Feature activation-5.73e-02

Pos logit contributions
c+0.027
bar+0.027
 named+0.026
 bank+0.024
ah+0.022
Neg logit contributions
ires-0.046
iders-0.045
olving-0.045
 accomplishments-0.044
 prayers-0.043
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
c+0.101
bar+0.098
 named+0.093
rob+0.088
 bank+0.087
Neg logit contributions
ires-0.082
olving-0.080
 footsteps-0.078
 accomplishments-0.078
 prayers-0.077
Token but
Token ID475
Feature activation-4.65e-02

Pos logit contributions
c+0.018
bar+0.017
rob+0.016
 named+0.016
ah+0.015
Neg logit contributions
ires-0.019
 footsteps-0.018
olving-0.018
 prayers-0.018
 accidents-0.018
Token then
Token ID788
Feature activation+1.29e-02

Pos logit contributions
c+0.077
bar+0.073
rob+0.068
 named+0.068
 bank+0.066
Neg logit contributions
ires-0.072
olving-0.071
 footsteps-0.069
 prayers-0.068
 accomplishments-0.068
Token she
Token ID673
Feature activation-4.44e-02

Pos logit contributions
ires+0.019
olving+0.019
 footsteps+0.019
 prayers+0.019
 accomplishments+0.019
Neg logit contributions
c-0.022
bar-0.021
 named-0.019
rob-0.019
 bank-0.019
Token smiled
Token ID13541
Feature activation+2.96e-02

Pos logit contributions
c+0.060
bar+0.058
rob+0.056
 named+0.051
 bank+0.051
Neg logit contributions
 footsteps-0.075
ires-0.075
 prayers-0.075
olving-0.075
 accomplishments-0.074
Token and
Token ID290
Feature activation+8.04e-04

Pos logit contributions
iders+0.060
inner+0.060
ires+0.057
olving+0.056
 accomplishments+0.055
Neg logit contributions
c-0.038
bar-0.036
 named-0.035
 one-0.030
ah-0.029
Token said
Token ID531
Feature activation-7.03e-02

Pos logit contributions
 prayers+0.001
ires+0.001
 footsteps+0.001
olving+0.001
 accidents+0.001
Neg logit contributions
c-0.001
bar-0.001
rob-0.001
ah-0.001
 bank-0.001
Token,
Token ID11
Feature activation-1.14e-02

Pos logit contributions
c+0.087
 named+0.087
bar+0.085
ah+0.069
 bank+0.069
Neg logit contributions
ires-0.139
iders-0.131
 accomplishments-0.130
olving-0.130
 footsteps-0.129
Token "
Token ID366
Feature activation-3.16e-02

Pos logit contributions
c+0.019
bar+0.019
 named+0.018
 bank+0.017
ah+0.016
Neg logit contributions
ires-0.017
olving-0.017
 accomplishments-0.016
iders-0.016
 footsteps-0.016
Token light
Token ID1657
Feature activation+5.28e-02

Pos logit contributions
ires+0.037
olving+0.034
iders+0.033
ps+0.033
 accomplishments+0.033
Neg logit contributions
c-0.036
 named-0.034
bar-0.034
 bank-0.032
 pouch-0.031
Token in
Token ID287
Feature activation-1.31e-02

Pos logit contributions
ires+0.084
olving+0.081
 accomplishments+0.080
iders+0.078
 prayers+0.078
Neg logit contributions
c-0.088
bar-0.083
 named-0.083
 bank-0.074
ah-0.073
Token a
Token ID257
Feature activation+2.17e-02

Pos logit contributions
c+0.021
bar+0.020
 named+0.019
 bank+0.018
ah+0.017
Neg logit contributions
ires-0.021
olving-0.021
 footsteps-0.020
 accomplishments-0.020
 prayers-0.020
Token window
Token ID4324
Feature activation+2.70e-02

Pos logit contributions
 footsteps+0.034
olving+0.033
ires+0.033
 prayers+0.032
 progress+0.032
Neg logit contributions
bar-0.033
c-0.033
 named-0.030
rob-0.030
ah-0.029
Token.
Token ID13
Feature activation+1.41e-02

Pos logit contributions
ires+0.039
olving+0.038
 accomplishments+0.037
 prayers+0.036
iders+0.036
Neg logit contributions
c-0.048
bar-0.046
 named-0.045
 bank-0.041
ah-0.041
Token She
Token ID1375
Feature activation-8.95e-03

Pos logit contributions
ires+0.025
 accomplishments+0.025
olving+0.025
iders+0.024
 progress+0.024
Neg logit contributions
c-0.020
 named-0.019
bar-0.018
 bank-0.016
 pouch-0.016
Token smelled
Token ID37609
Feature activation+1.89e-02

Pos logit contributions
c+0.013
bar+0.013
 named+0.011
rob+0.011
 bank+0.011
Neg logit contributions
ires-0.015
 footsteps-0.015
 prayers-0.015
olving-0.015
 accomplishments-0.015
Token something
Token ID1223
Feature activation+9.53e-02

Pos logit contributions
iders+0.040
olving+0.039
ires+0.038
 accomplishments+0.036
inner+0.036
Neg logit contributions
 named-0.022
c-0.021
 bank-0.019
bar-0.018
 one-0.017
Token good
Token ID922
Feature activation-6.61e-03

Pos logit contributions
ires+0.150
olving+0.147
 accomplishments+0.141
iders+0.139
 footsteps+0.137
Neg logit contributions
c-0.159
 named-0.150
bar-0.149
 bank-0.137
ah-0.130
Token.
Token ID13
Feature activation+1.51e-02

Pos logit contributions
c+0.009
 named+0.009
bar+0.009
 bank+0.008
ah+0.008
Neg logit contributions
ires-0.012
iders-0.011
 accomplishments-0.011
olving-0.011
 footsteps-0.011
Token She
Token ID1375
Feature activation-8.91e-03

Pos logit contributions
 accomplishments+0.030
olving+0.029
ires+0.029
ps+0.029
ieve+0.029
Neg logit contributions
c-0.019
 named-0.018
bar-0.016
 pouch-0.015
 bank-0.015
Token man
Token ID582
Feature activation-4.75e-02

Pos logit contributions
c+0.016
bar+0.016
 named+0.015
 bank+0.015
 pouch+0.013
Neg logit contributions
ires-0.024
iders-0.023
olving-0.023
ps-0.022
 accomplishments-0.021
Token with
Token ID351
Feature activation-6.33e-02

Pos logit contributions
c+0.061
 named+0.056
bar+0.055
 bank+0.048
ah+0.048
Neg logit contributions
ires-0.096
olving-0.092
 footsteps-0.091
iders-0.091
 accomplishments-0.090
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
c+0.102
bar+0.097
 named+0.093
 bank+0.086
rob+0.085
Neg logit contributions
ires-0.102
olving-0.099
 accomplishments-0.096
 footsteps-0.096
 prayers-0.095
Token dangerous
Token ID4923
Feature activation+1.46e-03

Pos logit contributions
c+0.017
bar+0.016
 named+0.015
 bank+0.014
rob+0.014
Neg logit contributions
ires-0.024
iders-0.024
olving-0.023
 footsteps-0.023
 accomplishments-0.023
Token pistol
Token ID16790
Feature activation-5.55e-02

Pos logit contributions
ires+0.003
olving+0.003
iders+0.003
 accomplishments+0.003
 footsteps+0.003
Neg logit contributions
c-0.002
bar-0.002
 named-0.002
 bank-0.002
rob-0.002
Token had
Token ID550
Feature activation-5.29e-02

Pos logit contributions
c+0.089
bar+0.087
 named+0.083
 bank+0.078
ah+0.074
Neg logit contributions
ires-0.091
olving-0.085
 accomplishments-0.084
iders-0.084
 footsteps-0.084
Token to
Token ID284
Feature activation-1.59e-02

Pos logit contributions
c+0.075
bar+0.071
 named+0.068
 bank+0.062
rob+0.061
Neg logit contributions
ires-0.095
olving-0.093
 accomplishments-0.090
 footsteps-0.090
 prayers-0.089
Token be
Token ID307
Feature activation+1.51e-03

Pos logit contributions
c+0.029
bar+0.028
 named+0.027
 bank+0.025
ah+0.025
Neg logit contributions
ires-0.022
olving-0.021
 accomplishments-0.021
 footsteps-0.021
iders-0.020
Token avoided
Token ID13941
Feature activation+3.99e-02

Pos logit contributions
olving+0.002
ires+0.002
 accomplishments+0.002
 footsteps+0.002
 progress+0.002
Neg logit contributions
c-0.003
bar-0.002
 named-0.002
rob-0.002
ah-0.002
Token,
Token ID11
Feature activation-8.24e-03

Pos logit contributions
ires+0.061
olving+0.057
iders+0.057
inner+0.056
 accomplishments+0.056
Neg logit contributions
c-0.068
bar-0.066
 named-0.064
 bank-0.059
ah-0.057
Token but
Token ID475
Feature activation-4.26e-02

Pos logit contributions
c+0.013
bar+0.012
 named+0.011
rob+0.011
 bank+0.011
Neg logit contributions
ires-0.014
olving-0.014
 accomplishments-0.013
 footsteps-0.013
 prayers-0.013
Token day
Token ID1110
Feature activation+6.02e-03

Pos logit contributions
bar+0.032
c+0.032
 named+0.028
rob+0.027
 bank+0.027
Neg logit contributions
ires-0.052
olving-0.051
 accomplishments-0.050
inner-0.049
 footsteps-0.049
Token,
Token ID11
Feature activation-9.82e-03

Pos logit contributions
ires+0.011
olving+0.011
 footsteps+0.011
 accomplishments+0.011
 prayers+0.011
Neg logit contributions
c-0.008
 named-0.008
bar-0.008
 bank-0.007
ah-0.007
Token a
Token ID257
Feature activation+1.95e-02

Pos logit contributions
c+0.016
 named+0.016
bar+0.015
ah+0.013
 bank+0.013
Neg logit contributions
olving-0.016
ires-0.016
 accomplishments-0.016
 prayers-0.016
 progress-0.015
Token little
Token ID1310
Feature activation-9.93e-04

Pos logit contributions
ps+0.029
ires+0.029
olving+0.029
iders+0.028
 progress+0.027
Neg logit contributions
 named-0.036
c-0.034
ah-0.031
bar-0.030
 bank-0.029
Token boy
Token ID2933
Feature activation-4.76e-02

Pos logit contributions
c+0.002
bar+0.002
 bank+0.002
bank+0.002
rob+0.002
Neg logit contributions
ires-0.001
inner-0.001
 accidents-0.001
 footsteps-0.001
 accomplishments-0.001
Token named
Token ID3706
Feature activation-1.22e-01

Pos logit contributions
bar+0.029
c+0.019
 bank+0.018
rob+0.017
 pouch+0.014
Neg logit contributions
ires-0.120
olving-0.120
 footsteps-0.117
 accidents-0.116
inner-0.114
Token Tim
Token ID5045
Feature activation+2.65e-02

Pos logit contributions
c+0.169
bar+0.160
 named+0.152
 bank+0.139
rob+0.135
Neg logit contributions
ires-0.228
olving-0.222
 footsteps-0.216
 accomplishments-0.216
 prayers-0.214
Token was
Token ID373
Feature activation-1.48e-02

Pos logit contributions
ires+0.052
olving+0.052
 footsteps+0.050
inner+0.049
 accomplishments+0.049
Neg logit contributions
bar-0.031
c-0.030
 named-0.026
 bank-0.025
rob-0.025
Token very
Token ID845
Feature activation-4.53e-02

Pos logit contributions
c+0.029
bar+0.028
rob+0.027
ah+0.027
 bank+0.025
Neg logit contributions
ires-0.018
 footsteps-0.018
olving-0.017
 accidents-0.016
iring-0.016
Token eager
Token ID11069
Feature activation-1.51e-02

Pos logit contributions
c+0.069
bar+0.065
 named+0.061
rob+0.058
 bank+0.057
Neg logit contributions
ires-0.079
olving-0.076
 accomplishments-0.074
 footsteps-0.073
 prayers-0.073
Token to
Token ID284
Feature activation-1.46e-02

Pos logit contributions
c+0.026
bar+0.024
 named+0.023
rob+0.022
ah+0.021
Neg logit contributions
 footsteps-0.023
ires-0.023
olving-0.023
 prayers-0.022
 accomplishments-0.022
Token time
Token ID640
Feature activation+3.81e-02

Pos logit contributions
ires+0.028
olving+0.027
 footsteps+0.026
iders+0.026
 prayers+0.025
Neg logit contributions
c-0.028
 named-0.026
bar-0.025
ah-0.024
 bank-0.023
Token there
Token ID612
Feature activation-2.47e-02

Pos logit contributions
ires+0.082
 prayers+0.079
 progress+0.078
ps+0.078
 accomplishments+0.078
Neg logit contributions
c-0.042
 named-0.041
bar-0.038
ah-0.032
 bank-0.028
Token were
Token ID547
Feature activation-1.24e-02

Pos logit contributions
c+0.036
 named+0.034
bar+0.032
ah+0.029
 bank+0.029
Neg logit contributions
ires-0.046
olving-0.044
 accomplishments-0.044
iders-0.043
 footsteps-0.043
Token two
Token ID734
Feature activation-6.87e-02

Pos logit contributions
c+0.025
bar+0.024
 named+0.023
 bank+0.023
rob+0.022
Neg logit contributions
ires-0.015
 footsteps-0.014
 accidents-0.014
olving-0.014
 prayers-0.013
Token birds
Token ID10087
Feature activation+5.88e-02

Pos logit contributions
c+0.126
bar+0.123
 named+0.115
rob+0.110
 bank+0.110
Neg logit contributions
ires-0.094
olving-0.089
 footsteps-0.088
 accomplishments-0.087
 prayers-0.086
Token named
Token ID3706
Feature activation-1.23e-01

Pos logit contributions
ires+0.075
iring+0.070
olving+0.070
ble+0.067
ps+0.065
Neg logit contributions
bar-0.104
c-0.098
rob-0.097
 bank-0.095
 pouch-0.090
Token Steve
Token ID6542
Feature activation+2.20e-02

Pos logit contributions
bar+0.198
c+0.195
rob+0.175
 bank+0.173
 named+0.172
Neg logit contributions
ires-0.182
 footsteps-0.172
olving-0.169
 prayers-0.168
ps-0.168
Token and
Token ID290
Feature activation+2.95e-03

Pos logit contributions
ires+0.026
olving+0.025
 accomplishments+0.024
 prayers+0.023
 footsteps+0.023
Neg logit contributions
bar-0.042
c-0.042
 bank-0.038
 named-0.038
rob-0.038
Token Joe
Token ID5689
Feature activation+2.84e-02

Pos logit contributions
 footsteps+0.004
 prayers+0.003
 words+0.003
ires+0.003
 angels+0.003
Neg logit contributions
c-0.006
bar-0.005
 pouch-0.005
 bank-0.005
rob-0.004
Token.
Token ID13
Feature activation+4.93e-03

Pos logit contributions
ires+0.029
olving+0.029
ps+0.026
 footsteps+0.026
 accomplishments+0.026
Neg logit contributions
bar-0.058
c-0.057
rob-0.054
 bank-0.052
 named-0.052
Token Steve
Token ID6542
Feature activation+2.24e-02

Pos logit contributions
ires+0.008
olving+0.008
 footsteps+0.008
 accomplishments+0.008
 progress+0.008
Neg logit contributions
c-0.008
bar-0.008
 named-0.007
 bank-0.006
 pouch-0.006
Token there
Token ID612
Feature activation-1.80e-02

Pos logit contributions
c+0.005
 named+0.005
bar+0.005
 bank+0.004
ah+0.004
Neg logit contributions
ires-0.006
olving-0.006
 accomplishments-0.006
 footsteps-0.006
 prayers-0.006
Token was
Token ID373
Feature activation-1.03e-02

Pos logit contributions
c+0.025
 named+0.023
bar+0.021
ah+0.019
 bank+0.018
Neg logit contributions
ires-0.035
iders-0.034
 accomplishments-0.034
olving-0.034
 prayers-0.033
Token a
Token ID257
Feature activation+2.28e-02

Pos logit contributions
c+0.019
bar+0.019
 named+0.018
 bank+0.017
rob+0.016
Neg logit contributions
ires-0.014
olving-0.013
 accomplishments-0.013
 footsteps-0.013
 prayers-0.013
Token little
Token ID1310
Feature activation+7.09e-03

Pos logit contributions
ires+0.031
olving+0.031
ps+0.029
iders+0.029
 footsteps+0.028
Neg logit contributions
 named-0.043
c-0.042
bar-0.039
ah-0.037
 bank-0.037
Token crab
Token ID32202
Feature activation-1.83e-02

Pos logit contributions
ires+0.009
 footsteps+0.009
 accidents+0.009
inner+0.009
 accomplishments+0.008
Neg logit contributions
c-0.013
bar-0.013
 bank-0.012
 named-0.012
bank-0.012
Token named
Token ID3706
Feature activation-1.15e-01

Pos logit contributions
bar+0.022
rob+0.020
 bank+0.018
 Fer+0.017
 pouch+0.016
Neg logit contributions
ires-0.032
ble-0.030
iders-0.030
 spell-0.030
iring-0.030
Token Sam
Token ID3409
Feature activation+2.07e-02

Pos logit contributions
c+0.196
bar+0.181
 named+0.168
 bank+0.167
rob+0.164
Neg logit contributions
ires-0.175
olving-0.162
 footsteps-0.159
inner-0.155
 accidents-0.153
Token.
Token ID13
Feature activation+7.87e-03

Pos logit contributions
ires+0.023
olving+0.021
 accomplishments+0.020
 footsteps+0.020
iders+0.019
Neg logit contributions
bar-0.042
c-0.041
 bank-0.039
rob-0.038
 named-0.038
Token Sam
Token ID3409
Feature activation+2.14e-02

Pos logit contributions
ires+0.010
olving+0.010
 footsteps+0.009
 progress+0.009
 accomplishments+0.009
Neg logit contributions
c-0.015
bar-0.015
 named-0.014
 bank-0.014
 pouch-0.014
Token loved
Token ID6151
Feature activation+9.05e-02

Pos logit contributions
ires+0.031
olving+0.030
 prayers+0.029
 accomplishments+0.029
inner+0.029
Neg logit contributions
bar-0.036
c-0.034
 named-0.030
 bank-0.030
rob-0.030
Token to
Token ID284
Feature activation-7.93e-03

Pos logit contributions
ires+0.140
olving+0.132
 accidents+0.130
 footsteps+0.128
 accomplishments+0.128
Neg logit contributions
c-0.156
bar-0.147
 named-0.137
 bank-0.130
ah-0.130
Token
Token ID198
Feature activation-1.56e-03

Pos logit contributions
ires+0.004
olving+0.004
 footsteps+0.004
 accomplishments+0.004
 prayers+0.004
Neg logit contributions
c-0.004
bar-0.003
 named-0.003
 bank-0.003
rob-0.003
Token
Token ID198
Feature activation-1.08e-03

Pos logit contributions
c+0.003
bar+0.003
 named+0.003
 bank+0.002
rob+0.002
Neg logit contributions
ires-0.002
olving-0.002
 accomplishments-0.002
iders-0.002
 footsteps-0.002
TokenHe
Token ID1544
Feature activation+2.58e-02

Pos logit contributions
c+0.002
bar+0.002
 named+0.002
rob+0.002
 bank+0.002
Neg logit contributions
ires-0.002
olving-0.001
iders-0.001
 accomplishments-0.001
inner-0.001
Token waved
Token ID26834
Feature activation-4.56e-02

Pos logit contributions
olving+0.041
 prayers+0.040
 accomplishments+0.040
 footsteps+0.040
ires+0.040
Neg logit contributions
bar-0.037
c-0.037
rob-0.033
 pouch-0.029
ah-0.028
Token the
Token ID262
Feature activation-1.52e-02

Pos logit contributions
c+0.068
bar+0.065
 named+0.063
 bank+0.057
ah+0.056
Neg logit contributions
ires-0.079
olving-0.078
iders-0.075
 accomplishments-0.075
inner-0.074
Token jar
Token ID17379
Feature activation-1.10e-01

Pos logit contributions
c+0.021
bar+0.019
 named+0.018
 bank+0.018
 pouch+0.018
Neg logit contributions
ires-0.030
iders-0.027
olving-0.027
iring-0.027
 footsteps-0.026
Token around
Token ID1088
Feature activation+1.74e-02

Pos logit contributions
c+0.190
bar+0.181
 named+0.177
rob+0.173
 bank+0.166
Neg logit contributions
ires-0.159
olving-0.156
 accomplishments-0.149
 footsteps-0.149
 progress-0.146
Token and
Token ID290
Feature activation+2.51e-03

Pos logit contributions
ires+0.032
olving+0.031
iders+0.031
inner+0.031
 accomplishments+0.030
Neg logit contributions
c-0.024
 named-0.024
bar-0.023
 bank-0.021
ah-0.020
Token made
Token ID925
Feature activation-8.88e-02

Pos logit contributions
 footsteps+0.004
 accidents+0.004
 prayers+0.004
olving+0.004
ires+0.004
Neg logit contributions
c-0.004
bar-0.004
rob-0.003
 named-0.003
 pouch-0.003
Token them
Token ID606
Feature activation+5.82e-02

Pos logit contributions
c+0.136
bar+0.130
 named+0.129
 bank+0.121
ah+0.113
Neg logit contributions
olving-0.147
iders-0.147
ires-0.143
 accomplishments-0.135
inner-0.134
Token laugh
Token ID6487
Feature activation+5.97e-02

Pos logit contributions
ires+0.094
iders+0.090
olving+0.085
inner+0.084
 accomplishments+0.081
Neg logit contributions
c-0.099
bar-0.095
 named-0.092
 bank-0.089
 pouch-0.081
Token Lily
Token ID20037
Feature activation+8.32e-03

Pos logit contributions
bar+0.109
c+0.108
rob+0.098
ci+0.096
 bank+0.096
Neg logit contributions
 footsteps-0.053
 prayers-0.048
ires-0.047
 accidents-0.046
 words-0.045
Token said
Token ID531
Feature activation-6.54e-02

Pos logit contributions
 footsteps+0.013
 words+0.013
 accidents+0.012
iders+0.012
ps+0.012
Neg logit contributions
c-0.013
bar-0.013
rob-0.012
 pouch-0.011
ah-0.010
Token,
Token ID11
Feature activation+6.81e-04

Pos logit contributions
c+0.088
bar+0.085
 named+0.084
 bank+0.073
ah+0.070
Neg logit contributions
ires-0.124
olving-0.120
 accomplishments-0.117
inner-0.116
iders-0.116
Token showing
Token ID4478
Feature activation-6.23e-02

Pos logit contributions
ires+0.001
olving+0.001
inner+0.001
 accomplishments+0.001
 prayers+0.001
Neg logit contributions
c-0.001
 named-0.001
bar-0.001
 bank-0.001
ah-0.001
Token her
Token ID607
Feature activation+5.76e-02

Pos logit contributions
c+0.101
bar+0.100
 named+0.095
 bank+0.086
ah+0.086
Neg logit contributions
olving-0.098
ires-0.096
iders-0.095
 accomplishments-0.094
inner-0.090
Token basket
Token ID7988
Feature activation-1.23e-01

Pos logit contributions
ires+0.091
olving+0.089
 accomplishments+0.086
 footsteps+0.085
iders+0.085
Neg logit contributions
c-0.095
bar-0.091
 named-0.088
 bank-0.081
ah-0.079
Token.
Token ID13
Feature activation+1.29e-02

Pos logit contributions
c+0.204
bar+0.197
 named+0.189
 bank+0.176
ah+0.169
Neg logit contributions
ires-0.192
olving-0.184
 accomplishments-0.181
 prayers-0.179
iders-0.178
Token
Token ID198
Feature activation+6.38e-03

Pos logit contributions
 accomplishments+0.026
ieve+0.026
inner+0.026
olving+0.026
 happen+0.025
Neg logit contributions
 named-0.015
c-0.014
bar-0.013
 -0.012
 pouch-0.011
Token
Token ID198
Feature activation+6.70e-03

Pos logit contributions
olving+0.013
 accomplishments+0.013
 prayers+0.013
 progress+0.013
 footsteps+0.013
Neg logit contributions
 named-0.007
c-0.007
bar-0.006
 -0.005
ossible-0.005
TokenThey
Token ID2990
Feature activation-3.17e-03

Pos logit contributions
 prayers+0.011
olving+0.011
 accomplishments+0.011
ires+0.011
 progress+0.011
Neg logit contributions
c-0.010
bar-0.010
 named-0.010
P-0.009
 bank-0.009
Token kept
Token ID4030
Feature activation-1.89e-02

Pos logit contributions
c+0.006
bar+0.005
rob+0.005
bank+0.005
 pouch+0.004
Neg logit contributions
 spit-0.004
 footsteps-0.004
ps-0.004
 concentrate-0.004
 erase-0.004