TOP ACTIVATIONS
MAX = 4.784

loved playing outside until no ont ime . He was always
- four , forty - five , forty - six ,
- four , thirty - five , thirty - six ,
Once the apple was all che wed up , the cow
Bang ! You 're under arrest !" Their mom
- four , twenty - five , twenty - six ,
two and became two b unn ies . " Wow ,
lesson that day and never che wed on things that were
could see lots of av oc ados that the supplier had
not as important as being kind . They learned that a
friendly and asked the l itt ler frog to join them
's okay to ask for help when she needs it .
Sara , I have grape ear rings . They are round
not as important as having kind and helpful friends like the
not as important as being kind and friendly . They became
cops . They take b unn ies away ."
not terrible to ask for help . Sometimes , we need
bear is deaf in one ear . That means it cannot
- four , forty - five , forty - six ,
and asked if it could help her . The tree said

MIN ACTIVATIONS
MIN = -3.598

was different from what you usually do ," mom said .
the boring h angers she usually saw . J
't taste like anything he usually ate , like honey or
. He ran to the concessions stand and grabbed a bag
He could hear a p ained noise coming from the woods
Jack was so happy he almost cried .
John felt so happy he almost shouted with joy .
up the stairs like he usually did ! Tom
in the wild . He usually kept to himself , but
able to do what she 'd done . For
zoom ed around , he usually visited his best friend Sammy
, " What are you gonna do with him ?". Joe
so proud of what he 'd done . He had tried
see who could roll the fart hest . They were a
thought was weird because she usually had ham and cheese .
thinking about the rain he almost tri pped over it !
excited to see what she 'd make . Soon , Mom
was so pleased that she almost found an escape .
them all about what he 'd seen . His friends thought
was so happy that she almost squ eal ed .

INTERVAL 2.688 - 4.784
CONTAINS 0.009%

's mom asked her to help with the groceries . Lily
. They can ask for help . They learn that sometimes
not as bright as glowing hearts ." <|endoftext|> Tim and Sue
, so she asked for help from her bear ! Together
fixed things and asked for help . The man at the

INTERVAL 0.593 - 2.688
CONTAINS 14.052%

pile of leaves !" Lily says . She and Tom run
see the doctor who made his paw all better . P
airport and it was time to stop . Daddy , M
" Yes , let 's pick it !" Ben
but now she could also eat a snack in the water

INTERVAL -1.502 - 0.593
CONTAINS 85.013%

mom my said , " Sure , I 'll get it
she was sitting in the park listening to the birds ch
brilliant king . He was the best king in the whole
explore the zoo . Do you want to come with me
up with an empty stomach . She was very lucky ,

INTERVAL -3.598 - -1.502
CONTAINS 0.926%

hungry and angry . He jumped out from behind the bench
large lizard . They wish they listened to Tim . They
couldn 't figure out what it was . He looked around
wanted to whistle too , so he started to practice .
nods . He seems to like their story .
Token loved
Token ID6151
Feature activation+3.26e-01

Pos logit contributions
 robbers+0.010
 mice+0.010
 bear+0.010
 bears+0.010
 rabbits+0.010
Neg logit contributions
inkle-0.011
rig-0.011
itating-0.010
?",-0.010
ews-0.010
Token playing
Token ID2712
Feature activation+4.38e-01

Pos logit contributions
Carl+0.017
emaker+0.017
 bear+0.017
Found+0.016
pillar+0.016
Neg logit contributions
 early-0.009
 yet-0.008
ews-0.008
?",-0.007
 ours-0.007
Token outside
Token ID2354
Feature activation-1.24e-01

Pos logit contributions
 bear+0.023
 robbers+0.023
 bears+0.023
 mice+0.022
 rabbits+0.022
Neg logit contributions
itating-0.013
inkle-0.013
rig-0.012
shadow-0.012
ews-0.011
Token until
Token ID1566
Feature activation+3.08e-01

Pos logit contributions
itating+0.004
inkle+0.003
rig+0.003
?",+0.003
 early+0.003
Neg logit contributions
 robbers-0.007
 bear-0.007
 mice-0.006
 bears-0.006
 squirrel-0.006
Token no
Token ID645
Feature activation+1.87e-01

Pos logit contributions
pill+0.011
 mice+0.011
 bear+0.010
 robbers+0.010
 villains+0.010
Neg logit contributions
inkle-0.015
?",-0.014
 yet-0.014
itating-0.014
 early-0.014
Tokenont
Token ID756
Feature activation+3.74e+00

Pos logit contributions
pill+0.009
Carl+0.008
B+0.007
Mic+0.007
 villains+0.007
Neg logit contributions
 yet-0.007
?",-0.007
 early-0.007
?"-0.006
?!"-0.006
Tokenime
Token ID524
Feature activation+9.12e-01

Pos logit contributions
 robbers+0.169
 villains+0.152
 squirrel+0.151
 mice+0.150
Mic+0.149
Neg logit contributions
inkle-0.160
ews-0.155
ist-0.151
ossom-0.144
our-0.142
Token.
Token ID13
Feature activation+4.93e-01

Pos logit contributions
 robbers+0.032
 bear+0.029
 shields+0.029
 mice+0.028
 rabbits+0.028
Neg logit contributions
itating-0.043
inkle-0.042
?",-0.041
 yet-0.041
ews-0.041
Token He
Token ID679
Feature activation+6.47e-01

Pos logit contributions
 bear+0.016
 bears+0.016
 robbers+0.015
 mice+0.015
 rabbits+0.015
Neg logit contributions
itating-0.025
rig-0.025
inkle-0.025
ews-0.024
shadow-0.024
Token was
Token ID373
Feature activation-6.29e-02

Pos logit contributions
 robbers+0.022
 bear+0.021
 mice+0.021
 bears+0.021
 rabbits+0.020
Neg logit contributions
inkle-0.032
rig-0.031
itating-0.031
ews-0.030
?",-0.030
Token always
Token ID1464
Feature activation-4.75e-01

Pos logit contributions
inkle+0.003
itating+0.003
rig+0.003
mmm+0.003
ossom+0.003
Neg logit contributions
 bear-0.003
 bears-0.002
 robbers-0.002
 mice-0.002
 rabbits-0.002
Token-
Token ID12
Feature activation+1.11e+00

Pos logit contributions
 bear+0.033
 robbers+0.032
 bears+0.031
 mice+0.031
 rabbits+0.030
Neg logit contributions
inkle-0.033
itating-0.032
rig-0.031
shadow-0.031
ews-0.030
Tokenfour
Token ID14337
Feature activation+1.83e+00

Pos logit contributions
 bear+0.057
 robbers+0.056
 bears+0.055
 mice+0.055
 rabbits+0.055
Neg logit contributions
itating-0.036
shadow-0.036
rig-0.035
inkle-0.035
ews-0.033
Token,
Token ID11
Feature activation+1.47e+00

Pos logit contributions
 bear+0.076
 robbers+0.075
 bears+0.072
 mice+0.071
 rabbits+0.070
Neg logit contributions
inkle-0.080
itating-0.077
rig-0.075
ews-0.073
shadow-0.072
Token forty
Token ID16571
Feature activation+1.66e+00

Pos logit contributions
 bear+0.059
 robbers+0.058
 bears+0.056
 mice+0.056
 rabbits+0.055
Neg logit contributions
inkle-0.064
itating-0.064
rig-0.062
shadow-0.061
ews-0.060
Token-
Token ID12
Feature activation+1.89e+00

Pos logit contributions
 bear+0.071
 robbers+0.069
 bears+0.067
 mice+0.067
 rabbits+0.066
Neg logit contributions
inkle-0.069
itating-0.069
rig-0.067
shadow-0.065
ews-0.064
Tokenfive
Token ID13261
Feature activation+3.57e+00

Pos logit contributions
 bear+0.091
 robbers+0.089
 bears+0.088
 mice+0.087
 rabbits+0.086
Neg logit contributions
itating-0.069
inkle-0.068
rig-0.066
shadow-0.065
ews-0.063
Token,
Token ID11
Feature activation+1.16e+00

Pos logit contributions
 bear+0.147
 robbers+0.145
 mice+0.139
 bears+0.139
 rabbits+0.137
Neg logit contributions
inkle-0.152
itating-0.151
rig-0.145
shadow-0.143
ews-0.142
Token forty
Token ID16571
Feature activation+1.20e+00

Pos logit contributions
 bear+0.046
 robbers+0.045
 bears+0.044
 mice+0.043
 rabbits+0.042
Neg logit contributions
itating-0.051
inkle-0.051
rig-0.050
shadow-0.049
ews-0.048
Token-
Token ID12
Feature activation+1.50e+00

Pos logit contributions
 bear+0.051
 robbers+0.050
 bears+0.049
 mice+0.048
 rabbits+0.047
Neg logit contributions
inkle-0.050
itating-0.050
rig-0.048
shadow-0.047
ews-0.047
Tokensix
Token ID19412
Feature activation+9.89e-01

Pos logit contributions
 bear+0.074
 robbers+0.072
 bears+0.072
 mice+0.071
 rabbits+0.070
Neg logit contributions
itating-0.052
inkle-0.051
rig-0.050
shadow-0.050
ews-0.048
Token,
Token ID11
Feature activation+7.24e-01

Pos logit contributions
B+0.048
 robbers+0.048
 villains+0.045
 mice+0.044
Carl+0.044
Neg logit contributions
inkle-0.035
?",-0.031
ews-0.031
mmm-0.030
 yet-0.030
Token-
Token ID12
Feature activation+1.26e+00

Pos logit contributions
 bear+0.043
 robbers+0.042
 bears+0.041
 mice+0.041
 rabbits+0.040
Neg logit contributions
itating-0.046
inkle-0.046
rig-0.045
shadow-0.043
ews-0.043
Tokenfour
Token ID14337
Feature activation+1.78e+00

Pos logit contributions
 bear+0.063
 robbers+0.061
 bears+0.061
 mice+0.060
 rabbits+0.059
Neg logit contributions
itating-0.044
inkle-0.043
rig-0.042
shadow-0.042
ews-0.040
Token,
Token ID11
Feature activation+1.42e+00

Pos logit contributions
 bear+0.072
 robbers+0.070
 bears+0.068
 mice+0.067
 rabbits+0.066
Neg logit contributions
inkle-0.080
itating-0.079
rig-0.077
shadow-0.074
ews-0.074
Token thirty
Token ID12277
Feature activation+1.91e+00

Pos logit contributions
 bear+0.058
 robbers+0.056
 bears+0.055
 mice+0.055
 rabbits+0.053
Neg logit contributions
itating-0.062
inkle-0.062
rig-0.060
shadow-0.059
ews-0.058
Token-
Token ID12
Feature activation+1.88e+00

Pos logit contributions
 bear+0.079
 robbers+0.076
 bears+0.076
 mice+0.074
 rabbits+0.073
Neg logit contributions
itating-0.083
inkle-0.082
rig-0.080
shadow-0.078
ews-0.077
Tokenfive
Token ID13261
Feature activation+3.54e+00

Pos logit contributions
 bear+0.088
 robbers+0.085
 bears+0.085
 mice+0.084
 rabbits+0.082
Neg logit contributions
itating-0.071
inkle-0.070
rig-0.068
shadow-0.067
ews-0.065
Token,
Token ID11
Feature activation+1.14e+00

Pos logit contributions
 bear+0.143
 robbers+0.140
 bears+0.136
 mice+0.135
 rabbits+0.132
Neg logit contributions
inkle-0.154
itating-0.154
rig-0.148
shadow-0.145
ews-0.144
Token thirty
Token ID12277
Feature activation+1.46e+00

Pos logit contributions
 bear+0.046
 robbers+0.044
 bears+0.044
 mice+0.043
 rabbits+0.042
Neg logit contributions
itating-0.051
inkle-0.051
rig-0.049
shadow-0.048
ews-0.048
Token-
Token ID12
Feature activation+1.52e+00

Pos logit contributions
 bear+0.061
 robbers+0.059
 bears+0.058
 mice+0.057
 rabbits+0.056
Neg logit contributions
itating-0.063
inkle-0.063
rig-0.061
shadow-0.059
ews-0.059
Tokensix
Token ID19412
Feature activation+9.68e-01

Pos logit contributions
 bear+0.073
 robbers+0.071
 bears+0.070
 mice+0.069
 rabbits+0.068
Neg logit contributions
itating-0.056
inkle-0.055
rig-0.054
shadow-0.053
ews-0.052
Token,
Token ID11
Feature activation+7.75e-01

Pos logit contributions
 robbers+0.045
B+0.045
 bear+0.042
 villains+0.042
 mice+0.042
Neg logit contributions
inkle-0.036
ews-0.033
?",-0.032
mmm-0.031
itating-0.031
TokenOnce
Token ID7454
Feature activation+7.15e-02

Pos logit contributions
 bear+0.009
 robbers+0.008
 bears+0.008
 mice+0.008
 rabbits+0.008
Neg logit contributions
itating-0.006
inkle-0.006
rig-0.006
shadow-0.006
ews-0.005
Token the
Token ID262
Feature activation+7.28e-01

Pos logit contributions
 bear+0.003
 bears+0.003
 mice+0.003
 robbers+0.002
 rabbits+0.002
Neg logit contributions
itating-0.003
rig-0.003
inkle-0.003
shadow-0.003
ews-0.003
Token apple
Token ID17180
Feature activation+1.42e+00

Pos logit contributions
 robbers+0.027
 villains+0.026
 bear+0.026
 mice+0.025
 bears+0.025
Neg logit contributions
inkle-0.034
rig-0.033
itating-0.033
ews-0.031
shadow-0.031
Token was
Token ID373
Feature activation+8.59e-01

Pos logit contributions
 bear+0.043
 robbers+0.041
 bears+0.040
 mice+0.040
 rabbits+0.038
Neg logit contributions
itating-0.077
inkle-0.077
rig-0.075
shadow-0.073
ews-0.073
Token all
Token ID477
Feature activation+1.25e+00

Pos logit contributions
 bear+0.036
 bears+0.035
 rabbits+0.034
 mice+0.033
 robbers+0.033
Neg logit contributions
itating-0.038
rig-0.037
inkle-0.036
apers-0.035
ews-0.035
Token che
Token ID1125
Feature activation+3.52e+00

Pos logit contributions
 bear+0.053
 robbers+0.051
 bears+0.050
 mice+0.049
 rabbits+0.048
Neg logit contributions
itating-0.054
inkle-0.053
rig-0.052
shadow-0.050
ews-0.050
Tokenwed
Token ID19103
Feature activation+9.95e-01

Pos logit contributions
 bear+0.151
 robbers+0.148
 bears+0.141
 mice+0.140
 squirrel+0.139
Neg logit contributions
inkle-0.157
itating-0.147
rig-0.145
shadow-0.144
ews-0.140
Token up
Token ID510
Feature activation-2.68e-02

Pos logit contributions
 bear+0.039
 bears+0.037
 mice+0.037
 rabbits+0.036
 squirrel+0.036
Neg logit contributions
itating-0.047
rig-0.046
inkle-0.045
ews-0.045
shadow-0.045
Token,
Token ID11
Feature activation+5.08e-01

Pos logit contributions
itating+0.001
inkle+0.001
rig+0.001
shadow+0.001
ews+0.001
Neg logit contributions
 bear-0.001
 bears-0.001
 robbers-0.001
 mice-0.001
 squirrel-0.001
Token the
Token ID262
Feature activation+2.07e-01

Pos logit contributions
 bear+0.018
 bears+0.017
 mice+0.016
 squirrel+0.016
 rabbits+0.016
Neg logit contributions
inkle-0.027
rig-0.027
itating-0.027
shadow-0.025
ews-0.025
Token cow
Token ID9875
Feature activation-4.52e-01

Pos logit contributions
 robbers+0.007
 bear+0.006
 bears+0.006
 villains+0.006
 mice+0.006
Neg logit contributions
inkle-0.010
itating-0.010
rig-0.010
shadow-0.010
ews-0.010
Token Bang
Token ID9801
Feature activation-1.98e-01

Pos logit contributions
 bear+0.010
 bears+0.010
 robbers+0.010
 mice+0.010
 rabbits+0.010
Neg logit contributions
itating-0.012
inkle-0.011
shadow-0.011
rig-0.011
ews-0.011
Token!
Token ID0
Feature activation+2.00e-01

Pos logit contributions
inkle+0.007
itating+0.007
?",+0.007
rig+0.007
?!"+0.007
Neg logit contributions
 robbers-0.009
 bear-0.009
 mice-0.009
 bears-0.009
 rabbits-0.009
Token You
Token ID921
Feature activation+7.57e-01

Pos logit contributions
 bear+0.009
 bears+0.009
 robbers+0.008
 mice+0.008
 rabbits+0.008
Neg logit contributions
itating-0.008
inkle-0.008
shadow-0.008
rig-0.008
ews-0.007
Token're
Token ID821
Feature activation-4.92e-01

Pos logit contributions
 mice+0.028
 bears+0.028
 robbers+0.028
 bear+0.028
 rabbits+0.027
Neg logit contributions
itating-0.034
inkle-0.033
?",-0.032
rig-0.032
shadow-0.031
Token under
Token ID739
Feature activation+4.77e-01

Pos logit contributions
inkle+0.018
itating+0.018
shadow+0.017
rig+0.017
 ours+0.016
Neg logit contributions
 bear-0.023
 bears-0.022
 robbers-0.022
 mice-0.022
 squirrel-0.021
Token arrest
Token ID3251
Feature activation+3.43e+00

Pos logit contributions
 bear+0.013
 servant+0.013
 robbers+0.013
pill+0.012
 bears+0.012
Neg logit contributions
inkle-0.024
 ours-0.024
?",-0.023
?!"-0.023
ews-0.023
Token!"
Token ID2474
Feature activation-1.71e-01

Pos logit contributions
 robbers+0.207
 bear+0.205
 bears+0.199
 mice+0.199
 rabbits+0.197
Neg logit contributions
inkle-0.074
itating-0.068
?",-0.066
rig-0.064
shadow-0.064
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
inkle+0.011
itating+0.011
rated+0.010
rig+0.010
ossom+0.010
Neg logit contributions
 bear-0.004
 squirrel-0.004
 mice-0.004
 robbers-0.004
B-0.004
Token
Token ID198
Feature activation+7.72e-02

Pos logit contributions
 bear+0.005
B+0.005
 robbers+0.005
 mice+0.005
 squirrel+0.005
Neg logit contributions
inkle-0.008
itating-0.008
rig-0.008
shadow-0.008
ews-0.008
TokenTheir
Token ID14574
Feature activation+1.82e-01

Pos logit contributions
 bear+0.003
 robbers+0.003
 bears+0.003
 mice+0.003
 squirrel+0.003
Neg logit contributions
inkle-0.004
itating-0.004
rig-0.004
shadow-0.003
ews-0.003
Token mom
Token ID1995
Feature activation-2.68e-01

Pos logit contributions
pill+0.010
orns+0.009
B+0.008
emaker+0.008
pillar+0.008
Neg logit contributions
inkle-0.005
rig-0.005
 common-0.005
ews-0.005
har-0.005
Token-
Token ID12
Feature activation+1.47e+00

Pos logit contributions
 bear+0.065
 bears+0.063
 mice+0.061
 robbers+0.060
 rabbits+0.059
Neg logit contributions
itating-0.073
rig-0.069
inkle-0.068
shadow-0.067
ews-0.065
Tokenfour
Token ID14337
Feature activation+1.72e+00

Pos logit contributions
 bear+0.072
 robbers+0.070
 bears+0.069
 mice+0.068
 rabbits+0.067
Neg logit contributions
itating-0.053
inkle-0.052
rig-0.051
shadow-0.049
ews-0.048
Token,
Token ID11
Feature activation+1.42e+00

Pos logit contributions
 bear+0.066
 robbers+0.063
 bears+0.063
 mice+0.062
 rabbits+0.060
Neg logit contributions
itating-0.080
inkle-0.079
rig-0.077
shadow-0.076
ews-0.074
Token twenty
Token ID8208
Feature activation+2.18e+00

Pos logit contributions
 bear+0.058
 bears+0.055
 robbers+0.054
 mice+0.053
 squirrel+0.053
Neg logit contributions
itating-0.065
inkle-0.063
rig-0.063
ews-0.060
shadow-0.060
Token-
Token ID12
Feature activation+1.84e+00

Pos logit contributions
 bear+0.086
 bears+0.083
 robbers+0.081
 mice+0.080
 squirrel+0.078
Neg logit contributions
itating-0.101
inkle-0.097
rig-0.096
shadow-0.094
ews-0.092
Tokenfive
Token ID13261
Feature activation+3.43e+00

Pos logit contributions
 bear+0.086
 robbers+0.084
 bears+0.083
 mice+0.082
 rabbits+0.080
Neg logit contributions
itating-0.070
inkle-0.069
rig-0.067
shadow-0.065
ews-0.064
Token,
Token ID11
Feature activation+1.08e+00

Pos logit contributions
 bear+0.134
 robbers+0.130
 bears+0.128
 mice+0.126
 rabbits+0.123
Neg logit contributions
itating-0.156
inkle-0.155
rig-0.151
shadow-0.147
ews-0.146
Token twenty
Token ID8208
Feature activation+1.76e+00

Pos logit contributions
 bear+0.042
 bears+0.041
 robbers+0.039
 squirrel+0.039
 rabbits+0.038
Neg logit contributions
itating-0.052
rig-0.050
inkle-0.050
ews-0.047
shadow-0.047
Token-
Token ID12
Feature activation+1.53e+00

Pos logit contributions
 bear+0.067
 bears+0.065
 mice+0.063
 robbers+0.062
 rabbits+0.061
Neg logit contributions
itating-0.085
rig-0.080
inkle-0.079
shadow-0.079
ews-0.076
Tokensix
Token ID19412
Feature activation+9.09e-01

Pos logit contributions
 bear+0.073
 robbers+0.071
 bears+0.070
 mice+0.069
 squirrel+0.068
Neg logit contributions
itating-0.057
inkle-0.056
rig-0.054
shadow-0.052
ews-0.052
Token,
Token ID11
Feature activation+7.80e-01

Pos logit contributions
 robbers+0.038
 bear+0.038
 mice+0.036
B+0.036
 bears+0.036
Neg logit contributions
inkle-0.038
itating-0.035
ews-0.035
?",-0.035
rig-0.034
Token two
Token ID734
Feature activation+1.17e+00

Pos logit contributions
 bear+0.010
 robbers+0.010
 bears+0.010
 mice+0.010
 rabbits+0.009
Neg logit contributions
itating-0.013
inkle-0.013
rig-0.013
shadow-0.013
ews-0.013
Token and
Token ID290
Feature activation+1.37e+00

Pos logit contributions
 robbers+0.045
 bear+0.044
 villains+0.043
 servant+0.042
 bears+0.041
Neg logit contributions
inkle-0.054
itating-0.051
ews-0.050
rig-0.047
?",-0.046
Token became
Token ID2627
Feature activation+1.03e+00

Pos logit contributions
 bear+0.054
 robbers+0.053
 bears+0.051
 mice+0.050
 squirrel+0.049
Neg logit contributions
itating-0.058
inkle-0.058
ews-0.056
rig-0.056
shadow-0.055
Token two
Token ID734
Feature activation+1.34e+00

Pos logit contributions
 bear+0.044
 robbers+0.043
 bears+0.042
 squirrel+0.040
 mice+0.040
Neg logit contributions
itating-0.042
inkle-0.041
rig-0.040
ews-0.039
shadow-0.039
Token b
Token ID275
Feature activation+1.49e+00

Pos logit contributions
 robbers+0.047
B+0.044
 bear+0.044
 villains+0.043
Carl+0.041
Neg logit contributions
inkle-0.065
itating-0.062
ews-0.060
rig-0.060
ossom-0.056
Tokenunn
Token ID20935
Feature activation+3.38e+00

Pos logit contributions
 bear+0.056
 robbers+0.051
 bears+0.048
 villains+0.048
 monster+0.047
Neg logit contributions
inkle-0.073
ews-0.073
rig-0.073
ossom-0.073
ist-0.070
Tokenies
Token ID444
Feature activation+3.38e-01

Pos logit contributions
 bear+0.189
 robbers+0.187
 villains+0.180
B+0.179
 squirrel+0.178
Neg logit contributions
inkle-0.086
itating-0.086
ews-0.083
rig-0.082
ossom-0.079
Token.
Token ID13
Feature activation+3.87e-01

Pos logit contributions
 robbers+0.013
 bear+0.012
 villains+0.012
 bears+0.012
B+0.012
Neg logit contributions
itating-0.015
inkle-0.014
rig-0.014
shadow-0.014
ews-0.014
Token "
Token ID366
Feature activation-4.93e-01

Pos logit contributions
 bear+0.015
 mice+0.015
 robbers+0.015
 bears+0.014
 rabbits+0.014
Neg logit contributions
inkle-0.019
itating-0.018
rig-0.017
shadow-0.017
?",-0.017
TokenWow
Token ID22017
Feature activation+1.58e+00

Pos logit contributions
inkle+0.023
itating+0.022
rig+0.022
ews+0.021
shadow+0.021
Neg logit contributions
 bear-0.020
 robbers-0.019
 bears-0.019
 mice-0.019
 squirrel-0.018
Token,
Token ID11
Feature activation+7.75e-01

Pos logit contributions
 bear+0.064
 bears+0.061
 robbers+0.060
 mice+0.059
 rabbits+0.058
Neg logit contributions
itating-0.072
rig-0.071
inkle-0.069
ews-0.067
shadow-0.067
Token lesson
Token ID11483
Feature activation-2.13e-01

Pos logit contributions
itating+0.009
inkle+0.009
shadow+0.008
ews+0.008
rig+0.008
Neg logit contributions
 bear-0.008
 squirrel-0.007
 robbers-0.007
 bears-0.007
 mice-0.007
Token that
Token ID326
Feature activation-1.50e-01

Pos logit contributions
itating+0.009
inkle+0.009
rig+0.009
shadow+0.009
ews+0.009
Neg logit contributions
 bear-0.009
 robbers-0.008
 bears-0.008
 mice-0.008
 rabbits-0.008
Token day
Token ID1110
Feature activation-3.94e-01

Pos logit contributions
itating+0.008
inkle+0.008
rig+0.007
shadow+0.007
ews+0.007
Neg logit contributions
 bear-0.005
 robbers-0.005
 bears-0.005
 mice-0.005
 rabbits-0.005
Token and
Token ID290
Feature activation+3.77e-02

Pos logit contributions
itating+0.019
inkle+0.019
rig+0.019
shadow+0.018
ews+0.018
Neg logit contributions
 bear-0.014
 robbers-0.013
 bears-0.013
 mice-0.013
 rabbits-0.013
Token never
Token ID1239
Feature activation+1.48e-01

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 mice+0.001
 rabbits+0.001
Neg logit contributions
itating-0.002
inkle-0.002
rig-0.002
shadow-0.002
ews-0.002
Token che
Token ID1125
Feature activation+3.31e+00

Pos logit contributions
 bears+0.006
 bear+0.006
 mice+0.006
 robbers+0.006
B+0.006
Neg logit contributions
shadow-0.006
itating-0.006
rig-0.006
?",-0.006
inkle-0.005
Tokenwed
Token ID19103
Feature activation+9.76e-01

Pos logit contributions
 bear+0.120
 bears+0.115
 robbers+0.115
 mice+0.113
 rabbits+0.109
Neg logit contributions
itating-0.162
inkle-0.158
rig-0.156
shadow-0.152
ews-0.150
Token on
Token ID319
Feature activation+8.07e-02

Pos logit contributions
 bear+0.039
 bears+0.037
 mice+0.037
 robbers+0.036
 rabbits+0.035
Neg logit contributions
itating-0.046
rig-0.045
inkle-0.045
shadow-0.043
ews-0.043
Token things
Token ID1243
Feature activation+3.13e-01

Pos logit contributions
 bear+0.003
 robbers+0.003
 bears+0.003
 mice+0.003
 rabbits+0.003
Neg logit contributions
inkle-0.004
itating-0.004
rig-0.004
shadow-0.004
ews-0.003
Token that
Token ID326
Feature activation+2.57e-01

Pos logit contributions
 bear+0.013
 robbers+0.013
 bears+0.012
 mice+0.012
 squirrel+0.012
Neg logit contributions
inkle-0.013
itating-0.013
rig-0.013
ews-0.013
shadow-0.013
Token were
Token ID547
Feature activation+8.63e-01

Pos logit contributions
 bear+0.010
 robbers+0.010
 bears+0.010
 mice+0.009
 rabbits+0.009
Neg logit contributions
inkle-0.012
itating-0.011
rig-0.011
shadow-0.011
?",-0.011
Token could
Token ID714
Feature activation+8.24e-01

Pos logit contributions
 bear+0.028
 robbers+0.028
 bears+0.027
 mice+0.026
 rabbits+0.025
Neg logit contributions
inkle-0.046
itating-0.046
rig-0.044
shadow-0.043
ews-0.043
Token see
Token ID766
Feature activation-4.21e-01

Pos logit contributions
 bear+0.034
 bears+0.032
 robbers+0.032
 mice+0.032
 squirrel+0.031
Neg logit contributions
itating-0.036
inkle-0.035
rig-0.035
shadow-0.035
ews-0.034
Token lots
Token ID6041
Feature activation+9.59e-01

Pos logit contributions
itating+0.018
inkle+0.018
rig+0.017
shadow+0.017
ews+0.016
Neg logit contributions
 robbers-0.018
 bear-0.017
 villains-0.016
 bears-0.016
 mice-0.016
Token of
Token ID286
Feature activation+7.28e-01

Pos logit contributions
 robbers+0.039
 bear+0.038
 bears+0.036
 villains+0.035
 mice+0.035
Neg logit contributions
itating-0.042
inkle-0.042
rig-0.042
shadow-0.039
ews-0.039
Token av
Token ID1196
Feature activation+2.91e+00

Pos logit contributions
 bear+0.031
 robbers+0.031
 bears+0.029
 mice+0.028
 villains+0.028
Neg logit contributions
inkle-0.030
itating-0.030
rig-0.029
?",-0.028
shadow-0.028
Tokenoc
Token ID420
Feature activation+3.30e+00

Pos logit contributions
 bear+0.100
 robbers+0.098
 villains+0.096
 bears+0.093
 rabbits+0.088
Neg logit contributions
inkle-0.148
itating-0.140
shadow-0.140
ossom-0.138
mmm-0.136
Tokenados
Token ID22484
Feature activation+7.20e-01

Pos logit contributions
 bear+0.139
 villains+0.138
 robbers+0.134
B+0.127
 rac+0.126
Neg logit contributions
mmm-0.143
inkle-0.133
ews-0.130
shadow-0.126
har-0.124
Token that
Token ID326
Feature activation+3.02e-01

Pos logit contributions
 bear+0.027
 robbers+0.027
 bears+0.025
 mice+0.025
 villains+0.025
Neg logit contributions
itating-0.034
inkle-0.033
rig-0.032
shadow-0.032
ews-0.031
Token the
Token ID262
Feature activation-2.44e-02

Pos logit contributions
 bear+0.009
 robbers+0.009
 bears+0.009
 mice+0.009
 rabbits+0.008
Neg logit contributions
itating-0.016
inkle-0.016
rig-0.016
shadow-0.015
ews-0.015
Token supplier
Token ID22693
Feature activation+2.38e-01

Pos logit contributions
inkle+0.001
itating+0.001
?",+0.001
rig+0.001
 ours+0.001
Neg logit contributions
 bears-0.001
B-0.001
 villains-0.001
 robbers-0.001
 bear-0.001
Token had
Token ID550
Feature activation+6.07e-01

Pos logit contributions
 bear+0.007
 robbers+0.007
 bears+0.007
 mice+0.007
 rabbits+0.006
Neg logit contributions
itating-0.013
inkle-0.013
rig-0.013
shadow-0.012
ews-0.012
Token not
Token ID407
Feature activation+6.12e-02

Pos logit contributions
inkle+0.005
itating+0.005
ews+0.005
rig+0.005
ossom+0.004
Neg logit contributions
 bear-0.006
 robbers-0.006
 bears-0.005
 mice-0.005
 rabbits-0.005
Token as
Token ID355
Feature activation+8.45e-01

Pos logit contributions
 bear+0.003
 robbers+0.003
 bears+0.003
 mice+0.002
 rabbits+0.002
Neg logit contributions
itating-0.002
inkle-0.002
rig-0.002
shadow-0.002
ews-0.002
Token important
Token ID1593
Feature activation+2.28e+00

Pos logit contributions
 bear+0.036
 robbers+0.035
 bears+0.035
 mice+0.034
 rabbits+0.033
Neg logit contributions
itating-0.035
inkle-0.035
rig-0.034
shadow-0.033
ews-0.032
Token as
Token ID355
Feature activation+9.06e-01

Pos logit contributions
 bear+0.092
 robbers+0.088
 bears+0.087
 mice+0.085
 squirrel+0.084
Neg logit contributions
itating-0.100
inkle-0.099
rig-0.097
shadow-0.094
ews-0.093
Token being
Token ID852
Feature activation+2.45e+00

Pos logit contributions
 bear+0.037
 robbers+0.035
 bears+0.035
 squirrel+0.033
 mice+0.033
Neg logit contributions
inkle-0.039
itating-0.038
rig-0.037
shadow-0.036
ews-0.036
Token kind
Token ID1611
Feature activation+3.27e+00

Pos logit contributions
 bear+0.097
 robbers+0.094
 bears+0.093
 mice+0.093
 rabbits+0.090
Neg logit contributions
itating-0.112
inkle-0.111
rig-0.109
shadow-0.106
ews-0.105
Token.
Token ID13
Feature activation-4.43e-01

Pos logit contributions
 bear+0.153
 robbers+0.151
 bears+0.147
Carl+0.141
 squirrel+0.141
Neg logit contributions
itating-0.114
rig-0.107
inkle-0.105
 yet-0.102
ews-0.101
Token They
Token ID1119
Feature activation+1.92e-01

Pos logit contributions
inkle+0.022
itating+0.022
rig+0.021
shadow+0.021
ews+0.020
Neg logit contributions
 bear-0.016
 mice-0.015
 robbers-0.015
 squirrel-0.015
 bears-0.015
Token learned
Token ID4499
Feature activation+1.43e+00

Pos logit contributions
 robbers+0.009
 bears+0.009
 mice+0.009
 bear+0.008
 skeletons+0.008
Neg logit contributions
itating-0.007
inkle-0.006
rig-0.006
?",-0.006
ossom-0.006
Token that
Token ID326
Feature activation-2.43e-01

Pos logit contributions
 bear+0.042
 mice+0.039
 squirrel+0.039
 bears+0.037
 robbers+0.037
Neg logit contributions
inkle-0.084
itating-0.081
shadow-0.079
ews-0.078
rated-0.078
Token a
Token ID257
Feature activation-2.21e-01

Pos logit contributions
itating+0.010
inkle+0.010
shadow+0.009
rig+0.009
?",+0.009
Neg logit contributions
 bear-0.010
 robbers-0.010
 bears-0.010
 mice-0.009
 rabbits-0.009
Token friendly
Token ID8030
Feature activation+8.36e-01

Pos logit contributions
apers+0.030
inkle+0.030
ews+0.029
itating+0.029
ist+0.028
Neg logit contributions
 bear-0.031
 squirrel-0.030
 robbers-0.029
 rabbits-0.029
 rac-0.028
Token and
Token ID290
Feature activation+4.67e-01

Pos logit contributions
 robbers+0.042
 bear+0.041
 villains+0.040
 bears+0.040
 mice+0.039
Neg logit contributions
itating-0.025
rig-0.024
 yet-0.023
?",-0.023
inkle-0.023
Token asked
Token ID1965
Feature activation+1.13e+00

Pos logit contributions
 bear+0.017
 robbers+0.016
 bears+0.016
 mice+0.016
 rabbits+0.015
Neg logit contributions
itating-0.022
inkle-0.022
rig-0.022
shadow-0.021
ews-0.021
Token the
Token ID262
Feature activation+9.15e-01

Pos logit contributions
 robbers+0.049
 bear+0.048
pill+0.048
 villains+0.047
 mice+0.045
Neg logit contributions
shadow-0.040
?",-0.039
itating-0.039
inkle-0.039
 yet-0.038
Token l
Token ID300
Feature activation+2.02e+00

Pos logit contributions
emaker+0.035
Mic+0.033
ted+0.033
 shields+0.033
 robbers+0.033
Neg logit contributions
itating-0.039
 higher-0.035
rig-0.035
 common-0.035
 early-0.033
Tokenitt
Token ID715
Feature activation+3.26e+00

Pos logit contributions
 robbers+0.094
 bear+0.091
 bears+0.089
 mice+0.085
 shields+0.083
Neg logit contributions
itating-0.084
inkle-0.084
ossom-0.082
rig-0.077
ues-0.076
Tokenler
Token ID1754
Feature activation+3.81e-01

Pos logit contributions
 robbers+0.142
 bear+0.135
 mice+0.132
 villains+0.129
 bears+0.128
Neg logit contributions
inkle-0.136
itating-0.135
rig-0.127
shadow-0.126
ossom-0.124
Token frog
Token ID21264
Feature activation+1.17e+00

Pos logit contributions
 robbers+0.014
 bear+0.014
 bears+0.014
 mice+0.014
 villains+0.013
Neg logit contributions
itating-0.017
inkle-0.017
rig-0.017
shadow-0.016
ews-0.016
Token to
Token ID284
Feature activation+9.84e-01

Pos logit contributions
 robbers+0.054
 bear+0.053
 mice+0.051
 bears+0.051
 villains+0.051
Neg logit contributions
itating-0.044
rig-0.042
inkle-0.042
shadow-0.041
ossom-0.039
Token join
Token ID4654
Feature activation-6.44e-02

Pos logit contributions
 bear+0.038
 bears+0.037
 robbers+0.037
 mice+0.037
 villains+0.035
Neg logit contributions
itating-0.043
inkle-0.043
rig-0.042
shadow-0.041
?",-0.040
Token them
Token ID606
Feature activation-2.08e-01

Pos logit contributions
itating+0.003
inkle+0.003
?",+0.003
rig+0.003
shadow+0.003
Neg logit contributions
 robbers-0.002
 bear-0.002
 villains-0.002
 mice-0.002
 bears-0.002
Token's
Token ID338
Feature activation+5.23e-01

Pos logit contributions
 robbers+0.007
 bear+0.007
 bears+0.007
 mice+0.006
 rabbits+0.006
Neg logit contributions
itating-0.011
inkle-0.010
rig-0.010
shadow-0.010
ews-0.010
Token okay
Token ID8788
Feature activation-9.39e-02

Pos logit contributions
 bear+0.027
 robbers+0.026
 bears+0.026
 mice+0.026
 rabbits+0.025
Neg logit contributions
itating-0.019
inkle-0.018
rig-0.017
ews-0.017
shadow-0.016
Token to
Token ID284
Feature activation+6.53e-01

Pos logit contributions
itating+0.004
inkle+0.004
rig+0.004
shadow+0.004
ews+0.004
Neg logit contributions
 bear-0.004
 bears-0.004
 mice-0.004
 robbers-0.004
 squirrel-0.004
Token ask
Token ID1265
Feature activation+1.65e+00

Pos logit contributions
 bear+0.027
 robbers+0.026
 squirrel+0.025
 mice+0.024
 rabbits+0.024
Neg logit contributions
itating-0.030
inkle-0.030
rig-0.029
ews-0.029
shadow-0.028
Token for
Token ID329
Feature activation+4.03e-01

Pos logit contributions
 bear+0.063
 mice+0.063
 bears+0.060
 robbers+0.060
 rabbits+0.059
Neg logit contributions
itating-0.084
inkle-0.080
rig-0.079
ews-0.075
ossom-0.075
Token help
Token ID1037
Feature activation+3.25e+00

Pos logit contributions
pill+0.012
 bear+0.012
 bears+0.011
 rabbits+0.011
Carl+0.011
Neg logit contributions
shadow-0.020
inkle-0.020
?",-0.020
 yet-0.020
 early-0.019
Token when
Token ID618
Feature activation+4.71e-01

Pos logit contributions
 bear+0.137
 mice+0.130
 bears+0.130
 robbers+0.130
 rabbits+0.125
Neg logit contributions
itating-0.144
inkle-0.144
rig-0.140
shadow-0.135
ews-0.134
Token she
Token ID673
Feature activation+6.52e-01

Pos logit contributions
 bear+0.019
 robbers+0.018
 bears+0.018
 mice+0.018
 rabbits+0.018
Neg logit contributions
itating-0.021
inkle-0.021
rig-0.021
shadow-0.020
ews-0.019
Token needs
Token ID2476
Feature activation+1.06e+00

Pos logit contributions
 robbers+0.027
 rabbits+0.025
 villains+0.025
B+0.025
 bears+0.025
Neg logit contributions
inkle-0.029
?",-0.028
?"-0.025
rig-0.025
?'-0.025
Token it
Token ID340
Feature activation+2.16e-01

Pos logit contributions
 bear+0.048
 robbers+0.047
 bears+0.047
 mice+0.046
 rabbits+0.045
Neg logit contributions
itating-0.041
inkle-0.041
rig-0.040
shadow-0.039
ews-0.038
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
 bear+0.007
 robbers+0.007
 bears+0.007
 mice+0.007
 rabbits+0.006
Neg logit contributions
itating-0.011
inkle-0.011
rig-0.011
shadow-0.011
ews-0.011
Token Sara
Token ID24799
Feature activation-2.14e-02

Pos logit contributions
 bear+0.037
 robbers+0.036
 bears+0.036
 mice+0.035
 rabbits+0.035
Neg logit contributions
inkle-0.033
itating-0.033
shadow-0.032
rig-0.032
?",-0.031
Token,
Token ID11
Feature activation+5.53e-01

Pos logit contributions
inkle+0.001
itating+0.001
rig+0.001
shadow+0.001
ews+0.001
Neg logit contributions
 robbers-0.001
 bear-0.001
 bears-0.001
 mice-0.001
 rabbits-0.001
Token I
Token ID314
Feature activation+2.59e-01

Pos logit contributions
 bear+0.024
 robbers+0.024
 bears+0.023
 mice+0.023
 rabbits+0.022
Neg logit contributions
itating-0.022
inkle-0.022
rig-0.021
shadow-0.021
?",-0.020
Token have
Token ID423
Feature activation+3.78e-01

Pos logit contributions
 bear+0.010
 robbers+0.009
 bears+0.009
 mice+0.009
 squirrel+0.009
Neg logit contributions
itating-0.013
rig-0.012
inkle-0.012
shadow-0.012
ews-0.012
Token grape
Token ID30777
Feature activation+6.57e-02

Pos logit contributions
 bear+0.016
 robbers+0.015
 bears+0.015
 mice+0.014
 villains+0.014
Neg logit contributions
inkle-0.016
itating-0.016
ews-0.015
rig-0.015
shadow-0.015
Token ear
Token ID1027
Feature activation+3.24e+00

Pos logit contributions
 bear+0.002
 robbers+0.002
 villains+0.002
 bears+0.002
 rac+0.002
Neg logit contributions
inkle-0.003
itating-0.003
?",-0.003
ossom-0.003
rig-0.003
Tokenrings
Token ID33173
Feature activation-7.22e-03

Pos logit contributions
 bear+0.111
 bears+0.105
 mice+0.105
 rabbits+0.103
 squirrel+0.101
Neg logit contributions
rig-0.169
itating-0.165
inkle-0.163
shadow-0.158
ews-0.154
Token.
Token ID13
Feature activation-5.87e-02

Pos logit contributions
itating+0.000
inkle+0.000
rig+0.000
shadow+0.000
ews+0.000
Neg logit contributions
 bear-0.000
 bears-0.000
 robbers-0.000
 mice-0.000
 rabbits-0.000
Token They
Token ID1119
Feature activation+2.95e-01

Pos logit contributions
inkle+0.003
itating+0.003
rig+0.003
shadow+0.003
ews+0.002
Neg logit contributions
 bear-0.002
 mice-0.002
 robbers-0.002
 bears-0.002
 squirrel-0.002
Token are
Token ID389
Feature activation+1.58e-01

Pos logit contributions
 bear+0.008
 bears+0.008
 mice+0.008
 squirrel+0.007
 robbers+0.007
Neg logit contributions
rig-0.017
itating-0.017
shadow-0.017
inkle-0.017
ews-0.017
Token round
Token ID2835
Feature activation+7.02e-01

Pos logit contributions
 bear+0.007
 bears+0.006
 mice+0.006
 rabbits+0.006
 robbers+0.006
Neg logit contributions
itating-0.007
rig-0.007
inkle-0.007
shadow-0.007
ews-0.007
Token not
Token ID407
Feature activation+1.31e-01

Pos logit contributions
 bear+0.020
 bears+0.018
 robbers+0.018
 mice+0.018
 rabbits+0.018
Neg logit contributions
itating-0.021
rig-0.020
inkle-0.020
ews-0.019
ossom-0.019
Token as
Token ID355
Feature activation+1.01e+00

Pos logit contributions
 bear+0.006
 robbers+0.006
 bears+0.006
 mice+0.006
 rabbits+0.006
Neg logit contributions
itating-0.005
inkle-0.005
rig-0.005
ews-0.005
shadow-0.005
Token important
Token ID1593
Feature activation+2.26e+00

Pos logit contributions
 bear+0.047
 robbers+0.046
 bears+0.045
 mice+0.045
 rabbits+0.044
Neg logit contributions
itating-0.039
inkle-0.039
rig-0.038
shadow-0.037
ews-0.036
Token as
Token ID355
Feature activation+1.06e+00

Pos logit contributions
 bear+0.123
 robbers+0.116
 bears+0.116
 mice+0.114
 squirrel+0.113
Neg logit contributions
inkle-0.063
shadow-0.062
rig-0.062
itating-0.062
 yet-0.061
Token having
Token ID1719
Feature activation+1.62e+00

Pos logit contributions
 bear+0.045
 bears+0.043
 robbers+0.043
 mice+0.042
 squirrel+0.041
Neg logit contributions
inkle-0.041
shadow-0.041
rig-0.040
itating-0.040
 ours-0.039
Token kind
Token ID1611
Feature activation+3.24e+00

Pos logit contributions
 bear+0.071
 robbers+0.067
 bears+0.066
 servant+0.064
 mice+0.064
Neg logit contributions
inkle-0.061
itating-0.058
rig-0.058
shadow-0.058
ews-0.057
Token and
Token ID290
Feature activation+9.66e-01

Pos logit contributions
 bear+0.156
 robbers+0.148
Carl+0.146
 bears+0.145
B+0.141
Neg logit contributions
itating-0.104
inkle-0.102
rig-0.102
 yet-0.099
ews-0.098
Token helpful
Token ID7613
Feature activation+2.20e+00

Pos logit contributions
 bear+0.048
 bears+0.046
 mice+0.045
 robbers+0.045
 rabbits+0.045
Neg logit contributions
shadow-0.032
itating-0.032
rig-0.031
inkle-0.030
 ours-0.029
Token friends
Token ID2460
Feature activation+9.64e-01

Pos logit contributions
 bear+0.094
Carl+0.091
 robbers+0.090
 bears+0.088
B+0.087
Neg logit contributions
itating-0.078
rig-0.078
 yet-0.077
inkle-0.076
 ours-0.075
Token like
Token ID588
Feature activation-1.09e+00

Pos logit contributions
 bear+0.037
 robbers+0.035
 bears+0.035
 mice+0.035
 rabbits+0.034
Neg logit contributions
itating-0.044
inkle-0.042
rig-0.042
shadow-0.041
?",-0.041
Token the
Token ID262
Feature activation+2.76e-01

Pos logit contributions
 yet+0.042
inkle+0.041
 ours+0.041
?",+0.041
itating+0.040
Neg logit contributions
 bear-0.042
 robbers-0.041
Carl-0.040
 bears-0.040
B-0.039
Token not
Token ID407
Feature activation+1.43e-02

Pos logit contributions
inkle+0.008
itating+0.008
rig+0.008
ews+0.008
ossom+0.007
Neg logit contributions
 bear-0.009
 robbers-0.009
 bears-0.009
 mice-0.009
 rabbits-0.009
Token as
Token ID355
Feature activation+7.97e-01

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 mice+0.001
 rabbits+0.001
Neg logit contributions
itating-0.001
inkle-0.001
rig-0.001
shadow-0.001
ews-0.001
Token important
Token ID1593
Feature activation+2.21e+00

Pos logit contributions
 bear+0.035
 bears+0.033
 robbers+0.033
 mice+0.032
 rabbits+0.032
Neg logit contributions
itating-0.031
inkle-0.031
rig-0.031
shadow-0.030
ews-0.029
Token as
Token ID355
Feature activation+8.48e-01

Pos logit contributions
 bear+0.102
 robbers+0.095
 bears+0.094
 squirrel+0.092
 mice+0.091
Neg logit contributions
inkle-0.083
itating-0.082
rig-0.081
shadow-0.078
ews-0.078
Token being
Token ID852
Feature activation+2.34e+00

Pos logit contributions
 bear+0.035
 bears+0.032
 robbers+0.032
 squirrel+0.031
 mice+0.031
Neg logit contributions
inkle-0.036
rig-0.035
itating-0.034
shadow-0.034
 ours-0.034
Token kind
Token ID1611
Feature activation+3.24e+00

Pos logit contributions
 bear+0.091
 robbers+0.087
 bears+0.086
 mice+0.084
 squirrel+0.082
Neg logit contributions
itating-0.107
inkle-0.106
rig-0.104
shadow-0.101
ews-0.100
Token and
Token ID290
Feature activation+6.84e-01

Pos logit contributions
 bear+0.146
 robbers+0.143
 bears+0.139
Carl+0.138
B+0.135
Neg logit contributions
itating-0.113
 yet-0.107
rig-0.107
inkle-0.104
ews-0.102
Token friendly
Token ID8030
Feature activation+1.84e+00

Pos logit contributions
 bear+0.033
 bears+0.032
 robbers+0.031
 mice+0.031
 rabbits+0.031
Neg logit contributions
itating-0.024
shadow-0.024
rig-0.023
inkle-0.023
 ours-0.021
Token.
Token ID13
Feature activation-4.83e-01

Pos logit contributions
 robbers+0.073
 bear+0.073
Carl+0.071
Mic+0.068
B+0.068
Neg logit contributions
 yet-0.071
itating-0.069
rig-0.066
inkle-0.065
?",-0.064
Token They
Token ID1119
Feature activation+1.85e-01

Pos logit contributions
inkle+0.022
itating+0.022
rig+0.022
shadow+0.021
ews+0.021
Neg logit contributions
 bear-0.019
 robbers-0.018
 mice-0.018
 bears-0.018
 squirrel-0.018
Token became
Token ID2627
Feature activation+1.17e-01

Pos logit contributions
 robbers+0.008
 mice+0.007
 bears+0.007
 bear+0.007
 skeletons+0.007
Neg logit contributions
itating-0.007
inkle-0.007
rig-0.007
?",-0.007
ossom-0.006
Token cops
Token ID14073
Feature activation+5.80e-01

Pos logit contributions
 yet+0.029
?",+0.026
 ours+0.026
?!"+0.025
shadow+0.025
Neg logit contributions
 robbers-0.049
 villains-0.047
Carl-0.047
 servant-0.047
pill-0.047
Token.
Token ID13
Feature activation+4.12e-01

Pos logit contributions
 bear+0.025
 robbers+0.024
 bears+0.024
 mice+0.024
 rabbits+0.023
Neg logit contributions
itating-0.024
inkle-0.024
rig-0.023
shadow-0.022
ews-0.022
Token They
Token ID1119
Feature activation+2.67e-01

Pos logit contributions
 bear+0.017
 robbers+0.017
 bears+0.016
 mice+0.016
 squirrel+0.016
Neg logit contributions
inkle-0.019
itating-0.018
rig-0.018
ews-0.017
shadow-0.017
Token take
Token ID1011
Feature activation+2.26e-01

Pos logit contributions
 bear+0.010
 robbers+0.009
 bears+0.009
 mice+0.009
 rabbits+0.009
Neg logit contributions
itating-0.013
inkle-0.013
rig-0.012
shadow-0.012
ews-0.012
Token b
Token ID275
Feature activation+1.08e+00

Pos logit contributions
 bear+0.010
 robbers+0.009
 bears+0.009
 mice+0.009
 rabbits+0.009
Neg logit contributions
inkle-0.009
itating-0.009
rig-0.009
shadow-0.009
ews-0.009
Tokenunn
Token ID20935
Feature activation+3.22e+00

Pos logit contributions
 bear+0.034
 bears+0.030
 robbers+0.030
 rabbits+0.029
 mice+0.028
Neg logit contributions
shadow-0.058
rig-0.058
itating-0.057
inkle-0.056
ews-0.056
Tokenies
Token ID444
Feature activation-2.19e-01

Pos logit contributions
 bear+0.166
 robbers+0.162
 squirrel+0.157
 bears+0.157
 mice+0.156
Neg logit contributions
itating-0.099
inkle-0.099
rig-0.097
shadow-0.094
ews-0.092
Token away
Token ID1497
Feature activation-5.49e-01

Pos logit contributions
inkle+0.009
itating+0.009
rig+0.009
ews+0.009
mmm+0.009
Neg logit contributions
 bear-0.010
 bears-0.009
 robbers-0.009
 mice-0.009
 rabbits-0.009
Token."
Token ID526
Feature activation-9.20e-02

Pos logit contributions
inkle+0.026
itating+0.025
rig+0.023
shadow+0.023
ews+0.023
Neg logit contributions
 bear-0.024
 bears-0.023
 mice-0.023
 rabbits-0.023
 robbers-0.022
Token
Token ID198
Feature activation+2.07e-01

Pos logit contributions
itating+0.004
inkle+0.004
rig+0.004
shadow+0.004
ews+0.004
Neg logit contributions
 bear-0.004
 robbers-0.004
 bears-0.004
 mice-0.004
 rabbits-0.004
Token
Token ID198
Feature activation+2.21e-01

Pos logit contributions
 bear+0.009
 robbers+0.009
 bears+0.009
 mice+0.008
 rabbits+0.008
Neg logit contributions
itating-0.009
inkle-0.009
rig-0.009
shadow-0.008
ews-0.008
Token not
Token ID407
Feature activation+9.15e-03

Pos logit contributions
 bear+0.011
 robbers+0.010
 bears+0.010
 mice+0.010
 rabbits+0.010
Neg logit contributions
ews-0.011
itating-0.010
inkle-0.010
rig-0.010
ossom-0.010
Token terrible
Token ID7818
Feature activation+1.06e-01

Pos logit contributions
 bear+0.000
 robbers+0.000
 mice+0.000
 bears+0.000
 rabbits+0.000
Neg logit contributions
inkle-0.000
itating-0.000
rig-0.000
ews-0.000
ossom-0.000
Token to
Token ID284
Feature activation+5.93e-01

Pos logit contributions
 bear+0.005
 robbers+0.005
 bears+0.005
 squirrel+0.004
 mice+0.004
Neg logit contributions
itating-0.004
inkle-0.004
rig-0.004
?",-0.004
shadow-0.004
Token ask
Token ID1265
Feature activation+1.80e+00

Pos logit contributions
 bear+0.024
 robbers+0.023
 bears+0.023
 mice+0.023
 rabbits+0.022
Neg logit contributions
itating-0.026
inkle-0.026
rig-0.025
shadow-0.025
ews-0.024
Token for
Token ID329
Feature activation+4.70e-01

Pos logit contributions
 bear+0.073
 mice+0.071
 robbers+0.070
 bears+0.070
 rabbits+0.069
Neg logit contributions
itating-0.084
inkle-0.082
rig-0.081
ews-0.077
shadow-0.077
Token help
Token ID1037
Feature activation+3.21e+00

Pos logit contributions
 bear+0.013
pill+0.012
 robbers+0.012
 bears+0.012
Carl+0.011
Neg logit contributions
inkle-0.025
shadow-0.025
?",-0.025
ews-0.024
itating-0.024
Token.
Token ID13
Feature activation+5.55e-01

Pos logit contributions
 bear+0.145
 robbers+0.140
 bears+0.139
 mice+0.139
 rabbits+0.136
Neg logit contributions
inkle-0.130
itating-0.129
rig-0.127
shadow-0.121
ews-0.121
Token Sometimes
Token ID8975
Feature activation-1.07e+00

Pos logit contributions
 bear+0.023
 mice+0.022
 bears+0.021
 robbers+0.021
 squirrel+0.021
Neg logit contributions
inkle-0.026
itating-0.025
rig-0.024
ews-0.024
shadow-0.023
Token,
Token ID11
Feature activation+3.70e-01

Pos logit contributions
inkle+0.046
itating+0.046
rig+0.045
shadow+0.044
ews+0.043
Neg logit contributions
 bear-0.044
 robbers-0.042
 bears-0.042
 mice-0.041
 rabbits-0.040
Token we
Token ID356
Feature activation+2.97e-01

Pos logit contributions
 mice+0.014
 bear+0.014
 rabbits+0.013
 bears+0.013
 squirrel+0.013
Neg logit contributions
rig-0.019
inkle-0.019
itating-0.018
ews-0.018
shadow-0.017
Token need
Token ID761
Feature activation+5.83e-02

Pos logit contributions
 bear+0.010
 robbers+0.009
 bears+0.009
 mice+0.009
 rabbits+0.009
Neg logit contributions
itating-0.015
inkle-0.015
rig-0.015
shadow-0.014
?",-0.014
Token bear
Token ID6842
Feature activation+7.01e-01

Pos logit contributions
 bear+0.007
 robbers+0.007
 bears+0.007
 mice+0.006
 rabbits+0.006
Neg logit contributions
inkle-0.043
itating-0.043
rig-0.042
shadow-0.042
ews-0.041
Token is
Token ID318
Feature activation-9.73e-03

Pos logit contributions
 bear+0.028
 robbers+0.027
 bears+0.027
 mice+0.026
 rabbits+0.026
Neg logit contributions
itating-0.031
inkle-0.031
rig-0.030
shadow-0.029
ews-0.029
Token deaf
Token ID21815
Feature activation+1.79e-01

Pos logit contributions
itating+0.000
rig+0.000
inkle+0.000
ews+0.000
shadow+0.000
Neg logit contributions
 bear-0.000
 bears-0.000
 robbers-0.000
 mice-0.000
 rabbits-0.000
Token in
Token ID287
Feature activation-3.56e-02

Pos logit contributions
 bear+0.006
 robbers+0.006
 bears+0.006
 mice+0.006
 rabbits+0.006
Neg logit contributions
itating-0.009
inkle-0.009
rig-0.009
shadow-0.008
ews-0.008
Token one
Token ID530
Feature activation-3.87e-01

Pos logit contributions
inkle+0.001
itating+0.001
rig+0.001
?",+0.001
 ours+0.001
Neg logit contributions
 bear-0.002
 robbers-0.002
 bears-0.002
 squirrel-0.002
 villains-0.001
Token ear
Token ID1027
Feature activation+3.21e+00

Pos logit contributions
itating+0.018
inkle+0.018
rig+0.017
shadow+0.017
ews+0.017
Neg logit contributions
 bear-0.015
 robbers-0.014
 bears-0.014
 mice-0.014
 rabbits-0.014
Token.
Token ID13
Feature activation+7.44e-02

Pos logit contributions
 bear+0.116
 bears+0.108
 robbers+0.106
 rabbits+0.103
 mice+0.103
Neg logit contributions
itating-0.158
inkle-0.158
rig-0.157
shadow-0.151
ews-0.144
Token That
Token ID1320
Feature activation+8.72e-01

Pos logit contributions
 bear+0.003
 robbers+0.003
 bears+0.003
 mice+0.003
 squirrel+0.003
Neg logit contributions
inkle-0.004
itating-0.004
rig-0.003
shadow-0.003
ews-0.003
Token means
Token ID1724
Feature activation-3.33e-01

Pos logit contributions
 bear+0.032
 bears+0.029
 robbers+0.029
 mice+0.028
 squirrel+0.028
Neg logit contributions
itating-0.045
inkle-0.044
rig-0.044
shadow-0.043
ews-0.042
Token it
Token ID340
Feature activation-1.63e-01

Pos logit contributions
itating+0.014
inkle+0.014
rig+0.014
shadow+0.013
ews+0.013
Neg logit contributions
 bear-0.014
 robbers-0.013
 bears-0.013
 mice-0.013
 rabbits-0.013
Token cannot
Token ID2314
Feature activation-4.04e-01

Pos logit contributions
itating+0.008
inkle+0.008
rig+0.008
shadow+0.007
ews+0.007
Neg logit contributions
 bear-0.006
 robbers-0.006
 bears-0.006
 mice-0.006
 rabbits-0.005
Token-
Token ID12
Feature activation+1.40e+00

Pos logit contributions
 bear+0.040
 robbers+0.040
 mice+0.039
 bears+0.039
 rabbits+0.038
Neg logit contributions
inkle-0.037
itating-0.036
rig-0.035
shadow-0.034
ews-0.034
Tokenfour
Token ID14337
Feature activation+1.58e+00

Pos logit contributions
 bear+0.070
 robbers+0.070
 mice+0.068
 rabbits+0.068
 bears+0.068
Neg logit contributions
shadow-0.047
itating-0.046
rig-0.046
inkle-0.045
ews-0.043
Token,
Token ID11
Feature activation+1.32e+00

Pos logit contributions
 bear+0.064
 robbers+0.063
 bears+0.061
 mice+0.060
 rabbits+0.059
Neg logit contributions
inkle-0.070
itating-0.069
rig-0.067
ews-0.065
shadow-0.064
Token forty
Token ID16571
Feature activation+1.40e+00

Pos logit contributions
 bear+0.053
 robbers+0.051
 bears+0.050
 mice+0.050
 rabbits+0.049
Neg logit contributions
itating-0.059
inkle-0.058
rig-0.057
shadow-0.056
ews-0.055
Token-
Token ID12
Feature activation+1.69e+00

Pos logit contributions
 bear+0.061
 robbers+0.060
 bears+0.058
 mice+0.058
 rabbits+0.057
Neg logit contributions
inkle-0.057
itating-0.056
rig-0.055
shadow-0.054
ews-0.053
Tokenfive
Token ID13261
Feature activation+3.20e+00

Pos logit contributions
 bear+0.086
 robbers+0.085
 bears+0.083
 mice+0.083
 rabbits+0.083
Neg logit contributions
itating-0.056
shadow-0.055
inkle-0.054
rig-0.054
ews-0.052
Token,
Token ID11
Feature activation+8.86e-01

Pos logit contributions
 bear+0.131
 robbers+0.127
 bears+0.125
 mice+0.123
 rabbits+0.121
Neg logit contributions
itating-0.140
inkle-0.139
rig-0.135
shadow-0.132
ews-0.130
Token forty
Token ID16571
Feature activation+1.05e+00

Pos logit contributions
 bear+0.033
 robbers+0.032
 bears+0.031
 mice+0.031
 rabbits+0.030
Neg logit contributions
itating-0.042
inkle-0.042
rig-0.041
shadow-0.040
ews-0.040
Token-
Token ID12
Feature activation+1.42e+00

Pos logit contributions
 bear+0.045
 robbers+0.045
 bears+0.043
 mice+0.043
 rabbits+0.043
Neg logit contributions
inkle-0.043
itating-0.042
rig-0.041
shadow-0.040
ews-0.040
Tokensix
Token ID19412
Feature activation+8.96e-01

Pos logit contributions
 bear+0.072
 robbers+0.071
 mice+0.070
 bears+0.070
 rabbits+0.070
Neg logit contributions
itating-0.047
shadow-0.046
rig-0.045
inkle-0.045
ews-0.043
Token,
Token ID11
Feature activation+5.85e-01

Pos logit contributions
 robbers+0.040
B+0.040
 bear+0.038
 mice+0.038
 villains+0.037
Neg logit contributions
inkle-0.035
ews-0.032
?",-0.032
itating-0.031
mmm-0.031
Token and
Token ID290
Feature activation+3.10e-01

Pos logit contributions
 bear+0.033
 robbers+0.031
 bears+0.031
 mice+0.030
 rabbits+0.030
Neg logit contributions
inkle-0.041
itating-0.041
rig-0.040
shadow-0.039
ews-0.039
Token asked
Token ID1965
Feature activation+1.00e+00

Pos logit contributions
 bear+0.010
 robbers+0.009
 bears+0.009
 squirrel+0.009
 mice+0.009
Neg logit contributions
inkle-0.017
itating-0.017
rig-0.017
shadow-0.016
ews-0.016
Token if
Token ID611
Feature activation+6.53e-01

Pos logit contributions
 bear+0.037
 robbers+0.036
 bears+0.035
 mice+0.034
 villains+0.034
Neg logit contributions
itating-0.047
inkle-0.046
rig-0.045
shadow-0.045
?",-0.044
Token it
Token ID340
Feature activation+1.30e+00

Pos logit contributions
 robbers+0.025
 bear+0.025
 bears+0.024
 mice+0.024
 villains+0.024
Neg logit contributions
itating-0.027
inkle-0.027
?",-0.027
shadow-0.026
ews-0.026
Token could
Token ID714
Feature activation+2.23e+00

Pos logit contributions
 robbers+0.046
 bear+0.042
 bears+0.042
 villains+0.042
 mice+0.042
Neg logit contributions
inkle-0.060
itating-0.059
?",-0.059
rig-0.058
shadow-0.057
Token help
Token ID1037
Feature activation+3.19e+00

Pos logit contributions
 bear+0.077
 robbers+0.070
 bears+0.070
 squirrel+0.069
 mice+0.069
Neg logit contributions
itating-0.116
rig-0.113
inkle-0.112
shadow-0.111
ews-0.111
Token her
Token ID607
Feature activation+6.53e-01

Pos logit contributions
 bear+0.092
 mice+0.085
 bears+0.084
 robbers+0.081
 squirrel+0.081
Neg logit contributions
itating-0.186
rig-0.183
inkle-0.183
ews-0.177
shadow-0.177
Token.
Token ID13
Feature activation+5.97e-01

Pos logit contributions
 bear+0.020
 bears+0.017
 squirrel+0.017
 mice+0.016
 rabbits+0.016
Neg logit contributions
itating-0.038
shadow-0.038
rig-0.038
inkle-0.038
apers-0.037
Token The
Token ID383
Feature activation-9.94e-02

Pos logit contributions
 bear+0.025
 robbers+0.024
 mice+0.024
 bears+0.023
 squirrel+0.023
Neg logit contributions
inkle-0.027
itating-0.026
rig-0.025
shadow-0.025
ews-0.024
Token tree
Token ID5509
Feature activation+6.53e-01

Pos logit contributions
itating+0.005
inkle+0.004
rig+0.004
?",+0.004
ews+0.004
Neg logit contributions
 robbers-0.004
 bears-0.004
 bear-0.004
 villains-0.003
 mice-0.003
Token said
Token ID531
Feature activation+2.70e-01

Pos logit contributions
 bear+0.024
 bears+0.022
 squirrel+0.022
 mice+0.021
 rabbits+0.021
Neg logit contributions
itating-0.033
inkle-0.032
rig-0.032
shadow-0.031
ews-0.031
Token was
Token ID373
Feature activation+3.60e-01

Pos logit contributions
itating+0.010
inkle+0.010
rig+0.010
shadow+0.010
ews+0.010
Neg logit contributions
 bear-0.007
 bears-0.007
 robbers-0.007
 mice-0.007
 rabbits-0.006
Token different
Token ID1180
Feature activation+7.92e-01

Pos logit contributions
 bear+0.015
 bears+0.014
 mice+0.014
 rabbits+0.014
 dragons+0.013
Neg logit contributions
itating-0.018
har-0.016
rig-0.016
shadow-0.016
ews-0.016
Token from
Token ID422
Feature activation+4.64e-02

Pos logit contributions
 bears+0.030
 bear+0.030
 mice+0.030
 rabbits+0.028
 robbers+0.027
Neg logit contributions
inkle-0.039
itating-0.039
shadow-0.038
rig-0.037
ews-0.036
Token what
Token ID644
Feature activation+1.07e+00

Pos logit contributions
 bear+0.002
 bears+0.002
 mice+0.002
 robbers+0.002
 rabbits+0.002
Neg logit contributions
itating-0.002
rig-0.002
inkle-0.002
shadow-0.002
ews-0.002
Token you
Token ID345
Feature activation-1.18e+00

Pos logit contributions
 bear+0.045
 robbers+0.044
 bears+0.042
 mice+0.041
 rabbits+0.040
Neg logit contributions
inkle-0.043
itating-0.043
?",-0.042
ews-0.041
rig-0.041
Token usually
Token ID3221
Feature activation-3.60e+00

Pos logit contributions
itating+0.061
inkle+0.059
rig+0.059
shadow+0.058
ews+0.057
Neg logit contributions
 bear-0.041
 robbers-0.039
 bears-0.038
 mice-0.037
 squirrel-0.036
Token do
Token ID466
Feature activation-5.59e-01

Pos logit contributions
itating+0.190
rig+0.183
shadow+0.181
inkle+0.178
ews+0.176
Neg logit contributions
 bear-0.122
 robbers-0.114
 bears-0.113
 mice-0.108
 squirrel-0.108
Token,"
Token ID553
Feature activation+4.10e-01

Pos logit contributions
rig+0.033
itating+0.032
har+0.031
ews+0.031
shadow+0.030
Neg logit contributions
 bear-0.016
 bears-0.015
 mice-0.014
 rabbits-0.013
 robbers-0.013
Token mom
Token ID1995
Feature activation-4.11e-01

Pos logit contributions
 robbers+0.021
 villains+0.020
pill+0.020
 skeletons+0.019
 seaw+0.019
Neg logit contributions
inkle-0.014
?",-0.012
 early-0.012
itating-0.012
shadow-0.011
Token said
Token ID531
Feature activation+2.30e-01

Pos logit contributions
itating+0.016
inkle+0.016
rig+0.015
shadow+0.015
ews+0.015
Neg logit contributions
 robbers-0.019
 bear-0.019
 mice-0.018
 bears-0.018
 rabbits-0.018
Token.
Token ID13
Feature activation-4.71e-02

Pos logit contributions
 bear+0.007
 robbers+0.007
 bears+0.007
 mice+0.006
 rabbits+0.006
Neg logit contributions
itating-0.013
inkle-0.012
rig-0.012
shadow-0.012
ews-0.012
Token the
Token ID262
Feature activation-5.13e-01

Pos logit contributions
rig+0.044
itating+0.044
ossom+0.043
shadow+0.043
ounded+0.041
Neg logit contributions
 bear-0.020
 bears-0.019
 t-0.018
 mice-0.017
 mar-0.017
Token boring
Token ID14262
Feature activation-1.48e+00

Pos logit contributions
itating+0.026
shadow+0.025
inkle+0.025
rig+0.025
ews+0.024
Neg logit contributions
 bear-0.020
 bears-0.018
 robbers-0.018
 mice-0.017
 rabbits-0.017
Token h
Token ID289
Feature activation-4.05e-01

Pos logit contributions
itating+0.073
inkle+0.070
rig+0.070
shadow+0.069
ews+0.066
Neg logit contributions
 bear-0.056
 robbers-0.053
 bears-0.052
 mice-0.051
 rabbits-0.050
Tokenangers
Token ID6606
Feature activation-1.97e+00

Pos logit contributions
itating+0.016
inkle+0.015
rig+0.015
shadow+0.015
ews+0.014
Neg logit contributions
 bear-0.018
 robbers-0.018
 bears-0.018
 mice-0.017
 rabbits-0.017
Token she
Token ID673
Feature activation-1.04e+00

Pos logit contributions
rig+0.116
itating+0.114
shadow+0.112
inkle+0.112
har+0.107
Neg logit contributions
 bear-0.053
 robbers-0.047
 bears-0.047
 rabbits-0.045
 mice-0.045
Token usually
Token ID3221
Feature activation-3.58e+00

Pos logit contributions
itating+0.061
inkle+0.059
shadow+0.058
rig+0.058
ews+0.057
Neg logit contributions
 bear-0.029
 robbers-0.027
 bears-0.026
 mice-0.025
 squirrel-0.025
Token saw
Token ID2497
Feature activation-7.62e-01

Pos logit contributions
itating+0.214
shadow+0.205
rig+0.200
inkle+0.194
mmm+0.189
Neg logit contributions
 bear-0.099
 robbers-0.088
 bears-0.087
 squirrel-0.083
 rabbits-0.082
Token.
Token ID13
Feature activation+3.55e-02

Pos logit contributions
itating+0.043
inkle+0.043
rig+0.042
shadow+0.041
ews+0.040
Neg logit contributions
 bear-0.022
 bears-0.021
 mice-0.020
 robbers-0.020
 rabbits-0.019
Token
Token ID198
Feature activation-1.70e-01

Pos logit contributions
 bear+0.001
 robbers+0.001
 mice+0.001
 rabbits+0.001
 bears+0.001
Neg logit contributions
inkle-0.002
itating-0.002
rig-0.002
shadow-0.002
har-0.002
Token
Token ID198
Feature activation-8.84e-02

Pos logit contributions
itating+0.009
inkle+0.009
shadow+0.009
rig+0.008
ews+0.008
Neg logit contributions
 bear-0.006
 squirrel-0.005
B-0.005
 bears-0.005
 robbers-0.005
TokenJ
Token ID41
Feature activation+1.16e+00

Pos logit contributions
inkle+0.005
itating+0.005
shadow+0.005
rig+0.005
ews+0.005
Neg logit contributions
 bear-0.002
B-0.002
 robbers-0.002
 squirrel-0.002
 mice-0.002
Token't
Token ID470
Feature activation+1.93e-01

Pos logit contributions
 bear+0.017
 robbers+0.016
 bears+0.016
 mice+0.016
 rabbits+0.015
Neg logit contributions
itating-0.014
inkle-0.014
rig-0.014
shadow-0.013
ews-0.013
Token taste
Token ID6938
Feature activation+7.43e-01

Pos logit contributions
 bear+0.009
 robbers+0.008
 bears+0.008
 mice+0.008
 squirrel+0.008
Neg logit contributions
itating-0.008
inkle-0.008
rig-0.008
ews-0.008
shadow-0.008
Token like
Token ID588
Feature activation-6.68e-01

Pos logit contributions
 bear+0.026
 mice+0.025
 bears+0.025
 robbers+0.024
 squirrel+0.023
Neg logit contributions
itating-0.039
rig-0.038
ews-0.038
inkle-0.037
shadow-0.037
Token anything
Token ID1997
Feature activation-6.46e-01

Pos logit contributions
 yet+0.024
 ours+0.020
 early+0.020
inkle+0.019
icing+0.018
Neg logit contributions
Carl-0.031
 bear-0.029
 robbers-0.029
B-0.029
 servant-0.028
Token he
Token ID339
Feature activation-8.28e-01

Pos logit contributions
inkle+0.032
itating+0.032
rig+0.031
?",+0.030
shadow+0.030
Neg logit contributions
 bear-0.022
 robbers-0.021
 bears-0.021
 mice-0.020
 rabbits-0.020
Token usually
Token ID3221
Feature activation-3.37e+00

Pos logit contributions
inkle+0.041
rig+0.040
itating+0.039
?",+0.039
shadow+0.038
Neg logit contributions
 bear-0.027
 bears-0.027
 robbers-0.027
 mice-0.027
 rabbits-0.026
Token ate
Token ID15063
Feature activation+4.75e-01

Pos logit contributions
itating+0.187
inkle+0.183
rig+0.180
shadow+0.178
ews+0.175
Neg logit contributions
 bear-0.101
 robbers-0.096
 bears-0.094
 mice-0.092
 squirrel-0.090
Token,
Token ID11
Feature activation+1.06e-01

Pos logit contributions
 bear+0.015
 robbers+0.014
 bears+0.014
 mice+0.014
 rabbits+0.014
Neg logit contributions
itating-0.025
inkle-0.025
rig-0.025
shadow-0.024
ews-0.024
Token like
Token ID588
Feature activation-1.48e+00

Pos logit contributions
 bear+0.006
 squirrel+0.005
 bears+0.005
 robbers+0.005
 rabbits+0.005
Neg logit contributions
inkle-0.004
itating-0.004
ossom-0.004
ews-0.004
rig-0.004
Token honey
Token ID12498
Feature activation-5.56e-01

Pos logit contributions
 yet+0.053
 ours+0.048
 early+0.047
shadow+0.047
itating+0.045
Neg logit contributions
Carl-0.063
 robbers-0.061
 bear-0.061
B-0.061
pill-0.058
Token or
Token ID393
Feature activation-5.31e-01

Pos logit contributions
inkle+0.025
itating+0.024
 yet+0.023
rig+0.023
?",+0.022
Neg logit contributions
 robbers-0.021
 bear-0.020
 mice-0.020
 villains-0.020
 bears-0.020
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
itating+0.054
shadow+0.054
?",+0.053
rig+0.053
 yet+0.053
Neg logit contributions
 mice-0.054
 bears-0.053
 robbers-0.053
 bear-0.053
 rabbits-0.052
Token He
Token ID679
Feature activation-6.93e-02

Pos logit contributions
itating+0.009
rig+0.009
inkle+0.009
shadow+0.008
ews+0.008
Neg logit contributions
 bear-0.005
 bears-0.005
 robbers-0.005
 mice-0.005
 squirrel-0.004
Token ran
Token ID4966
Feature activation-4.21e-01

Pos logit contributions
itating+0.003
inkle+0.003
rig+0.003
shadow+0.003
ews+0.003
Neg logit contributions
 bear-0.002
 robbers-0.002
 bears-0.002
 mice-0.002
 rabbits-0.002
Token to
Token ID284
Feature activation+2.31e-02

Pos logit contributions
inkle+0.024
mmm+0.022
itating+0.022
ews+0.021
rig+0.021
Neg logit contributions
 bear-0.016
 robbers-0.016
 bears-0.014
 squirrel-0.014
 mice-0.013
Token the
Token ID262
Feature activation-7.37e-01

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 mice+0.001
 squirrel+0.001
Neg logit contributions
itating-0.001
inkle-0.001
rig-0.001
ews-0.001
shadow-0.001
Token concessions
Token ID26739
Feature activation-3.37e+00

Pos logit contributions
itating+0.034
inkle+0.033
rig+0.033
ews+0.032
shadow+0.031
Neg logit contributions
 bear-0.029
 robbers-0.028
 bears-0.027
 mice-0.027
 rabbits-0.026
Token stand
Token ID1302
Feature activation-2.66e-01

Pos logit contributions
inkle+0.154
itating+0.152
rig+0.144
shadow+0.143
ews+0.143
Neg logit contributions
 bear-0.139
 robbers-0.132
 bears-0.129
 mice-0.125
 squirrel-0.123
Token and
Token ID290
Feature activation+7.59e-02

Pos logit contributions
inkle+0.013
mmm+0.013
shadow+0.012
itating+0.012
apers+0.012
Neg logit contributions
 bear-0.011
 sword-0.009
 bears-0.009
 robbers-0.008
 t-0.008
Token grabbed
Token ID13176
Feature activation-7.02e-01

Pos logit contributions
 bear+0.003
 robbers+0.002
 bears+0.002
 mice+0.002
 squirrel+0.002
Neg logit contributions
itating-0.004
inkle-0.004
rig-0.004
shadow-0.004
ews-0.004
Token a
Token ID257
Feature activation-8.85e-02

Pos logit contributions
inkle+0.031
itating+0.030
rig+0.029
shadow+0.029
ews+0.028
Neg logit contributions
 bear-0.027
 robbers-0.027
 bears-0.026
 squirrel-0.026
 mice-0.026
Token bag
Token ID6131
Feature activation-1.23e-01

Pos logit contributions
itating+0.005
shadow+0.005
apers+0.005
inkle+0.005
mmm+0.005
Neg logit contributions
 bear-0.003
 robbers-0.003
 t-0.002
 bears-0.002
 sword-0.002
Token He
Token ID679
Feature activation+2.01e-01

Pos logit contributions
inkle+0.005
itating+0.005
rig+0.005
shadow+0.005
ews+0.005
Neg logit contributions
 bear-0.004
 robbers-0.004
 mice-0.004
 bears-0.004
 squirrel-0.003
Token could
Token ID714
Feature activation-3.51e-01

Pos logit contributions
 bear+0.007
 robbers+0.007
 bears+0.007
 mice+0.007
 rabbits+0.007
Neg logit contributions
inkle-0.010
itating-0.010
rig-0.009
shadow-0.009
ews-0.009
Token hear
Token ID3285
Feature activation-6.29e-01

Pos logit contributions
ews+0.015
shadow+0.015
rig+0.014
inkle+0.014
apers+0.014
Neg logit contributions
 bear-0.016
 squirrel-0.015
 robbers-0.014
 t-0.014
 rabbits-0.013
Token a
Token ID257
Feature activation-2.35e-01

Pos logit contributions
itating+0.027
inkle+0.027
rig+0.026
ews+0.025
shadow+0.025
Neg logit contributions
 bear-0.026
 robbers-0.025
 bears-0.025
 mice-0.024
 rabbits-0.024
Token p
Token ID279
Feature activation+4.29e-01

Pos logit contributions
itating+0.009
inkle+0.009
rig+0.009
shadow+0.009
ews+0.008
Neg logit contributions
 bear-0.011
 robbers-0.010
 bears-0.010
 mice-0.010
 rabbits-0.010
Tokenained
Token ID1328
Feature activation-3.34e+00

Pos logit contributions
 bear+0.017
 squirrel+0.015
 rac+0.015
 bears+0.015
 mice+0.015
Neg logit contributions
shadow-0.018
?",-0.018
itating-0.017
 ours-0.017
!?"-0.017
Token noise
Token ID7838
Feature activation-4.05e-01

Pos logit contributions
inkle+0.145
itating+0.144
rig+0.139
shadow+0.137
ews+0.135
Neg logit contributions
 bear-0.141
 robbers-0.135
 bears-0.134
 mice-0.132
 rabbits-0.130
Token coming
Token ID2406
Feature activation-1.00e+00

Pos logit contributions
inkle+0.017
itating+0.017
rig+0.016
shadow+0.016
ews+0.016
Neg logit contributions
 bear-0.018
 bears-0.017
 robbers-0.017
 mice-0.016
 squirrel-0.016
Token from
Token ID422
Feature activation+2.09e-01

Pos logit contributions
inkle+0.046
ews+0.044
itating+0.043
rig+0.042
ossom+0.042
Neg logit contributions
 bear-0.046
 squirrel-0.042
 bears-0.041
 rabbits-0.040
 robbers-0.040
Token the
Token ID262
Feature activation+2.58e-01

Pos logit contributions
 bear+0.008
 bears+0.008
 robbers+0.007
 mice+0.007
 rabbits+0.007
Neg logit contributions
itating-0.010
rig-0.010
inkle-0.010
shadow-0.010
ews-0.010
Token woods
Token ID16479
Feature activation-5.62e-02

Pos logit contributions
 robbers+0.008
 bears+0.008
 bear+0.008
 mice+0.008
 villains+0.007
Neg logit contributions
itating-0.013
inkle-0.013
rig-0.012
ews-0.012
?",-0.012
Token Jack
Token ID3619
Feature activation-8.60e-01

Pos logit contributions
itating+0.004
inkle+0.004
rig+0.004
shadow+0.004
ews+0.004
Neg logit contributions
 bear-0.004
 bears-0.003
 robbers-0.003
 mice-0.003
 rabbits-0.003
Token was
Token ID373
Feature activation-2.27e-01

Pos logit contributions
itating+0.047
inkle+0.046
rig+0.045
shadow+0.044
ews+0.044
Neg logit contributions
 bear-0.027
 robbers-0.025
 bears-0.025
 mice-0.024
 rabbits-0.024
Token so
Token ID523
Feature activation-1.22e+00

Pos logit contributions
inkle+0.010
apers+0.010
rig+0.010
ossom+0.010
itating+0.009
Neg logit contributions
 bear-0.010
 squirrel-0.009
 bears-0.009
 t-0.009
 rabbits-0.009
Token happy
Token ID3772
Feature activation+3.20e-01

Pos logit contributions
inkle+0.051
apers+0.051
itating+0.049
rig+0.048
ist+0.048
Neg logit contributions
 bear-0.052
 squirrel-0.050
 robbers-0.048
 bears-0.047
 mice-0.047
Token he
Token ID339
Feature activation-8.16e-01

Pos logit contributions
 bear+0.014
 robbers+0.013
 bears+0.013
 mice+0.013
 rabbits+0.013
Neg logit contributions
itating-0.013
inkle-0.013
rig-0.013
shadow-0.013
ews-0.012
Token almost
Token ID2048
Feature activation-3.27e+00

Pos logit contributions
itating+0.048
inkle+0.047
rig+0.046
ews+0.045
shadow+0.045
Neg logit contributions
 bear-0.023
 robbers-0.021
 bears-0.020
 squirrel-0.020
 mice-0.019
Token cried
Token ID16896
Feature activation+9.82e-01

Pos logit contributions
itating+0.171
inkle+0.170
rig+0.167
shadow+0.163
ews+0.161
Neg logit contributions
 bear-0.107
 robbers-0.102
 bears-0.101
 mice-0.099
 rabbits-0.096
Token.
Token ID13
Feature activation-3.85e-02

Pos logit contributions
 bear+0.040
 robbers+0.039
 bears+0.039
 mice+0.038
 rabbits+0.037
Neg logit contributions
itating-0.043
inkle-0.042
rig-0.041
shadow-0.040
ews-0.040
Token
Token ID220
Feature activation+1.21e-01

Pos logit contributions
itating+0.002
inkle+0.002
rig+0.002
shadow+0.002
ews+0.002
Neg logit contributions
 bear-0.002
 bears-0.002
 robbers-0.001
 mice-0.001
 rabbits-0.001
Token
Token ID198
Feature activation-1.93e-02

Pos logit contributions
 bear+0.005
 robbers+0.005
 bears+0.005
 mice+0.005
 rabbits+0.005
Neg logit contributions
itating-0.005
inkle-0.005
rig-0.005
shadow-0.005
ews-0.005
Token
Token ID198
Feature activation+1.52e-02

Pos logit contributions
inkle+0.001
itating+0.001
rig+0.001
shadow+0.001
ews+0.001
Neg logit contributions
 bear-0.001
 robbers-0.001
 bears-0.001
 mice-0.001
 squirrel-0.001
Token John
Token ID1757
Feature activation-6.74e-01

Pos logit contributions
 bear+0.004
 robbers+0.004
 bears+0.004
 mice+0.004
 squirrel+0.004
Neg logit contributions
inkle-0.006
itating-0.006
rig-0.005
ews-0.005
ossom-0.005
Token felt
Token ID2936
Feature activation+6.89e-02

Pos logit contributions
itating+0.038
inkle+0.037
rig+0.036
shadow+0.036
ews+0.035
Neg logit contributions
 bear-0.022
 bears-0.019
 robbers-0.018
 squirrel-0.018
 mice-0.018
Token so
Token ID523
Feature activation-1.25e+00

Pos logit contributions
 bear+0.003
 bears+0.003
 mice+0.003
 robbers+0.003
 squirrel+0.003
Neg logit contributions
itating-0.003
inkle-0.003
rig-0.003
shadow-0.003
ews-0.003
Token happy
Token ID3772
Feature activation+4.07e-01

Pos logit contributions
itating+0.049
rig+0.046
shadow+0.046
inkle+0.046
apers+0.045
Neg logit contributions
 bear-0.058
 bears-0.054
 robbers-0.054
 mice-0.053
 squirrel-0.053
Token he
Token ID339
Feature activation-8.02e-01

Pos logit contributions
 bear+0.016
 robbers+0.015
 bears+0.015
 mice+0.015
 rabbits+0.015
Neg logit contributions
itating-0.019
inkle-0.019
rig-0.018
shadow-0.018
ews-0.017
Token almost
Token ID2048
Feature activation-3.27e+00

Pos logit contributions
itating+0.048
inkle+0.047
rig+0.046
shadow+0.045
ews+0.045
Neg logit contributions
 bear-0.022
 robbers-0.020
 bears-0.020
 squirrel-0.019
 mice-0.018
Token shouted
Token ID17293
Feature activation-2.16e-01

Pos logit contributions
itating+0.179
inkle+0.177
rig+0.175
shadow+0.170
ews+0.168
Neg logit contributions
 bear-0.099
 robbers-0.094
 bears-0.092
 mice-0.090
 squirrel-0.088
Token with
Token ID351
Feature activation+6.24e-01

Pos logit contributions
rig+0.012
itating+0.012
inkle+0.012
ews+0.011
shadow+0.011
Neg logit contributions
 bear-0.007
 robbers-0.006
 bears-0.006
 mice-0.006
 rabbits-0.006
Token joy
Token ID8716
Feature activation+6.00e-01

Pos logit contributions
 bear+0.028
 bears+0.027
 robbers+0.027
 mice+0.027
 rabbits+0.026
Neg logit contributions
inkle-0.023
rig-0.023
itating-0.022
?",-0.021
 ours-0.021
Token.
Token ID13
Feature activation-9.17e-02

Pos logit contributions
 bear+0.019
 robbers+0.018
 bears+0.018
 mice+0.018
 rabbits+0.017
Neg logit contributions
itating-0.032
inkle-0.032
rig-0.031
shadow-0.030
ews-0.030
Token
Token ID198
Feature activation-1.28e-01

Pos logit contributions
inkle+0.005
itating+0.005
rig+0.004
shadow+0.004
ews+0.004
Neg logit contributions
 bear-0.003
 robbers-0.003
 bears-0.003
 mice-0.003
 squirrel-0.003
Token up
Token ID510
Feature activation-3.50e-01

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 balls+0.001
 squirrel+0.001
Neg logit contributions
inkle-0.001
mmm-0.001
ews-0.001
ossom-0.001
itating-0.001
Token the
Token ID262
Feature activation+2.31e-02

Pos logit contributions
inkle+0.018
itating+0.018
ossom+0.018
shadow+0.018
rig+0.018
Neg logit contributions
 bear-0.013
 robbers-0.012
 bears-0.012
 rac-0.011
 squirrel-0.011
Token stairs
Token ID16046
Feature activation-6.64e-01

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 mice+0.001
 squirrel+0.001
Neg logit contributions
inkle-0.001
itating-0.001
rig-0.001
shadow-0.001
ossom-0.001
Token like
Token ID588
Feature activation-1.73e+00

Pos logit contributions
inkle+0.030
itating+0.029
rig+0.029
shadow+0.029
ews+0.028
Neg logit contributions
 bear-0.027
 robbers-0.026
 bears-0.025
 mice-0.025
 rabbits-0.024
Token he
Token ID339
Feature activation-4.32e-01

Pos logit contributions
 yet+0.064
?",+0.063
shadow+0.062
itating+0.061
?!"+0.060
Neg logit contributions
 bear-0.071
 mice-0.070
Carl-0.070
 robbers-0.070
 bears-0.069
Token usually
Token ID3221
Feature activation-3.25e+00

Pos logit contributions
inkle+0.021
itating+0.021
rig+0.021
shadow+0.020
?",+0.020
Neg logit contributions
 robbers-0.014
 bear-0.014
 mice-0.014
 bears-0.014
 rabbits-0.014
Token did
Token ID750
Feature activation-8.22e-02

Pos logit contributions
itating+0.173
inkle+0.171
rig+0.168
shadow+0.164
ews+0.162
Neg logit contributions
 bear-0.104
 robbers-0.098
 bears-0.097
 mice-0.094
 squirrel-0.092
Token!
Token ID0
Feature activation+1.02e-02

Pos logit contributions
rig+0.005
itating+0.005
inkle+0.004
ews+0.004
ossom+0.004
Neg logit contributions
 bear-0.002
 robbers-0.002
 bears-0.002
 villains-0.002
 squirrel-0.002
Token
Token ID198
Feature activation-2.20e-01

Pos logit contributions
 bear+0.000
 robbers+0.000
 squirrel+0.000
 bears+0.000
 mice+0.000
Neg logit contributions
inkle-0.001
itating-0.001
rig-0.001
ossom-0.001
shadow-0.001
Token
Token ID198
Feature activation-1.63e-01

Pos logit contributions
inkle+0.013
ossom+0.012
itating+0.012
 ours+0.012
ews+0.012
Neg logit contributions
B-0.006
 bear-0.006
 robbers-0.005
 squirrel-0.005
 rac-0.005
TokenTom
Token ID13787
Feature activation+6.90e-01

Pos logit contributions
inkle+0.008
itating+0.007
ossom+0.007
rig+0.007
ews+0.007
Neg logit contributions
 robbers-0.007
B-0.006
 bear-0.006
 squirrel-0.006
 villains-0.006
Token in
Token ID287
Feature activation-3.71e-01

Pos logit contributions
 robbers+0.014
pill+0.014
 bears+0.013
 bear+0.013
 villains+0.013
Neg logit contributions
itating-0.007
shadow-0.006
inkle-0.006
rig-0.006
 early-0.006
Token the
Token ID262
Feature activation-1.91e-01

Pos logit contributions
inkle+0.009
 late+0.009
 common+0.009
 yet+0.008
 ours+0.008
Neg logit contributions
 robbers-0.020
 servant-0.019
pill-0.019
 rabbits-0.019
 villains-0.019
Token wild
Token ID4295
Feature activation+1.60e-01

Pos logit contributions
itating+0.009
inkle+0.009
?",+0.009
 early+0.009
iver+0.009
Neg logit contributions
 robbers-0.006
pill-0.006
 villains-0.006
emaker-0.005
 shields-0.005
Token.
Token ID13
Feature activation+1.54e-02

Pos logit contributions
 robbers+0.005
 shields+0.004
pill+0.004
 villains+0.004
Carl+0.004
Neg logit contributions
?",-0.008
inkle-0.008
?"-0.008
 yet-0.008
 early-0.008
Token He
Token ID679
Feature activation+4.36e-02

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 mice+0.001
 rabbits+0.001
Neg logit contributions
itating-0.001
inkle-0.001
rig-0.001
shadow-0.001
ews-0.001
Token usually
Token ID3221
Feature activation-3.24e+00

Pos logit contributions
 robbers+0.002
 mice+0.002
 bear+0.002
 bears+0.002
 rabbits+0.002
Neg logit contributions
inkle-0.002
?",-0.002
rig-0.002
itating-0.002
ews-0.002
Token kept
Token ID4030
Feature activation-1.24e-01

Pos logit contributions
inkle+0.166
itating+0.165
rig+0.161
shadow+0.157
ews+0.157
Neg logit contributions
 bear-0.105
 robbers-0.103
 bears-0.100
 mice-0.099
 rabbits-0.096
Token to
Token ID284
Feature activation+7.09e-01

Pos logit contributions
itating+0.006
inkle+0.006
rig+0.006
shadow+0.006
ews+0.006
Neg logit contributions
 bear-0.004
 robbers-0.004
 bears-0.004
 mice-0.004
 rabbits-0.004
Token himself
Token ID2241
Feature activation+5.04e-01

Pos logit contributions
 bear+0.028
 robbers+0.026
 bears+0.026
 mice+0.025
 squirrel+0.025
Neg logit contributions
itating-0.035
inkle-0.033
rig-0.033
shadow-0.032
ews-0.032
Token,
Token ID11
Feature activation-8.34e-02

Pos logit contributions
 bear+0.023
 bears+0.021
 robbers+0.021
 mice+0.021
 rabbits+0.021
Neg logit contributions
itating-0.021
inkle-0.020
rig-0.020
ews-0.019
shadow-0.019
Token but
Token ID475
Feature activation-9.63e-01

Pos logit contributions
inkle+0.003
itating+0.003
rig+0.003
ews+0.002
ossom+0.002
Neg logit contributions
 bear-0.005
 bears-0.005
 robbers-0.005
 squirrel-0.004
 rabbits-0.004
Token able
Token ID1498
Feature activation+7.09e-01

Pos logit contributions
 bear+0.031
 mice+0.030
 bears+0.030
 robbers+0.029
 rabbits+0.028
Neg logit contributions
inkle-0.030
itating-0.030
rig-0.030
ews-0.028
mmm-0.028
Token to
Token ID284
Feature activation+4.08e-01

Pos logit contributions
 bear+0.038
 bears+0.038
 robbers+0.037
 villains+0.036
 rabbits+0.035
Neg logit contributions
itating-0.019
shadow-0.019
 yet-0.019
 ours-0.018
rig-0.017
Token do
Token ID466
Feature activation-2.31e-02

Pos logit contributions
 robbers+0.017
 bears+0.017
 bear+0.017
 rabbits+0.016
 mice+0.016
Neg logit contributions
inkle-0.017
itating-0.017
?",-0.016
rig-0.016
shadow-0.016
Token what
Token ID644
Feature activation+6.82e-01

Pos logit contributions
itating+0.001
inkle+0.001
rig+0.001
shadow+0.001
ews+0.001
Neg logit contributions
 bear-0.001
 robbers-0.001
 bears-0.001
 mice-0.001
 rabbits-0.001
Token she
Token ID673
Feature activation-1.68e+00

Pos logit contributions
 robbers+0.024
 bear+0.024
 bears+0.024
 rabbits+0.023
 mice+0.023
Neg logit contributions
itating-0.031
inkle-0.031
?",-0.030
rig-0.030
shadow-0.029
Token'd
Token ID1549
Feature activation-3.20e+00

Pos logit contributions
inkle+0.081
rig+0.079
itating+0.076
?",+0.076
shadow+0.073
Neg logit contributions
 robbers-0.059
 bears-0.057
 mice-0.057
 bear-0.057
 rabbits-0.057
Token done
Token ID1760
Feature activation-1.52e+00

Pos logit contributions
itating+0.145
inkle+0.140
rig+0.139
ews+0.138
shadow+0.136
Neg logit contributions
 bear-0.132
 robbers-0.127
 squirrel-0.121
 bears-0.121
 mice-0.120
Token.
Token ID13
Feature activation-4.43e-01

Pos logit contributions
rig+0.092
itating+0.089
ews+0.089
inkle+0.089
shadow+0.086
Neg logit contributions
 bear-0.039
 bears-0.035
 robbers-0.034
 mice-0.034
 balls-0.032
Token
Token ID198
Feature activation-2.78e-01

Pos logit contributions
itating+0.018
inkle+0.018
rig+0.018
shadow+0.017
ews+0.017
Neg logit contributions
 bear-0.019
 robbers-0.019
 bears-0.019
 mice-0.018
 rabbits-0.018
Token
Token ID198
Feature activation-1.87e-01

Pos logit contributions
inkle+0.012
itating+0.012
rig+0.012
shadow+0.011
ews+0.011
Neg logit contributions
 bear-0.012
 robbers-0.011
 bears-0.011
 mice-0.011
 rabbits-0.011
TokenFor
Token ID1890
Feature activation-4.79e-01

Pos logit contributions
itating+0.008
inkle+0.008
rig+0.007
shadow+0.007
ews+0.007
Neg logit contributions
 bear-0.008
 bears-0.008
 robbers-0.008
 mice-0.008
 rabbits-0.008
Token zoom
Token ID19792
Feature activation-5.06e-01

Pos logit contributions
 mice+0.030
 robbers+0.029
 bears+0.028
 rabbits+0.028
 bear+0.028
Neg logit contributions
inkle-0.047
itating-0.046
rig-0.046
?",-0.045
shadow-0.044
Tokened
Token ID276
Feature activation+5.52e-01

Pos logit contributions
itating+0.027
inkle+0.027
rig+0.027
ews+0.026
shadow+0.026
Neg logit contributions
 bear-0.017
 bears-0.015
 robbers-0.015
 squirrel-0.015
 mice-0.015
Token around
Token ID1088
Feature activation-5.16e-01

Pos logit contributions
 bear+0.027
 robbers+0.027
 mice+0.027
 bears+0.026
 rabbits+0.026
Neg logit contributions
itating-0.018
inkle-0.018
rig-0.017
shadow-0.017
ews-0.016
Token,
Token ID11
Feature activation+8.50e-02

Pos logit contributions
inkle+0.020
itating+0.020
rig+0.019
?",+0.019
shadow+0.019
Neg logit contributions
 robbers-0.022
 mice-0.021
 bear-0.021
 bears-0.021
 rabbits-0.021
Token he
Token ID339
Feature activation-2.25e-01

Pos logit contributions
pill+0.002
 villains+0.002
 robbers+0.002
 mice+0.002
 bears+0.002
Neg logit contributions
?",-0.004
inkle-0.004
itating-0.004
shadow-0.004
 early-0.004
Token usually
Token ID3221
Feature activation-3.20e+00

Pos logit contributions
itating+0.012
inkle+0.012
rig+0.011
shadow+0.011
ews+0.011
Neg logit contributions
 bear-0.007
 robbers-0.007
 bears-0.007
 mice-0.007
 rabbits-0.007
Token visited
Token ID8672
Feature activation-9.51e-01

Pos logit contributions
itating+0.178
inkle+0.175
rig+0.173
shadow+0.169
ews+0.167
Neg logit contributions
 bear-0.097
 robbers-0.090
 bears-0.089
 squirrel-0.085
 mice-0.084
Token his
Token ID465
Feature activation-2.09e-01

Pos logit contributions
itating+0.045
inkle+0.044
rig+0.043
shadow+0.042
ews+0.042
Neg logit contributions
 bear-0.037
 robbers-0.035
 bears-0.035
 mice-0.034
 rabbits-0.033
Token best
Token ID1266
Feature activation-2.10e+00

Pos logit contributions
itating+0.010
inkle+0.010
rig+0.010
ews+0.009
 ours+0.009
Neg logit contributions
 robbers-0.007
 bear-0.007
 bears-0.007
 mice-0.007
pill-0.007
Token friend
Token ID1545
Feature activation-6.39e-01

Pos logit contributions
rig+0.080
itating+0.079
ute+0.079
inkle+0.076
 early+0.073
Neg logit contributions
pill-0.092
 bears-0.083
 slit-0.083
 mice-0.082
 seaw-0.082
Token Sammy
Token ID44067
Feature activation-1.36e+00

Pos logit contributions
itating+0.026
inkle+0.025
rig+0.025
?",+0.025
shadow+0.025
Neg logit contributions
 robbers-0.025
 bear-0.025
 mice-0.025
 bears-0.025
 villains-0.024
Token,
Token ID11
Feature activation+3.75e-01

Pos logit contributions
itating+0.003
inkle+0.003
shadow+0.002
?",+0.002
rig+0.002
Neg logit contributions
 robbers-0.003
 bear-0.003
 mice-0.003
 bears-0.003
 rabbits-0.003
Token "
Token ID366
Feature activation+7.36e-02

Pos logit contributions
 bear+0.011
 robbers+0.010
 bears+0.010
 squirrel+0.010
 rabbits+0.010
Neg logit contributions
inkle-0.021
itating-0.021
rig-0.021
ews-0.020
ossom-0.020
TokenWhat
Token ID2061
Feature activation+4.77e-01

Pos logit contributions
 bear+0.003
 robbers+0.003
 bears+0.003
 mice+0.003
 rabbits+0.003
Neg logit contributions
itating-0.003
inkle-0.003
rig-0.003
shadow-0.003
ews-0.003
Token are
Token ID389
Feature activation-6.61e-01

Pos logit contributions
 bear+0.019
 robbers+0.019
 bears+0.018
 mice+0.018
 rabbits+0.017
Neg logit contributions
inkle-0.020
itating-0.020
?",-0.020
rig-0.020
ews-0.019
Token you
Token ID345
Feature activation-1.01e+00

Pos logit contributions
itating+0.024
inkle+0.023
shadow+0.023
?",+0.022
rig+0.022
Neg logit contributions
 bear-0.032
 robbers-0.030
 bears-0.030
 mice-0.029
 squirrel-0.029
Token gonna
Token ID8066
Feature activation-3.18e+00

Pos logit contributions
rig+0.055
ossom+0.051
ews+0.050
itating+0.050
har+0.050
Neg logit contributions
 bear-0.037
 robbers-0.033
 rabbits-0.033
 bears-0.033
 squirrel-0.031
Token do
Token ID466
Feature activation-3.55e-01

Pos logit contributions
itating+0.164
rig+0.158
ews+0.156
inkle+0.154
shadow+0.150
Neg logit contributions
 bear-0.121
 robbers-0.112
 squirrel-0.112
 mice-0.107
 villains-0.105
Token with
Token ID351
Feature activation+4.90e-02

Pos logit contributions
ews+0.017
rig+0.017
itating+0.016
ossom+0.016
har+0.016
Neg logit contributions
 bear-0.015
 robbers-0.014
 bears-0.014
 mice-0.014
 monster-0.013
Token him
Token ID683
Feature activation-1.24e-02

Pos logit contributions
 bear+0.002
 robbers+0.002
 bears+0.002
 mice+0.002
 rabbits+0.002
Neg logit contributions
itating-0.002
inkle-0.002
rig-0.002
shadow-0.002
ews-0.002
Token?".
Token ID43634
Feature activation-8.59e-01

Pos logit contributions
rig+0.000
itating+0.000
ews+0.000
ounded+0.000
har+0.000
Neg logit contributions
 bear-0.001
 bears-0.001
 squirrel-0.001
 robbers-0.001
 rabbits-0.001
Token Joe
Token ID5689
Feature activation-6.61e-01

Pos logit contributions
inkle+0.046
itating+0.044
rig+0.044
shadow+0.043
 ours+0.042
Neg logit contributions
 bear-0.030
 squirrel-0.027
 robbers-0.026
 rabbits-0.026
 bears-0.026
Token so
Token ID523
Feature activation-1.03e+00

Pos logit contributions
 bear+0.004
 bears+0.004
 squirrel+0.004
 t+0.004
 b+0.004
Neg logit contributions
rig-0.004
apers-0.004
itating-0.004
inkle-0.004
ossom-0.004
Token proud
Token ID6613
Feature activation+1.29e+00

Pos logit contributions
apers+0.042
inkle+0.040
itating+0.039
ist+0.039
ews+0.039
Neg logit contributions
 bear-0.045
 squirrel-0.044
 b-0.041
 rac-0.041
 bears-0.040
Token of
Token ID286
Feature activation-1.71e+00

Pos logit contributions
 robbers+0.059
 bear+0.057
 bears+0.056
 mice+0.056
 villains+0.056
Neg logit contributions
rig-0.047
itating-0.046
shadow-0.044
?",-0.043
 early-0.043
Token what
Token ID644
Feature activation+7.28e-01

Pos logit contributions
inkle+0.073
shadow+0.072
itating+0.072
 yet+0.072
 early+0.070
Neg logit contributions
pill-0.063
 robbers-0.063
 bear-0.062
 mice-0.061
 squirrel-0.059
Token he
Token ID339
Feature activation-1.65e+00

Pos logit contributions
pill+0.021
 rabbits+0.021
 mice+0.021
 bears+0.020
B+0.020
Neg logit contributions
?",-0.034
 early-0.033
 yet-0.033
?!"-0.032
!?"-0.031
Token'd
Token ID1549
Feature activation-3.18e+00

Pos logit contributions
itating+0.095
inkle+0.094
rig+0.092
shadow+0.090
ews+0.090
Neg logit contributions
 bear-0.047
 robbers-0.044
 bears-0.044
 mice-0.042
 rabbits-0.041
Token done
Token ID1760
Feature activation-1.34e+00

Pos logit contributions
itating+0.171
rig+0.164
inkle+0.164
ews+0.164
shadow+0.158
Neg logit contributions
 bear-0.105
 robbers-0.101
 squirrel-0.097
 villains-0.092
 rac-0.090
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
rig+0.082
itating+0.082
ossom+0.080
ews+0.080
inkle+0.080
Neg logit contributions
 bear-0.033
 bears-0.031
 robbers-0.027
 dinosaurs-0.026
 mar-0.026
Token He
Token ID679
Feature activation+5.90e-02

Pos logit contributions
 bears+0.005
 bear+0.005
 rabbits+0.005
 robbers+0.005
 mice+0.005
Neg logit contributions
rig-0.005
itating-0.005
mmm-0.005
inkle-0.005
ews-0.005
Token had
Token ID550
Feature activation-3.70e-01

Pos logit contributions
 bear+0.002
 robbers+0.002
 bears+0.002
 mice+0.002
 rabbits+0.002
Neg logit contributions
inkle-0.003
itating-0.003
rig-0.003
shadow-0.003
ews-0.003
Token tried
Token ID3088
Feature activation+1.23e+00

Pos logit contributions
itating+0.016
inkle+0.016
rig+0.016
shadow+0.015
ews+0.015
Neg logit contributions
 bear-0.015
 robbers-0.014
 bears-0.014
 mice-0.014
 rabbits-0.014
Token see
Token ID766
Feature activation-1.44e+00

Pos logit contributions
itating+0.007
inkle+0.007
rig+0.007
shadow+0.006
?",+0.006
Neg logit contributions
 bear-0.006
 bears-0.006
 robbers-0.006
 mice-0.006
 rabbits-0.005
Token who
Token ID508
Feature activation+7.30e-01

Pos logit contributions
itating+0.060
inkle+0.059
rig+0.057
shadow+0.056
ews+0.055
Neg logit contributions
 bear-0.063
 robbers-0.061
 bears-0.060
 mice-0.059
 rabbits-0.058
Token could
Token ID714
Feature activation-2.57e-01

Pos logit contributions
 bear+0.020
 robbers+0.019
 bears+0.018
 mice+0.018
 rabbits+0.018
Neg logit contributions
itating-0.042
inkle-0.042
rig-0.041
shadow-0.040
ews-0.039
Token roll
Token ID4836
Feature activation-1.17e+00

Pos logit contributions
itating+0.012
inkle+0.012
rig+0.012
shadow+0.011
ews+0.011
Neg logit contributions
 bear-0.010
 robbers-0.009
 bears-0.009
 mice-0.009
 rabbits-0.009
Token the
Token ID262
Feature activation+5.97e-02

Pos logit contributions
inkle+0.054
itating+0.053
rig+0.052
ews+0.052
shadow+0.052
Neg logit contributions
 bear-0.048
 bears-0.046
 mice-0.045
 robbers-0.045
 squirrel-0.044
Token fart
Token ID15189
Feature activation-3.17e+00

Pos logit contributions
 villains+0.002
 mice+0.002
 bears+0.002
pill+0.002
 robbers+0.002
Neg logit contributions
itating-0.003
?",-0.003
inkle-0.003
rig-0.003
 ours-0.003
Tokenhest
Token ID3634
Feature activation-1.37e+00

Pos logit contributions
itating+0.091
inkle+0.089
rig+0.086
shadow+0.082
ews+0.080
Neg logit contributions
 bear-0.180
 robbers-0.175
 bears-0.174
 mice-0.172
 rabbits-0.169
Token.
Token ID13
Feature activation-7.04e-02

Pos logit contributions
itating+0.052
 yet+0.052
rig+0.049
 ours+0.049
inkle+0.048
Neg logit contributions
 robbers-0.056
 bear-0.055
Mic-0.054
 bears-0.053
B-0.053
Token They
Token ID1119
Feature activation-3.24e-02

Pos logit contributions
inkle+0.003
itating+0.003
shadow+0.003
rig+0.003
ews+0.003
Neg logit contributions
 bear-0.003
 mice-0.003
 robbers-0.003
 bears-0.003
 rabbits-0.003
Token were
Token ID547
Feature activation-1.41e-01

Pos logit contributions
?",+0.001
itating+0.001
ounded+0.001
vy+0.001
 almost+0.001
Neg logit contributions
pill-0.001
 skeletons-0.001
 villains-0.001
 mice-0.001
 skeleton-0.001
Token a
Token ID257
Feature activation-1.89e-01

Pos logit contributions
itating+0.006
inkle+0.006
rig+0.006
shadow+0.005
ews+0.005
Neg logit contributions
 bear-0.006
 robbers-0.006
 bears-0.006
 mice-0.006
 rabbits-0.006
Token thought
Token ID1807
Feature activation+7.11e-01

Pos logit contributions
 robbers+0.003
 bear+0.003
 bears+0.003
 mice+0.003
 rabbits+0.003
Neg logit contributions
inkle-0.005
itating-0.004
rig-0.004
ews-0.004
?",-0.004
Token was
Token ID373
Feature activation-5.04e-02

Pos logit contributions
 bear+0.030
 robbers+0.029
 bears+0.029
 mice+0.029
 rabbits+0.028
Neg logit contributions
itating-0.030
inkle-0.030
rig-0.029
shadow-0.028
ews-0.028
Token weird
Token ID7650
Feature activation-1.09e-01

Pos logit contributions
inkle+0.002
itating+0.002
rig+0.002
shadow+0.002
ews+0.002
Neg logit contributions
 bear-0.002
 robbers-0.002
 bears-0.002
 mice-0.002
 rabbits-0.002
Token because
Token ID780
Feature activation+2.53e-01

Pos logit contributions
itating+0.005
inkle+0.005
rig+0.005
shadow+0.004
ews+0.004
Neg logit contributions
 bear-0.004
 robbers-0.004
 bears-0.004
 mice-0.004
 rabbits-0.004
Token she
Token ID673
Feature activation-8.00e-01

Pos logit contributions
 bear+0.010
 robbers+0.010
 bears+0.010
 mice+0.009
 rabbits+0.009
Neg logit contributions
inkle-0.011
itating-0.011
rig-0.010
shadow-0.010
ews-0.010
Token usually
Token ID3221
Feature activation-3.17e+00

Pos logit contributions
inkle+0.040
itating+0.038
rig+0.038
?",+0.037
ossom+0.036
Neg logit contributions
 robbers-0.027
 bear-0.027
 bears-0.026
 mice-0.026
 rabbits-0.025
Token had
Token ID550
Feature activation+2.97e-01

Pos logit contributions
itating+0.167
inkle+0.166
rig+0.162
shadow+0.159
ews+0.157
Neg logit contributions
 bear-0.101
 robbers-0.097
 bears-0.096
 mice-0.094
 rabbits-0.091
Token ham
Token ID8891
Feature activation+2.29e+00

Pos logit contributions
 bear+0.012
 robbers+0.012
 bears+0.012
 mice+0.012
 rabbits+0.011
Neg logit contributions
inkle-0.013
itating-0.012
rig-0.012
shadow-0.012
ews-0.012
Token and
Token ID290
Feature activation+7.11e-01

Pos logit contributions
 robbers+0.089
 bear+0.088
 bears+0.084
 mice+0.083
 villains+0.083
Neg logit contributions
inkle-0.103
itating-0.100
ossom-0.095
rig-0.094
shadow-0.094
Token cheese
Token ID9891
Feature activation+9.60e-01

Pos logit contributions
 robbers+0.020
 villains+0.020
B+0.019
emaker+0.019
 bear+0.018
Neg logit contributions
inkle-0.035
?",-0.034
 ours-0.034
mmm-0.034
 yet-0.033
Token.
Token ID13
Feature activation-3.22e-01

Pos logit contributions
 robbers+0.040
 bear+0.038
 villains+0.037
 bears+0.037
 mice+0.036
Neg logit contributions
inkle-0.040
itating-0.038
ossom-0.037
rig-0.036
?",-0.036
Token thinking
Token ID3612
Feature activation+6.21e-01

Pos logit contributions
 bear+0.002
 bears+0.002
 robbers+0.002
 mice+0.002
 rabbits+0.002
Neg logit contributions
inkle-0.003
itating-0.003
rig-0.003
shadow-0.002
ews-0.002
Token about
Token ID546
Feature activation-1.21e+00

Pos logit contributions
 bear+0.026
 bears+0.024
 mice+0.024
 robbers+0.023
 rabbits+0.023
Neg logit contributions
itating-0.028
inkle-0.028
rig-0.027
shadow-0.027
ews-0.026
Token the
Token ID262
Feature activation-4.96e-01

Pos logit contributions
itating+0.052
inkle+0.052
rig+0.051
shadow+0.050
ews+0.049
Neg logit contributions
 bear-0.049
 robbers-0.047
 bears-0.046
 mice-0.046
 rabbits-0.045
Token rain
Token ID6290
Feature activation-9.50e-01

Pos logit contributions
itating+0.023
inkle+0.023
rig+0.023
shadow+0.022
ews+0.022
Neg logit contributions
 bear-0.018
 robbers-0.018
 bears-0.018
 mice-0.017
 rabbits-0.017
Token he
Token ID339
Feature activation-7.43e-01

Pos logit contributions
itating+0.041
inkle+0.040
rig+0.039
shadow+0.038
ews+0.038
Neg logit contributions
 bear-0.040
 robbers-0.038
 bears-0.038
 mice-0.038
 rabbits-0.037
Token almost
Token ID2048
Feature activation-3.17e+00

Pos logit contributions
itating+0.040
inkle+0.040
rig+0.039
shadow+0.038
ews+0.038
Neg logit contributions
 bear-0.023
 robbers-0.022
 bears-0.021
 mice-0.021
 rabbits-0.020
Token tri
Token ID1333
Feature activation-9.11e-01

Pos logit contributions
itating+0.163
inkle+0.162
rig+0.159
shadow+0.155
ews+0.153
Neg logit contributions
 bear-0.106
 robbers-0.101
 bears-0.100
 mice-0.098
 rabbits-0.095
Tokenpped
Token ID1496
Feature activation-6.37e-01

Pos logit contributions
itating+0.044
inkle+0.043
rig+0.042
shadow+0.042
ews+0.041
Neg logit contributions
 bear-0.034
 robbers-0.032
 bears-0.032
 mice-0.032
 rabbits-0.031
Token over
Token ID625
Feature activation-8.31e-01

Pos logit contributions
itating+0.024
inkle+0.023
rig+0.023
shadow+0.022
ews+0.022
Neg logit contributions
 bear-0.030
 robbers-0.029
 bears-0.029
 mice-0.029
 rabbits-0.028
Token it
Token ID340
Feature activation+9.84e-02

Pos logit contributions
itating+0.035
inkle+0.035
rig+0.034
shadow+0.033
ews+0.033
Neg logit contributions
 bear-0.033
 robbers-0.033
 bears-0.032
 mice-0.031
 rabbits-0.031
Token!
Token ID0
Feature activation-2.83e-01

Pos logit contributions
 bear+0.003
 robbers+0.003
 bears+0.003
 mice+0.003
 rabbits+0.003
Neg logit contributions
itating-0.005
inkle-0.005
rig-0.005
shadow-0.005
ews-0.005
Token excited
Token ID6568
Feature activation+3.29e-01

Pos logit contributions
 bear+0.009
 bears+0.008
 mice+0.008
 rabbits+0.008
 squirrel+0.008
Neg logit contributions
itating-0.010
rig-0.010
inkle-0.009
apers-0.009
ounded-0.009
Token to
Token ID284
Feature activation+2.35e-01

Pos logit contributions
 bear+0.013
 bears+0.012
 mice+0.012
 robbers+0.012
 rabbits+0.012
Neg logit contributions
inkle-0.016
itating-0.015
rig-0.015
shadow-0.015
ews-0.015
Token see
Token ID766
Feature activation-1.02e+00

Pos logit contributions
 bear+0.009
 robbers+0.008
 bears+0.008
 mice+0.008
 squirrel+0.008
Neg logit contributions
itating-0.012
inkle-0.011
rig-0.011
shadow-0.011
ews-0.011
Token what
Token ID644
Feature activation+1.09e+00

Pos logit contributions
itating+0.053
inkle+0.052
rig+0.051
shadow+0.051
ews+0.050
Neg logit contributions
 bear-0.036
 bears-0.034
 mice-0.033
 robbers-0.032
 rabbits-0.032
Token she
Token ID673
Feature activation-1.71e+00

Pos logit contributions
 robbers+0.044
 bear+0.043
 bears+0.041
 mice+0.039
 rabbits+0.039
Neg logit contributions
itating-0.047
inkle-0.047
rig-0.046
ews-0.045
?",-0.045
Token'd
Token ID1549
Feature activation-3.17e+00

Pos logit contributions
itating+0.094
inkle+0.094
rig+0.092
shadow+0.090
ews+0.089
Neg logit contributions
 bear-0.051
 robbers-0.049
 bears-0.048
 mice-0.048
 rabbits-0.046
Token make
Token ID787
Feature activation-1.17e+00

Pos logit contributions
itating+0.165
rig+0.159
ews+0.158
inkle+0.158
shadow+0.157
Neg logit contributions
 bear-0.110
 robbers-0.104
 squirrel-0.102
 rabbits-0.096
 villains-0.096
Token.
Token ID13
Feature activation-1.63e-01

Pos logit contributions
itating+0.079
rig+0.077
shadow+0.075
inkle+0.075
ews+0.074
Neg logit contributions
 bear-0.024
 bears-0.023
 mice-0.021
 rabbits-0.019
 robbers-0.017
Token Soon
Token ID15894
Feature activation-9.95e-01

Pos logit contributions
itating+0.007
inkle+0.007
rig+0.007
shadow+0.007
ews+0.007
Neg logit contributions
 bear-0.007
 robbers-0.007
 bears-0.006
 mice-0.006
 rabbits-0.006
Token,
Token ID11
Feature activation+4.80e-01

Pos logit contributions
itating+0.049
rig+0.048
inkle+0.048
shadow+0.046
ews+0.045
Neg logit contributions
 bear-0.037
 bears-0.036
 robbers-0.035
 mice-0.035
 rabbits-0.034
Token Mom
Token ID11254
Feature activation-2.27e-01

Pos logit contributions
 bear+0.015
 bears+0.014
 mice+0.013
 rabbits+0.013
 squirrel+0.013
Neg logit contributions
rig-0.029
inkle-0.029
itating-0.029
shadow-0.027
iver-0.026
Token was
Token ID373
Feature activation-4.85e-01

Pos logit contributions
 robbers+0.003
 bear+0.002
 mice+0.002
 bears+0.002
 rabbits+0.002
Neg logit contributions
inkle-0.004
itating-0.004
rig-0.004
shadow-0.003
ews-0.003
Token so
Token ID523
Feature activation-1.50e+00

Pos logit contributions
inkle+0.020
rig+0.019
itating+0.019
apers+0.018
mmm+0.018
Neg logit contributions
 bear-0.023
 bears-0.022
 squirrel-0.021
 rabbits-0.021
 robbers-0.021
Token pleased
Token ID10607
Feature activation-8.90e-01

Pos logit contributions
apers+0.056
inkle+0.055
itating+0.055
rig+0.054
?",+0.051
Neg logit contributions
 bear-0.070
 squirrel-0.066
 rac-0.064
 bears-0.064
 mice-0.063
Token that
Token ID326
Feature activation-3.68e-01

Pos logit contributions
inkle+0.045
itating+0.043
rig+0.043
ews+0.042
shadow+0.040
Neg logit contributions
 bear-0.034
 squirrel-0.031
 bears-0.031
 rabbits-0.030
 robbers-0.030
Token she
Token ID673
Feature activation-1.08e+00

Pos logit contributions
itating+0.018
inkle+0.018
rig+0.017
shadow+0.017
?",+0.016
Neg logit contributions
 bear-0.013
 robbers-0.013
 bears-0.013
 mice-0.012
 rabbits-0.012
Token almost
Token ID2048
Feature activation-3.15e+00

Pos logit contributions
itating+0.061
inkle+0.061
rig+0.060
ews+0.058
shadow+0.058
Neg logit contributions
 bear-0.031
 robbers-0.029
 bears-0.028
 mice-0.027
 squirrel-0.027
Token found
Token ID1043
Feature activation-1.05e+00

Pos logit contributions
itating+0.159
inkle+0.158
rig+0.154
shadow+0.151
ews+0.150
Neg logit contributions
 bear-0.108
 robbers-0.104
 bears-0.103
 mice-0.101
 rabbits-0.099
Token an
Token ID281
Feature activation-1.66e-01

Pos logit contributions
itating+0.043
inkle+0.043
rig+0.041
shadow+0.040
ews+0.040
Neg logit contributions
 bear-0.045
 robbers-0.045
 bears-0.044
 mice-0.043
 rabbits-0.042
Token escape
Token ID6654
Feature activation-9.39e-01

Pos logit contributions
itating+0.006
inkle+0.006
rig+0.006
shadow+0.006
ews+0.006
Neg logit contributions
 bear-0.008
 robbers-0.008
 bears-0.008
 mice-0.007
 squirrel-0.007
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
itating+0.045
inkle+0.045
rig+0.044
shadow+0.043
ews+0.042
Neg logit contributions
 bear-0.034
 robbers-0.033
 bears-0.033
 mice-0.032
 rabbits-0.031
Token
Token ID220
Feature activation-9.57e-02

Pos logit contributions
itating+0.007
inkle+0.007
rig+0.007
ews+0.007
shadow+0.007
Neg logit contributions
 bear-0.008
 bears-0.008
 robbers-0.008
 mice-0.008
 villains-0.008
Token them
Token ID606
Feature activation-9.51e-01

Pos logit contributions
inkle+0.004
itating+0.004
rig+0.004
?",+0.004
 early+0.003
Neg logit contributions
 bear-0.005
pill-0.005
 robbers-0.005
 mice-0.005
 bears-0.005
Token all
Token ID477
Feature activation-2.30e-01

Pos logit contributions
itating+0.039
inkle+0.037
rig+0.037
ews+0.036
shadow+0.036
Neg logit contributions
 bear-0.040
 robbers-0.039
 bears-0.038
 mice-0.038
 rabbits-0.037
Token about
Token ID546
Feature activation-1.19e+00

Pos logit contributions
itating+0.005
inkle+0.005
rig+0.005
shadow+0.004
ews+0.004
Neg logit contributions
 bear-0.015
 robbers-0.014
 bears-0.014
 mice-0.014
 rabbits-0.014
Token what
Token ID644
Feature activation+8.23e-01

Pos logit contributions
inkle+0.048
rig+0.048
itating+0.048
?",+0.046
ews+0.046
Neg logit contributions
 robbers-0.045
 bear-0.045
B-0.044
 villains-0.043
 mice-0.043
Token he
Token ID339
Feature activation-1.64e+00

Pos logit contributions
 robbers+0.027
 bear+0.027
 bears+0.026
ted+0.026
pill+0.026
Neg logit contributions
?",-0.036
 yet-0.034
 common-0.034
?"-0.032
 early-0.032
Token'd
Token ID1549
Feature activation-3.15e+00

Pos logit contributions
inkle+0.075
rig+0.072
?",+0.072
itating+0.071
shadow+0.069
Neg logit contributions
 robbers-0.063
 bears-0.061
 mice-0.060
 bear-0.059
 rabbits-0.058
Token seen
Token ID1775
Feature activation-1.53e+00

Pos logit contributions
itating+0.164
inkle+0.155
rig+0.154
ews+0.154
shadow+0.150
Neg logit contributions
 bear-0.112
 robbers-0.107
 squirrel-0.104
 villains-0.100
 rabbits-0.098
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
itating+0.076
rig+0.075
inkle+0.074
shadow+0.073
ews+0.072
Neg logit contributions
 bear-0.059
 bears-0.055
 rabbits-0.053
 robbers-0.053
 mice-0.052
Token His
Token ID2399
Feature activation-1.57e-01

Pos logit contributions
 bear+0.009
 bears+0.008
 robbers+0.008
 mice+0.008
 rabbits+0.008
Neg logit contributions
itating-0.012
inkle-0.012
rig-0.012
ews-0.012
shadow-0.012
Token friends
Token ID2460
Feature activation-5.26e-01

Pos logit contributions
inkle+0.008
rig+0.007
ossom+0.007
 early+0.007
ews+0.007
Neg logit contributions
pill-0.005
B-0.005
 robbers-0.005
emaker-0.005
Mic-0.005
Token thought
Token ID1807
Feature activation-1.71e-01

Pos logit contributions
itating+0.029
inkle+0.029
rig+0.029
shadow+0.028
ews+0.028
Neg logit contributions
 bear-0.015
 robbers-0.014
 bears-0.014
 mice-0.014
 rabbits-0.013
Token was
Token ID373
Feature activation-4.84e-01

Pos logit contributions
 bear+0.004
 robbers+0.004
 bears+0.004
 mice+0.003
 rabbits+0.003
Neg logit contributions
itating-0.006
inkle-0.006
rig-0.006
shadow-0.006
ews-0.006
Token so
Token ID523
Feature activation-1.31e+00

Pos logit contributions
inkle+0.021
itating+0.021
rig+0.020
apers+0.020
mmm+0.019
Neg logit contributions
 bear-0.022
 bears-0.021
 rabbits-0.020
 mice-0.020
 squirrel-0.020
Token happy
Token ID3772
Feature activation+2.52e-01

Pos logit contributions
itating+0.051
apers+0.050
rig+0.050
inkle+0.050
shadow+0.049
Neg logit contributions
 bear-0.059
 bears-0.055
 squirrel-0.055
 mice-0.055
 rabbits-0.054
Token that
Token ID326
Feature activation-2.16e-01

Pos logit contributions
 bear+0.010
 bears+0.010
 mice+0.009
 rabbits+0.009
 squirrel+0.009
Neg logit contributions
inkle-0.012
itating-0.012
rig-0.011
shadow-0.011
ews-0.011
Token she
Token ID673
Feature activation-1.03e+00

Pos logit contributions
itating+0.010
inkle+0.010
shadow+0.010
rig+0.010
?",+0.010
Neg logit contributions
 bear-0.008
 robbers-0.008
 bears-0.007
 mice-0.007
 rabbits-0.007
Token almost
Token ID2048
Feature activation-3.14e+00

Pos logit contributions
itating+0.059
inkle+0.058
rig+0.057
ews+0.056
shadow+0.055
Neg logit contributions
 bear-0.031
 bears-0.028
 robbers-0.028
 squirrel-0.027
 mice-0.027
Token squ
Token ID2809
Feature activation-2.44e-01

Pos logit contributions
itating+0.151
inkle+0.150
rig+0.146
shadow+0.144
ews+0.142
Neg logit contributions
 bear-0.114
 robbers-0.111
 bears-0.110
 mice-0.108
 rabbits-0.105
Tokeneal
Token ID2287
Feature activation-3.00e-01

Pos logit contributions
itating+0.010
inkle+0.010
rig+0.010
shadow+0.009
ews+0.009
Neg logit contributions
 bear-0.011
 bears-0.010
 robbers-0.010
 mice-0.010
 rabbits-0.010
Tokened
Token ID276
Feature activation+5.61e-01

Pos logit contributions
inkle+0.019
rig+0.019
itating+0.018
ews+0.018
shadow+0.018
Neg logit contributions
 bear-0.007
 bears-0.007
 mice-0.006
 robbers-0.006
 squirrel-0.006
Token.
Token ID13
Feature activation-2.52e-01

Pos logit contributions
 bear+0.027
 bears+0.026
 robbers+0.025
 mice+0.025
 squirrel+0.025
Neg logit contributions
inkle-0.021
itating-0.021
rig-0.021
ews-0.020
shadow-0.020
Token
Token ID198
Feature activation-1.25e-01

Pos logit contributions
itating+0.011
inkle+0.011
rig+0.010
shadow+0.010
ews+0.010
Neg logit contributions
 bear-0.010
 robbers-0.010
 bears-0.010
 mice-0.010
 rabbits-0.010
Token's
Token ID338
Feature activation-3.27e-02

Pos logit contributions
 bear+0.015
 robbers+0.015
 bears+0.015
 mice+0.015
 rabbits+0.014
Neg logit contributions
inkle-0.024
itating-0.024
rig-0.024
ews-0.023
?",-0.023
Token mom
Token ID1995
Feature activation-1.35e-01

Pos logit contributions
 yet+0.001
ute+0.001
inkle+0.001
itating+0.001
rig+0.001
Neg logit contributions
pill-0.002
 villains-0.002
 robbers-0.002
orns-0.002
 seaw-0.002
Token asked
Token ID1965
Feature activation+9.44e-01

Pos logit contributions
itating+0.007
inkle+0.007
rig+0.007
shadow+0.007
ews+0.007
Neg logit contributions
 bear-0.004
 bears-0.004
 robbers-0.004
 mice-0.004
 squirrel-0.004
Token her
Token ID607
Feature activation+1.64e+00

Pos logit contributions
 bear+0.030
 robbers+0.029
 bears+0.028
 mice+0.027
 squirrel+0.027
Neg logit contributions
itating-0.050
inkle-0.050
rig-0.049
shadow-0.048
ews-0.047
Token to
Token ID284
Feature activation+1.25e+00

Pos logit contributions
 bear+0.073
 robbers+0.071
 bears+0.070
 mice+0.069
 rabbits+0.068
Neg logit contributions
itating-0.067
inkle-0.066
rig-0.064
shadow-0.062
ews-0.062
Token help
Token ID1037
Feature activation+2.70e+00

Pos logit contributions
 bear+0.044
 robbers+0.041
 bears+0.039
 squirrel+0.038
 mice+0.038
Neg logit contributions
itating-0.067
inkle-0.065
rig-0.064
ews-0.063
shadow-0.063
Token with
Token ID351
Feature activation+6.70e-01

Pos logit contributions
 bear+0.101
 mice+0.095
 bears+0.093
 robbers+0.092
B+0.089
Neg logit contributions
itating-0.136
rig-0.132
inkle-0.130
shadow-0.127
ews-0.125
Token the
Token ID262
Feature activation+7.01e-01

Pos logit contributions
 villains+0.026
 bear+0.025
 robbers+0.025
 squirrel+0.025
 rabbits+0.024
Neg logit contributions
inkle-0.030
?",-0.028
 ours-0.027
itating-0.027
ews-0.027
Token groceries
Token ID38464
Feature activation-2.84e-01

Pos logit contributions
 villains+0.023
pill+0.023
Carl+0.022
B+0.022
 robbers+0.021
Neg logit contributions
?",-0.032
 yet-0.031
inkle-0.031
 ours-0.031
itating-0.030
Token.
Token ID13
Feature activation+4.65e-01

Pos logit contributions
itating+0.018
inkle+0.018
rig+0.018
shadow+0.017
ews+0.017
Neg logit contributions
 bear-0.007
 robbers-0.006
 bears-0.006
 mice-0.006
 t-0.005
Token Lily
Token ID20037
Feature activation+7.07e-02

Pos logit contributions
 bear+0.012
 mice+0.010
 robbers+0.010
B+0.010
 balls+0.009
Neg logit contributions
inkle-0.029
itating-0.028
rig-0.028
shadow-0.028
ews-0.027
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
 bear+0.076
 mice+0.073
 robbers+0.071
 bears+0.071
 rabbits+0.068
Neg logit contributions
inkle-0.132
itating-0.131
rig-0.128
shadow-0.127
ews-0.126
Token They
Token ID1119
Feature activation+4.28e-01

Pos logit contributions
inkle+0.019
itating+0.019
rig+0.018
shadow+0.018
ews+0.017
Neg logit contributions
 bear-0.014
 robbers-0.013
 mice-0.013
 squirrel-0.013
 bears-0.013
Token can
Token ID460
Feature activation-8.30e-02

Pos logit contributions
 bear+0.019
 robbers+0.019
 bears+0.019
 mice+0.019
 rabbits+0.018
Neg logit contributions
itating-0.017
inkle-0.016
rig-0.016
shadow-0.015
ews-0.015
Token ask
Token ID1265
Feature activation+1.28e+00

Pos logit contributions
itating+0.003
inkle+0.003
rig+0.003
shadow+0.003
ews+0.003
Neg logit contributions
 bear-0.004
 robbers-0.004
 bears-0.003
 mice-0.003
 rabbits-0.003
Token for
Token ID329
Feature activation+8.24e-02

Pos logit contributions
 bear+0.049
 bears+0.047
 mice+0.047
 robbers+0.046
 rabbits+0.046
Neg logit contributions
itating-0.065
inkle-0.063
rig-0.062
shadow-0.060
ews-0.060
Token help
Token ID1037
Feature activation+2.85e+00

Pos logit contributions
 bear+0.002
 bears+0.002
 robbers+0.002
 rabbits+0.002
 mice+0.002
Neg logit contributions
inkle-0.005
itating-0.005
shadow-0.005
rig-0.004
ews-0.004
Token.
Token ID13
Feature activation-1.30e-01

Pos logit contributions
 bear+0.084
 mice+0.079
 bears+0.078
 robbers+0.077
 rabbits+0.074
Neg logit contributions
inkle-0.164
itating-0.162
rig-0.160
shadow-0.157
ews-0.156
Token They
Token ID1119
Feature activation+5.62e-01

Pos logit contributions
inkle+0.007
itating+0.007
rig+0.007
shadow+0.007
ews+0.007
Neg logit contributions
 bear-0.004
 robbers-0.004
 mice-0.004
 squirrel-0.004
B-0.004
Token learn
Token ID2193
Feature activation+1.11e+00

Pos logit contributions
 robbers+0.026
 bears+0.026
B+0.026
 mice+0.026
 bear+0.026
Neg logit contributions
inkle-0.020
itating-0.019
rig-0.019
?",-0.018
ossom-0.017
Token that
Token ID326
Feature activation-1.45e-01

Pos logit contributions
 bear+0.042
 bears+0.040
 mice+0.039
 robbers+0.039
 rabbits+0.038
Neg logit contributions
inkle-0.054
itating-0.054
shadow-0.051
rig-0.051
ossom-0.050
Token sometimes
Token ID3360
Feature activation-8.54e-01

Pos logit contributions
itating+0.006
inkle+0.005
rig+0.005
ews+0.005
shadow+0.005
Neg logit contributions
 bear-0.006
 robbers-0.006
 bears-0.006
 mice-0.006
B-0.006
Token not
Token ID407
Feature activation-2.88e-01

Pos logit contributions
 bear+0.005
 bears+0.005
 mice+0.005
 rabbits+0.005
 robbers+0.005
Neg logit contributions
itating-0.005
rig-0.005
inkle-0.005
shadow-0.005
ews-0.005
Token as
Token ID355
Feature activation+6.80e-01

Pos logit contributions
itating+0.013
inkle+0.012
rig+0.012
ews+0.012
shadow+0.012
Neg logit contributions
 bear-0.013
 bears-0.012
 robbers-0.012
 mice-0.012
 rabbits-0.012
Token bright
Token ID6016
Feature activation+2.11e+00

Pos logit contributions
 bear+0.028
 robbers+0.027
 bears+0.027
 mice+0.027
 rabbits+0.026
Neg logit contributions
itating-0.030
inkle-0.030
rig-0.029
shadow-0.028
ews-0.028
Token as
Token ID355
Feature activation+9.18e-01

Pos logit contributions
 bear+0.092
 bears+0.089
 mice+0.088
 robbers+0.088
 rabbits+0.085
Neg logit contributions
itating-0.091
inkle-0.087
rig-0.087
shadow-0.085
ews-0.083
Token glowing
Token ID21377
Feature activation+2.17e+00

Pos logit contributions
 bear+0.036
 bears+0.035
 robbers+0.035
 mice+0.035
 rabbits+0.034
Neg logit contributions
itating-0.043
inkle-0.041
rig-0.041
shadow-0.040
ews-0.039
Token hearts
Token ID11954
Feature activation+2.71e+00

Pos logit contributions
 bear+0.084
 bears+0.081
 mice+0.080
 robbers+0.079
 rabbits+0.078
Neg logit contributions
itating-0.103
inkle-0.101
rig-0.100
shadow-0.099
ews-0.096
Token."
Token ID526
Feature activation-3.04e-01

Pos logit contributions
 bear+0.082
 bears+0.078
 mice+0.075
 rabbits+0.074
 robbers+0.074
Neg logit contributions
rig-0.150
itating-0.149
shadow-0.145
inkle-0.144
har-0.141
Token<|endoftext|>
Token ID50256
Feature activation+4.81e-01

Pos logit contributions
itating+0.014
inkle+0.014
rig+0.014
shadow+0.014
ews+0.013
Neg logit contributions
 bear-0.012
 robbers-0.011
 bears-0.011
 mice-0.011
 squirrel-0.011
TokenTim
Token ID14967
Feature activation+3.36e-01

Pos logit contributions
 robbers+0.020
 bear+0.020
 bears+0.019
 villains+0.019
 mice+0.019
Neg logit contributions
inkle-0.020
itating-0.020
?",-0.019
rig-0.019
ews-0.018
Token and
Token ID290
Feature activation-4.33e-01

Pos logit contributions
 bear+0.014
 bears+0.013
 robbers+0.012
 squirrel+0.012
 mice+0.012
Neg logit contributions
itating-0.016
inkle-0.015
shadow-0.015
rig-0.015
ews-0.015
Token Sue
Token ID26089
Feature activation-4.14e-01

Pos logit contributions
itating+0.024
inkle+0.024
rig+0.023
shadow+0.023
ews+0.022
Neg logit contributions
 bear-0.014
 robbers-0.013
 bears-0.013
 mice-0.012
 squirrel-0.012
Token,
Token ID11
Feature activation+1.94e-01

Pos logit contributions
 bear+0.052
 bears+0.048
 mice+0.048
 robbers+0.046
 rabbits+0.044
Neg logit contributions
itating-0.118
rig-0.117
inkle-0.116
shadow-0.114
ews-0.114
Token so
Token ID523
Feature activation-1.29e+00

Pos logit contributions
 bear+0.010
 robbers+0.010
 squirrel+0.010
 bears+0.010
 rabbits+0.010
Neg logit contributions
inkle-0.008
itating-0.007
ossom-0.007
ews-0.006
rig-0.006
Token she
Token ID673
Feature activation-3.51e-01

Pos logit contributions
inkle+0.060
itating+0.059
shadow+0.057
ews+0.056
rig+0.056
Neg logit contributions
 bear-0.047
 robbers-0.047
 bears-0.045
 mice-0.045
 squirrel-0.044
Token asked
Token ID1965
Feature activation+7.35e-01

Pos logit contributions
inkle+0.018
itating+0.018
rig+0.017
shadow+0.017
ews+0.017
Neg logit contributions
 bear-0.012
 robbers-0.011
 bears-0.011
 mice-0.011
 rabbits-0.011
Token for
Token ID329
Feature activation+4.28e-02

Pos logit contributions
 robbers+0.028
 bear+0.028
 squirrel+0.027
 villains+0.026
 bears+0.026
Neg logit contributions
inkle-0.033
itating-0.032
?",-0.031
rig-0.031
shadow-0.031
Token help
Token ID1037
Feature activation+2.71e+00

Pos logit contributions
 bear+0.001
 bears+0.001
pill+0.001
 robbers+0.001
 squirrel+0.001
Neg logit contributions
inkle-0.002
shadow-0.002
?",-0.002
 early-0.002
mmm-0.002
Token from
Token ID422
Feature activation+4.21e-02

Pos logit contributions
 bear+0.067
 bears+0.060
 mice+0.059
 robbers+0.058
 rabbits+0.055
Neg logit contributions
inkle-0.167
itating-0.166
rig-0.164
ews-0.161
shadow-0.160
Token her
Token ID607
Feature activation+6.73e-01

Pos logit contributions
 bear+0.002
 robbers+0.002
 bears+0.001
 mice+0.001
 squirrel+0.001
Neg logit contributions
inkle-0.002
itating-0.002
rig-0.002
shadow-0.002
ews-0.002
Token bear
Token ID6842
Feature activation+7.91e-01

Pos logit contributions
 robbers+0.024
 bear+0.024
 bears+0.023
 squirrel+0.023
B+0.023
Neg logit contributions
inkle-0.031
rig-0.030
itating-0.030
?",-0.029
ews-0.029
Token!
Token ID0
Feature activation+1.91e-01

Pos logit contributions
 bear+0.026
 robbers+0.026
 bears+0.025
 mice+0.025
 squirrel+0.024
Neg logit contributions
itating-0.039
inkle-0.038
rig-0.038
shadow-0.037
ews-0.037
Token Together
Token ID17083
Feature activation-4.39e-01

Pos logit contributions
 bear+0.008
 robbers+0.008
 bears+0.008
 mice+0.008
 rabbits+0.007
Neg logit contributions
itating-0.008
inkle-0.008
rig-0.008
shadow-0.008
ews-0.008
Token fixed
Token ID5969
Feature activation-2.49e-02

Pos logit contributions
itating+0.011
inkle+0.011
rig+0.011
shadow+0.011
ews+0.011
Neg logit contributions
 bear-0.006
 bears-0.006
 mice-0.006
 robbers-0.006
 rabbits-0.005
Token things
Token ID1243
Feature activation-6.07e-01

Pos logit contributions
itating+0.001
inkle+0.001
rig+0.001
shadow+0.001
ews+0.001
Neg logit contributions
 bear-0.001
 bears-0.001
 mice-0.001
 robbers-0.001
 rabbits-0.001
Token and
Token ID290
Feature activation+1.41e-01

Pos logit contributions
inkle+0.028
itating+0.028
rig+0.028
shadow+0.027
ews+0.027
Neg logit contributions
 bear-0.023
 robbers-0.021
 bears-0.021
 mice-0.021
 squirrel-0.021
Token asked
Token ID1965
Feature activation+7.25e-01

Pos logit contributions
 bear+0.005
 robbers+0.005
 bears+0.005
 mice+0.005
 rabbits+0.005
Neg logit contributions
itating-0.007
inkle-0.007
rig-0.006
shadow-0.006
ews-0.006
Token for
Token ID329
Feature activation+1.12e-01

Pos logit contributions
 bear+0.030
 robbers+0.029
 bears+0.029
 mice+0.029
 rabbits+0.028
Neg logit contributions
itating-0.031
inkle-0.031
rig-0.030
shadow-0.029
ews-0.029
Token help
Token ID1037
Feature activation+2.75e+00

Pos logit contributions
 bear+0.003
pill+0.003
 bears+0.003
 robbers+0.003
 rabbits+0.003
Neg logit contributions
shadow-0.006
inkle-0.006
?",-0.005
 ours-0.005
itating-0.005
Token.
Token ID13
Feature activation+3.75e-01

Pos logit contributions
 bear+0.085
 robbers+0.080
 bears+0.079
 mice+0.078
 rabbits+0.076
Neg logit contributions
itating-0.149
inkle-0.149
rig-0.146
shadow-0.142
ews-0.141
Token The
Token ID383
Feature activation+8.93e-02

Pos logit contributions
 bear+0.016
 robbers+0.015
 mice+0.015
 bears+0.014
 rabbits+0.014
Neg logit contributions
inkle-0.018
itating-0.016
rig-0.016
shadow-0.016
ews-0.015
Token man
Token ID582
Feature activation-3.55e-02

Pos logit contributions
pill+0.003
ted+0.003
B+0.003
Mic+0.002
orns+0.002
Neg logit contributions
itating-0.004
inkle-0.004
rig-0.004
har-0.004
icing-0.004
Token at
Token ID379
Feature activation-3.12e-01

Pos logit contributions
itating+0.002
inkle+0.002
rig+0.002
shadow+0.002
ews+0.002
Neg logit contributions
 bear-0.001
 bears-0.001
 robbers-0.001
 mice-0.001
 squirrel-0.001
Token the
Token ID262
Feature activation+9.08e-02

Pos logit contributions
itating+0.016
inkle+0.015
rig+0.015
shadow+0.015
ews+0.015
Neg logit contributions
 bear-0.012
 robbers-0.011
 bears-0.011
 mice-0.011
 rabbits-0.010
Token pile
Token ID14540
Feature activation-8.70e-02

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 mice+0.001
 rabbits+0.001
Neg logit contributions
inkle-0.002
itating-0.002
rig-0.002
shadow-0.002
ews-0.002
Token of
Token ID286
Feature activation-9.46e-02

Pos logit contributions
itating+0.005
rig+0.005
inkle+0.005
ews+0.005
shadow+0.005
Neg logit contributions
 bear-0.003
 bears-0.003
 mice-0.002
 balls-0.002
 rabbits-0.002
Token leaves
Token ID5667
Feature activation+3.82e-01

Pos logit contributions
inkle+0.006
itating+0.006
rig+0.006
shadow+0.006
ews+0.006
Neg logit contributions
 bear-0.002
 robbers-0.002
 bears-0.002
 villains-0.002
 mice-0.002
Token!"
Token ID2474
Feature activation+2.98e-01

Pos logit contributions
 bear+0.018
 bears+0.017
 balls+0.017
 mice+0.017
 rabbits+0.016
Neg logit contributions
itating-0.016
rig-0.015
ews-0.015
inkle-0.015
shadow-0.014
Token Lily
Token ID20037
Feature activation+4.78e-01

Pos logit contributions
 bear+0.007
 robbers+0.007
 mice+0.007
 bears+0.007
 squirrel+0.006
Neg logit contributions
itating-0.019
inkle-0.019
rig-0.018
shadow-0.018
ossom-0.018
Token says
Token ID1139
Feature activation+7.76e-01

Pos logit contributions
 bear+0.020
 robbers+0.019
 bears+0.019
 mice+0.019
 rabbits+0.019
Neg logit contributions
itating-0.021
inkle-0.021
rig-0.020
shadow-0.020
ews-0.019
Token.
Token ID13
Feature activation+5.34e-01

Pos logit contributions
 bear+0.024
 robbers+0.023
 bears+0.023
 mice+0.022
 rabbits+0.022
Neg logit contributions
itating-0.042
inkle-0.041
rig-0.040
shadow-0.040
ews-0.039
Token She
Token ID1375
Feature activation+1.29e-01

Pos logit contributions
 bear+0.021
 robbers+0.020
 bears+0.020
 mice+0.020
 rabbits+0.019
Neg logit contributions
itating-0.024
inkle-0.024
rig-0.024
shadow-0.023
ews-0.023
Token and
Token ID290
Feature activation-4.60e-01

Pos logit contributions
 robbers+0.006
 villains+0.006
 bear+0.005
 squirrel+0.005
 mice+0.005
Neg logit contributions
inkle-0.005
rig-0.005
itating-0.005
?",-0.005
ews-0.005
Token Tom
Token ID4186
Feature activation-3.78e-01

Pos logit contributions
inkle+0.017
itating+0.016
ews+0.016
rig+0.016
?",+0.016
Neg logit contributions
 villains-0.020
 bear-0.020
B-0.019
 robbers-0.019
 mice-0.019
Token run
Token ID1057
Feature activation+7.16e-01

Pos logit contributions
inkle+0.014
rig+0.014
itating+0.014
?",+0.013
ist+0.013
Neg logit contributions
 villains-0.017
 robbers-0.017
 bear-0.016
 mice-0.016
 skeletons-0.016
Token see
Token ID766
Feature activation-8.50e-01

Pos logit contributions
inkle+0.021
itating+0.021
rig+0.021
ews+0.020
shadow+0.020
Neg logit contributions
 bear-0.022
 robbers-0.020
 bears-0.020
 mice-0.020
 squirrel-0.020
Token the
Token ID262
Feature activation+3.87e-02

Pos logit contributions
itating+0.036
rig+0.036
inkle+0.034
shadow+0.034
 early+0.034
Neg logit contributions
 robbers-0.033
 villains-0.032
 mice-0.029
 bear-0.029
 bears-0.029
Token doctor
Token ID6253
Feature activation-6.94e-01

Pos logit contributions
 robbers+0.001
 shields+0.001
 mice+0.001
 villains+0.001
 bears+0.001
Neg logit contributions
itating-0.002
inkle-0.002
rig-0.002
 yet-0.002
har-0.002
Token who
Token ID508
Feature activation+7.83e-01

Pos logit contributions
itating+0.036
inkle+0.036
rig+0.035
shadow+0.035
ews+0.034
Neg logit contributions
 bear-0.023
 bears-0.021
 robbers-0.021
 mice-0.021
 squirrel-0.020
Token made
Token ID925
Feature activation-1.06e+00

Pos logit contributions
 robbers+0.026
 bear+0.025
 bears+0.024
 mice+0.024
 rabbits+0.024
Neg logit contributions
inkle-0.040
itating-0.039
rig-0.038
?",-0.037
shadow-0.037
Token his
Token ID465
Feature activation+6.02e-01

Pos logit contributions
inkle+0.057
rig+0.055
itating+0.054
shadow+0.053
 early+0.052
Neg logit contributions
 robbers-0.034
 bear-0.030
 villains-0.030
 rabbits-0.029
 bears-0.028
Token paw
Token ID41827
Feature activation+3.95e-01

Pos logit contributions
 robbers+0.024
 bears+0.022
 mice+0.022
 rabbits+0.022
 bear+0.022
Neg logit contributions
inkle-0.026
rig-0.026
itating-0.025
shadow-0.025
ossom-0.024
Token all
Token ID477
Feature activation-7.73e-02

Pos logit contributions
 bear+0.018
 robbers+0.017
 bears+0.017
 mice+0.017
 rabbits+0.017
Neg logit contributions
itating-0.015
inkle-0.015
rig-0.015
shadow-0.015
ews-0.014
Token better
Token ID1365
Feature activation+4.94e-01

Pos logit contributions
itating+0.003
inkle+0.003
rig+0.003
shadow+0.003
ews+0.003
Neg logit contributions
 bear-0.004
 robbers-0.004
 bears-0.003
 mice-0.003
 rabbits-0.003
Token.
Token ID13
Feature activation+1.28e-01

Pos logit contributions
 robbers+0.019
pill+0.019
 bear+0.019
 rabbits+0.018
 mice+0.018
Neg logit contributions
inkle-0.021
 yet-0.020
shadow-0.020
itating-0.020
 early-0.019
Token P
Token ID350
Feature activation+3.22e-01

Pos logit contributions
 bear+0.006
 robbers+0.006
 bears+0.006
 mice+0.006
 squirrel+0.006
Neg logit contributions
itating-0.005
inkle-0.005
rig-0.005
ews-0.004
shadow-0.004
Token airport
Token ID9003
Feature activation-1.06e+00

Pos logit contributions
 bear+0.002
 robbers+0.002
 bears+0.002
 mice+0.002
 rabbits+0.002
Neg logit contributions
itating-0.002
inkle-0.002
rig-0.002
shadow-0.002
ews-0.002
Token and
Token ID290
Feature activation+4.82e-01

Pos logit contributions
itating+0.053
inkle+0.052
rig+0.052
shadow+0.049
apers+0.049
Neg logit contributions
 bear-0.039
 bears-0.035
 robbers-0.034
 rabbits-0.033
 squirrel-0.033
Token it
Token ID340
Feature activation+1.78e-01

Pos logit contributions
 bear+0.018
 bears+0.016
 robbers+0.016
 mice+0.016
 rabbits+0.015
Neg logit contributions
itating-0.025
inkle-0.024
rig-0.024
shadow-0.023
ews-0.023
Token was
Token ID373
Feature activation+1.11e+00

Pos logit contributions
 bear+0.005
 robbers+0.005
 bears+0.005
 mice+0.005
 rabbits+0.005
Neg logit contributions
itating-0.010
inkle-0.010
rig-0.010
shadow-0.009
ews-0.009
Token time
Token ID640
Feature activation+2.91e-01

Pos logit contributions
 bear+0.041
 bears+0.038
 t+0.038
 dragons+0.035
 rabbits+0.035
Neg logit contributions
itating-0.057
rig-0.055
ossom-0.054
apers-0.053
ute-0.051
Token to
Token ID284
Feature activation+1.43e+00

Pos logit contributions
 robbers+0.007
 bear+0.007
 t+0.006
 rabbits+0.006
 b+0.006
Neg logit contributions
inkle-0.017
itating-0.017
rig-0.017
iver-0.016
?",-0.016
Token stop
Token ID2245
Feature activation+5.45e-01

Pos logit contributions
 bear+0.043
 bears+0.038
 robbers+0.037
 squirrel+0.036
 rabbits+0.035
Neg logit contributions
itating-0.084
rig-0.080
shadow-0.079
ews-0.079
inkle-0.077
Token.
Token ID13
Feature activation+3.01e-01

Pos logit contributions
 bear+0.018
 bears+0.017
 rabbits+0.016
 robbers+0.016
 mice+0.016
Neg logit contributions
rig-0.030
itating-0.029
inkle-0.028
shadow-0.028
ossom-0.028
Token Daddy
Token ID26926
Feature activation-1.09e+00

Pos logit contributions
 bear+0.011
 robbers+0.010
 bears+0.009
 mice+0.009
 rabbits+0.009
Neg logit contributions
inkle-0.015
itating-0.015
rig-0.015
shadow-0.015
ews-0.014
Token,
Token ID11
Feature activation-8.33e-02

Pos logit contributions
itating+0.055
inkle+0.054
rig+0.053
ews+0.051
shadow+0.051
Neg logit contributions
 bear-0.041
 bears-0.037
 robbers-0.036
 squirrel-0.035
 mice-0.035
Token M
Token ID337
Feature activation-5.09e-01

Pos logit contributions
inkle+0.004
itating+0.004
rig+0.004
ossom+0.004
ews+0.004
Neg logit contributions
 bear-0.003
 bears-0.003
 robbers-0.003
 squirrel-0.003
 rabbits-0.003
Token
Token ID198
Feature activation+2.38e-01

Pos logit contributions
 bear+0.027
 robbers+0.026
 mice+0.025
 bears+0.025
 squirrel+0.025
Neg logit contributions
inkle-0.036
itating-0.036
rig-0.035
shadow-0.035
ews-0.034
Token
Token ID198
Feature activation+1.83e-01

Pos logit contributions
 bear+0.008
 robbers+0.007
B+0.007
 squirrel+0.007
 mice+0.007
Neg logit contributions
inkle-0.012
itating-0.012
rig-0.012
shadow-0.012
ews-0.011
Token"
Token ID1
Feature activation+1.60e-01

Pos logit contributions
 robbers+0.006
 bear+0.006
B+0.006
 squirrel+0.006
 mice+0.006
Neg logit contributions
inkle-0.010
rig-0.009
itating-0.009
shadow-0.009
ews-0.009
TokenYes
Token ID5297
Feature activation+3.85e-01

Pos logit contributions
B+0.006
 squirrel+0.006
 robbers+0.006
 bear+0.006
 mice+0.005
Neg logit contributions
inkle-0.009
ews-0.008
rig-0.007
shadow-0.007
itating-0.007
Token,
Token ID11
Feature activation+9.79e-01

Pos logit contributions
 bear+0.012
 bears+0.010
 b+0.010
 squirrel+0.009
 t+0.009
Neg logit contributions
itating-0.023
rig-0.023
ews-0.022
ossom-0.022
shadow-0.021
Token let
Token ID1309
Feature activation+6.64e-01

Pos logit contributions
 squirrel+0.038
 bear+0.038
 beetles+0.037
 balls+0.037
 rabbits+0.036
Neg logit contributions
inkle-0.052
ews-0.049
itating-0.049
ossom-0.048
har-0.047
Token's
Token ID338
Feature activation+4.68e-01

Pos logit contributions
 bear+0.022
 robbers+0.022
 bears+0.021
 mice+0.021
 rabbits+0.021
Neg logit contributions
inkle-0.034
itating-0.034
rig-0.033
shadow-0.032
ews-0.032
Token pick
Token ID2298
Feature activation+7.46e-01

Pos logit contributions
 bear+0.016
 squirrel+0.015
 mice+0.014
 robbers+0.014
 rabbits+0.013
Neg logit contributions
itating-0.025
rig-0.025
shadow-0.024
inkle-0.024
ews-0.024
Token it
Token ID340
Feature activation+4.28e-01

Pos logit contributions
 bear+0.031
 bears+0.030
 mice+0.029
 squirrel+0.028
 rabbits+0.028
Neg logit contributions
itating-0.035
rig-0.034
inkle-0.033
shadow-0.032
ews-0.032
Token!"
Token ID2474
Feature activation+5.15e-01

Pos logit contributions
 bear+0.019
 balls+0.018
 b+0.018
 bears+0.017
 mice+0.017
Neg logit contributions
rig-0.020
itating-0.019
ews-0.018
har-0.018
 outage-0.018
Token Ben
Token ID3932
Feature activation+3.56e-01

Pos logit contributions
 bear+0.014
 robbers+0.013
 bears+0.013
 mice+0.013
 rabbits+0.012
Neg logit contributions
itating-0.030
inkle-0.030
rig-0.029
shadow-0.029
ews-0.028
Token but
Token ID475
Feature activation-1.00e+00

Pos logit contributions
inkle+0.003
itating+0.003
ews+0.003
rig+0.003
?",+0.003
Neg logit contributions
 bear-0.003
 bears-0.003
 rabbits-0.003
 squirrel-0.003
 mice-0.003
Token now
Token ID783
Feature activation-2.53e-01

Pos logit contributions
inkle+0.050
rig+0.050
itating+0.050
ews+0.048
shadow+0.047
Neg logit contributions
 bear-0.037
 robbers-0.034
 bears-0.034
 mice-0.034
 squirrel-0.033
Token she
Token ID673
Feature activation-1.95e-01

Pos logit contributions
inkle+0.011
itating+0.011
?",+0.010
shadow+0.010
ews+0.010
Neg logit contributions
 bear-0.010
 robbers-0.010
 bears-0.010
 mice-0.010
 villains-0.009
Token could
Token ID714
Feature activation-1.21e-01

Pos logit contributions
inkle+0.010
itating+0.010
rig+0.009
ews+0.009
?",+0.009
Neg logit contributions
 robbers-0.007
 bear-0.006
 bears-0.006
 mice-0.006
 rabbits-0.006
Token also
Token ID635
Feature activation-1.15e+00

Pos logit contributions
shadow+0.005
itating+0.005
rig+0.005
ews+0.005
inkle+0.005
Neg logit contributions
 bear-0.005
 bears-0.005
 squirrel-0.005
 rabbits-0.005
 robbers-0.005
Token eat
Token ID4483
Feature activation+7.79e-01

Pos logit contributions
itating+0.057
shadow+0.055
ews+0.053
inkle+0.053
rig+0.052
Neg logit contributions
 bear-0.045
 robbers-0.041
 squirrel-0.040
 bears-0.040
 mice-0.039
Token a
Token ID257
Feature activation-4.55e-01

Pos logit contributions
 bear+0.027
 bears+0.026
 mice+0.025
 rabbits+0.025
 squirrel+0.024
Neg logit contributions
itating-0.042
rig-0.040
shadow-0.040
inkle-0.040
ews-0.039
Token snack
Token ID26906
Feature activation-8.79e-01

Pos logit contributions
itating+0.023
inkle+0.022
rig+0.022
shadow+0.022
ews+0.021
Neg logit contributions
 bear-0.017
 bears-0.015
 robbers-0.015
 mice-0.015
 squirrel-0.015
Token in
Token ID287
Feature activation-5.66e-01

Pos logit contributions
itating+0.044
inkle+0.044
rig+0.043
shadow+0.041
ews+0.041
Neg logit contributions
 bear-0.030
 robbers-0.029
 bears-0.028
 mice-0.028
 rabbits-0.027
Token the
Token ID262
Feature activation-2.96e-01

Pos logit contributions
itating+0.030
rig+0.029
inkle+0.029
shadow+0.029
ews+0.028
Neg logit contributions
 bear-0.019
 bears-0.018
 mice-0.018
 robbers-0.018
 rabbits-0.017
Token water
Token ID1660
Feature activation+1.83e-01

Pos logit contributions
itating+0.014
inkle+0.014
rig+0.014
shadow+0.014
ews+0.013
Neg logit contributions
 bear-0.011
 robbers-0.010
 bears-0.010
 mice-0.010
 rabbits-0.010
Token mom
Token ID1995
Feature activation-5.21e-01

Pos logit contributions
inkle+0.004
 early+0.003
 yet+0.003
rig+0.003
 common+0.003
Neg logit contributions
pill-0.010
orns-0.009
 seaw-0.009
ted-0.009
emaker-0.009
Tokenmy
Token ID1820
Feature activation-4.48e-01

Pos logit contributions
itating+0.019
shadow+0.018
ist+0.017
inkle+0.017
rig+0.017
Neg logit contributions
 villains-0.026
 robbers-0.026
 mice-0.025
pill-0.025
 rabbits-0.024
Token said
Token ID531
Feature activation+1.33e-02

Pos logit contributions
itating+0.019
inkle+0.019
ist+0.018
shadow+0.018
rig+0.018
Neg logit contributions
 villains-0.019
 robbers-0.018
 mice-0.017
 skeletons-0.017
pill-0.017
Token,
Token ID11
Feature activation+4.08e-01

Pos logit contributions
 bear+0.001
 robbers+0.001
 bears+0.001
 mice+0.001
 rabbits+0.001
Neg logit contributions
itating-0.001
inkle-0.001
rig-0.001
shadow-0.001
ews-0.001
Token "
Token ID366
Feature activation-7.29e-02

Pos logit contributions
 bear+0.011
 bears+0.009
 robbers+0.009
 mice+0.009
 squirrel+0.009
Neg logit contributions
inkle-0.026
rig-0.025
itating-0.025
ossom-0.024
ews-0.024
TokenSure
Token ID19457
Feature activation+1.04e-01

Pos logit contributions
inkle+0.003
ews+0.003
itating+0.003
rig+0.003
?",+0.003
Neg logit contributions
B-0.003
 bear-0.003
 squirrel-0.003
 robbers-0.003
 mice-0.003
Token,
Token ID11
Feature activation+9.95e-01

Pos logit contributions
 bear+0.004
 robbers+0.004
 bears+0.004
 mice+0.004
 squirrel+0.004
Neg logit contributions
itating-0.005
rig-0.005
inkle-0.005
ews-0.005
shadow-0.005
Token I
Token ID314
Feature activation+8.17e-01

Pos logit contributions
 bear+0.037
 bears+0.034
 robbers+0.033
 mice+0.033
 squirrel+0.033
Neg logit contributions
itating-0.053
inkle-0.052
ews-0.051
rig-0.050
ossom-0.048
Token'll
Token ID1183
Feature activation-9.45e-01

Pos logit contributions
 bear+0.029
 robbers+0.026
 bears+0.026
 squirrel+0.025
 mice+0.025
Neg logit contributions
itating-0.043
inkle-0.042
rig-0.041
ews-0.041
shadow-0.040
Token get
Token ID651
Feature activation+3.37e-01

Pos logit contributions
itating+0.064
rig+0.063
ews+0.063
inkle+0.062
shadow+0.061
Neg logit contributions
 bear-0.020
 robbers-0.015
 bears-0.014
 squirrel-0.014
 mice-0.013
Token it
Token ID340
Feature activation+8.19e-01

Pos logit contributions
 bear+0.015
 bears+0.014
 robbers+0.014
 mice+0.014
 rabbits+0.014
Neg logit contributions
itating-0.014
rig-0.014
inkle-0.014
ews-0.013
shadow-0.013
Token she
Token ID673
Feature activation+3.64e-01

Pos logit contributions
 bear+0.022
 mice+0.020
 bears+0.020
 squirrel+0.020
 rabbits+0.019
Neg logit contributions
rig-0.038
inkle-0.038
itating-0.038
shadow-0.037
ews-0.036
Token was
Token ID373
Feature activation+8.40e-02

Pos logit contributions
 bear+0.011
 robbers+0.010
 bears+0.010
 squirrel+0.009
 mice+0.009
Neg logit contributions
itating-0.021
inkle-0.021
rig-0.020
shadow-0.020
ews-0.019
Token sitting
Token ID5586
Feature activation-1.61e-01

Pos logit contributions
 bear+0.002
 robbers+0.002
 bears+0.002
 rabbits+0.002
 squirrel+0.002
Neg logit contributions
inkle-0.006
rig-0.006
mmm-0.005
itating-0.005
ossom-0.005
Token in
Token ID287
Feature activation-5.50e-02

Pos logit contributions
rig+0.008
itating+0.008
ews+0.008
inkle+0.008
shadow+0.007
Neg logit contributions
 bear-0.007
 bears-0.006
 mice-0.006
 rabbits-0.006
 squirrel-0.006
Token the
Token ID262
Feature activation+1.02e-01

Pos logit contributions
inkle+0.002
itating+0.002
rig+0.002
shadow+0.002
ews+0.002
Neg logit contributions
 bear-0.002
 robbers-0.002
 bears-0.002
 mice-0.002
 rabbits-0.002
Token park
Token ID3952
Feature activation+1.10e-01

Pos logit contributions
 bears+0.004
 robbers+0.004
 bear+0.004
 mice+0.004
 villains+0.004
Neg logit contributions
itating-0.005
inkle-0.005
rig-0.005
ews-0.004
shadow-0.004
Token listening
Token ID8680
Feature activation+1.10e+00

Pos logit contributions
 bear+0.005
 squirrel+0.005
 mice+0.005
 rabbits+0.005
 robbers+0.005
Neg logit contributions
inkle-0.005
rig-0.005
itating-0.004
shadow-0.004
?",-0.004
Token to
Token ID284
Feature activation-1.57e-01

Pos logit contributions
 bear+0.039
 mice+0.037
 rabbits+0.036
 bears+0.036
 squirrel+0.035
Neg logit contributions
inkle-0.057
itating-0.056
shadow-0.054
rig-0.053
mmm-0.053
Token the
Token ID262
Feature activation-5.61e-01

Pos logit contributions
itating+0.008
inkle+0.008
rig+0.008
shadow+0.007
ews+0.007
Neg logit contributions
 bear-0.005
 robbers-0.005
 bears-0.005
 mice-0.005
 rabbits-0.005
Token birds
Token ID10087
Feature activation-4.38e-01

Pos logit contributions
itating+0.029
rig+0.028
inkle+0.028
ews+0.027
shadow+0.027
Neg logit contributions
 bear-0.018
 robbers-0.018
 bears-0.018
 mice-0.017
 rabbits-0.016
Token ch
Token ID442
Feature activation+9.79e-01

Pos logit contributions
itating+0.020
inkle+0.018
rig+0.018
shadow+0.017
ews+0.017
Neg logit contributions
 robbers-0.018
 bear-0.017
 mice-0.017
 villains-0.017
 bears-0.017
Token brilliant
Token ID10457
Feature activation-6.55e-01

Pos logit contributions
 robbers+0.004
 bears+0.004
 bear+0.004
 mice+0.004
 rabbits+0.004
Neg logit contributions
inkle-0.006
itating-0.006
rig-0.006
shadow-0.005
ews-0.005
Token king
Token ID5822
Feature activation-5.87e-02

Pos logit contributions
itating+0.038
inkle+0.038
rig+0.037
shadow+0.037
ews+0.036
Neg logit contributions
 bear-0.018
 robbers-0.017
 bears-0.017
 mice-0.016
 squirrel-0.016
Token.
Token ID13
Feature activation+4.54e-01

Pos logit contributions
itating+0.002
inkle+0.002
rig+0.002
?",+0.002
ews+0.002
Neg logit contributions
 robbers-0.002
 mice-0.002
 bear-0.002
 bears-0.002
 rabbits-0.002
Token He
Token ID679
Feature activation+5.57e-01

Pos logit contributions
 bear+0.013
 robbers+0.013
 bears+0.012
 mice+0.012
 rabbits+0.012
Neg logit contributions
itating-0.025
inkle-0.025
rig-0.024
shadow-0.024
ews-0.024
Token was
Token ID373
Feature activation-2.09e-01

Pos logit contributions
 robbers+0.019
 mice+0.018
 bear+0.018
 rabbits+0.018
 bears+0.018
Neg logit contributions
inkle-0.027
?",-0.026
rig-0.025
itating-0.025
ews-0.025
Token the
Token ID262
Feature activation-3.43e-01

Pos logit contributions
itating+0.010
rig+0.010
inkle+0.010
shadow+0.009
ossom+0.009
Neg logit contributions
 bear-0.009
 bears-0.008
 robbers-0.008
 mice-0.008
 squirrel-0.008
Token best
Token ID1266
Feature activation-1.53e+00

Pos logit contributions
itating+0.020
inkle+0.020
rig+0.019
shadow+0.019
ews+0.019
Neg logit contributions
 bear-0.009
 robbers-0.008
 bears-0.008
 mice-0.008
 rabbits-0.008
Token king
Token ID5822
Feature activation-6.60e-01

Pos logit contributions
inkle+0.078
itating+0.075
?",+0.074
ossom+0.074
ews+0.074
Neg logit contributions
 robbers-0.045
B-0.043
 mice-0.042
 bears-0.042
 rabbits-0.041
Token in
Token ID287
Feature activation-8.64e-01

Pos logit contributions
itating+0.029
inkle+0.029
rig+0.028
shadow+0.027
?",+0.027
Neg logit contributions
 robbers-0.026
 bear-0.026
 bears-0.025
 mice-0.025
 rabbits-0.024
Token the
Token ID262
Feature activation-8.26e-01

Pos logit contributions
inkle+0.025
 early+0.024
 yet+0.024
 common+0.023
 late+0.022
Neg logit contributions
B-0.043
Carl-0.042
pill-0.042
 robbers-0.041
unn-0.040
Token whole
Token ID2187
Feature activation-3.88e-01

Pos logit contributions
itating+0.038
inkle+0.037
ews+0.036
?",+0.036
ossom+0.035
Neg logit contributions
 robbers-0.029
 bears-0.028
 bear-0.027
 villains-0.027
 mice-0.027
Token explore
Token ID7301
Feature activation-5.44e-01

Pos logit contributions
 bear+0.028
 robbers+0.027
 bears+0.027
 mice+0.026
 rabbits+0.026
Neg logit contributions
itating-0.037
inkle-0.037
rig-0.036
shadow-0.035
ews-0.035
Token the
Token ID262
Feature activation-2.73e-01

Pos logit contributions
itating+0.027
inkle+0.026
rig+0.026
ews+0.025
ossom+0.025
Neg logit contributions
 bear-0.021
 bears-0.021
 mice-0.020
 rabbits-0.020
 robbers-0.019
Token zoo
Token ID26626
Feature activation-6.36e-01

Pos logit contributions
itating+0.014
inkle+0.014
rig+0.014
shadow+0.014
ews+0.013
Neg logit contributions
 bear-0.009
 robbers-0.009
 bears-0.009
 mice-0.008
 rabbits-0.008
Token.
Token ID13
Feature activation-3.34e-01

Pos logit contributions
inkle+0.031
itating+0.031
shadow+0.029
rig+0.029
ews+0.028
Neg logit contributions
 bear-0.024
 bears-0.024
 mice-0.023
 robbers-0.023
 rabbits-0.022
Token Do
Token ID2141
Feature activation-6.06e-02

Pos logit contributions
inkle+0.017
itating+0.015
rig+0.015
ews+0.015
ossom+0.014
Neg logit contributions
 robbers-0.014
 bear-0.013
 mice-0.013
 bears-0.013
 rabbits-0.013
Token you
Token ID345
Feature activation+3.47e-01

Pos logit contributions
mmm+0.002
itating+0.002
shadow+0.002
inkle+0.002
?",+0.002
Neg logit contributions
 bear-0.003
 mice-0.003
 robbers-0.003
 bears-0.003
 rac-0.003
Token want
Token ID765
Feature activation-3.53e-01

Pos logit contributions
 bear+0.013
 robbers+0.012
 squirrel+0.012
 bears+0.011
 hop+0.011
Neg logit contributions
itating-0.019
ews-0.018
har-0.017
shadow-0.017
rig-0.017
Token to
Token ID284
Feature activation+6.57e-01

Pos logit contributions
itating+0.017
inkle+0.017
rig+0.016
shadow+0.016
ossom+0.015
Neg logit contributions
 bear-0.014
 bears-0.014
 robbers-0.013
 mice-0.013
 rabbits-0.013
Token come
Token ID1282
Feature activation-8.52e-01

Pos logit contributions
 bear+0.026
 robbers+0.025
 squirrel+0.024
 bears+0.024
 rabbits+0.024
Neg logit contributions
itating-0.031
rig-0.030
inkle-0.030
shadow-0.029
ews-0.029
Token with
Token ID351
Feature activation+4.05e-01

Pos logit contributions
rig+0.054
ews+0.053
rated+0.049
appointed+0.049
mmm+0.048
Neg logit contributions
 bear-0.031
 squirrel-0.025
 bears-0.024
 rabbits-0.023
 t-0.023
Token me
Token ID502
Feature activation-1.82e-01

Pos logit contributions
 bear+0.016
 bears+0.015
 robbers+0.015
 mice+0.015
 rabbits+0.014
Neg logit contributions
itating-0.020
rig-0.019
inkle-0.019
shadow-0.018
ews-0.018
Token up
Token ID510
Feature activation-6.06e-01

Pos logit contributions
 outage+0.006
rig+0.006
itating+0.006
shadow+0.006
ossom+0.006
Neg logit contributions
 bear-0.009
 him-0.008
 bears-0.008
 t-0.008
 walks-0.008
Token with
Token ID351
Feature activation+3.51e-01

Pos logit contributions
apers+0.029
shadow+0.027
rig+0.027
itating+0.027
 ours+0.026
Neg logit contributions
 bear-0.024
 t-0.022
 b-0.022
 rabbits-0.021
 squirrel-0.021
Token an
Token ID281
Feature activation+4.34e-01

Pos logit contributions
 robbers+0.016
 bears+0.016
 bear+0.016
 villains+0.016
 mice+0.016
Neg logit contributions
inkle-0.013
?",-0.012
itating-0.011
 early-0.011
rig-0.011
Token empty
Token ID6565
Feature activation-1.25e+00

Pos logit contributions
 bear+0.018
 bears+0.017
 mice+0.017
 robbers+0.017
 rabbits+0.017
Neg logit contributions
itating-0.020
shadow-0.019
inkle-0.019
ews-0.018
rig-0.018
Token stomach
Token ID11384
Feature activation-7.08e-02

Pos logit contributions
itating+0.068
shadow+0.065
rig+0.065
inkle+0.064
ews+0.062
Neg logit contributions
 bear-0.043
 robbers-0.039
 bears-0.038
 squirrel-0.038
 rabbits-0.037
Token.
Token ID13
Feature activation+1.36e-01

Pos logit contributions
itating+0.003
inkle+0.003
rig+0.003
ews+0.003
shadow+0.003
Neg logit contributions
 robbers-0.002
 bear-0.002
 bears-0.002
 mice-0.002
 villains-0.002
Token She
Token ID1375
Feature activation+9.30e-02

Pos logit contributions
 bear+0.005
 robbers+0.005
 mice+0.005
 bears+0.005
 squirrel+0.005
Neg logit contributions
inkle-0.007
itating-0.007
rig-0.006
shadow-0.006
ews-0.006
Token was
Token ID373
Feature activation-3.56e-01

Pos logit contributions
 bear+0.003
 robbers+0.003
 bears+0.003
 mice+0.003
 rabbits+0.003
Neg logit contributions
itating-0.005
inkle-0.005
rig-0.005
shadow-0.005
ews-0.005
Token very
Token ID845
Feature activation-1.26e+00

Pos logit contributions
rig+0.015
apers+0.015
inkle+0.015
itating+0.015
mmm+0.015
Neg logit contributions
 bear-0.016
 bears-0.015
 rabbits-0.015
 squirrel-0.014
 mice-0.014
Token lucky
Token ID9670
Feature activation+4.10e-01

Pos logit contributions
itating+0.054
apers+0.054
shadow+0.053
rig+0.052
inkle+0.050
Neg logit contributions
 bear-0.054
 squirrel-0.050
 mice-0.050
 rabbits-0.049
 b-0.049
Token,
Token ID11
Feature activation-5.18e-01

Pos logit contributions
 bear+0.018
 robbers+0.017
 bears+0.017
 mice+0.017
 rabbits+0.017
Neg logit contributions
itating-0.017
inkle-0.017
rig-0.016
shadow-0.016
ews-0.016
Token hungry
Token ID14720
Feature activation+6.69e-01

Pos logit contributions
itating+0.026
inkle+0.026
rig+0.025
ews+0.024
apers+0.024
Neg logit contributions
 bear-0.030
 bears-0.029
 mice-0.028
 robbers-0.028
 rabbits-0.028
Token and
Token ID290
Feature activation-8.11e-01

Pos logit contributions
 robbers+0.039
 bear+0.038
 villains+0.038
 bears+0.038
B+0.038
Neg logit contributions
itating-0.014
 yet-0.014
rig-0.014
inkle-0.014
 early-0.013
Token angry
Token ID7954
Feature activation-8.61e-01

Pos logit contributions
itating+0.035
inkle+0.035
rig+0.034
shadow+0.034
?",+0.033
Neg logit contributions
 bear-0.032
 robbers-0.031
 bears-0.031
 mice-0.030
 rabbits-0.029
Token.
Token ID13
Feature activation-1.05e+00

Pos logit contributions
itating+0.038
inkle+0.036
rig+0.036
shadow+0.036
 yet+0.035
Neg logit contributions
 robbers-0.032
 bear-0.032
 bears-0.031
 mice-0.030
 rabbits-0.030
Token He
Token ID679
Feature activation-5.33e-01

Pos logit contributions
itating+0.058
inkle+0.057
rig+0.056
shadow+0.055
ews+0.054
Neg logit contributions
 bear-0.032
 robbers-0.030
 bears-0.030
 mice-0.029
 squirrel-0.028
Token jumped
Token ID11687
Feature activation-1.76e+00

Pos logit contributions
inkle+0.027
itating+0.027
rig+0.027
ews+0.026
shadow+0.025
Neg logit contributions
 bear-0.017
 robbers-0.017
 bears-0.016
 mice-0.016
 rabbits-0.016
Token out
Token ID503
Feature activation-7.85e-02

Pos logit contributions
inkle+0.075
rig+0.073
itating+0.073
ews+0.072
shadow+0.071
Neg logit contributions
 bear-0.079
 bears-0.074
 robbers-0.074
 mice-0.073
 rabbits-0.073
Token from
Token ID422
Feature activation-5.85e-01

Pos logit contributions
itating+0.004
inkle+0.004
rig+0.003
shadow+0.003
ews+0.003
Neg logit contributions
 robbers-0.003
 bear-0.003
 bears-0.003
 mice-0.003
 villains-0.003
Token behind
Token ID2157
Feature activation-5.47e-01

Pos logit contributions
itating+0.024
inkle+0.023
rig+0.023
ews+0.022
shadow+0.022
Neg logit contributions
 bear-0.028
 robbers-0.026
 bears-0.026
 mice-0.026
 rabbits-0.025
Token the
Token ID262
Feature activation-4.05e-01

Pos logit contributions
inkle+0.018
 yet+0.018
?",+0.017
 early+0.017
itating+0.017
Neg logit contributions
 villains-0.025
 robbers-0.025
pill-0.024
 bear-0.024
 bears-0.023
Token bench
Token ID7624
Feature activation-2.96e-01

Pos logit contributions
inkle+0.020
itating+0.020
rig+0.020
?",+0.019
ews+0.019
Neg logit contributions
 robbers-0.012
 villains-0.011
B-0.011
 bears-0.011
 servant-0.011
Token large
Token ID1588
Feature activation-7.48e-01

Pos logit contributions
inkle+0.020
itating+0.020
rig+0.020
ews+0.019
shadow+0.019
Neg logit contributions
 robbers-0.009
 bear-0.008
 mice-0.008
 bears-0.008
 rabbits-0.008
Token lizard
Token ID42406
Feature activation-1.26e-01

Pos logit contributions
inkle+0.045
itating+0.043
rig+0.043
ews+0.042
?",+0.042
Neg logit contributions
 robbers-0.017
 bear-0.017
 bears-0.016
 mice-0.016
 rabbits-0.016
Token.
Token ID13
Feature activation-6.99e-01

Pos logit contributions
itating+0.005
inkle+0.005
shadow+0.005
rig+0.005
 yet+0.005
Neg logit contributions
 robbers-0.005
 mice-0.005
 bear-0.005
 bears-0.005
 rabbits-0.005
Token They
Token ID1119
Feature activation-1.61e-01

Pos logit contributions
inkle+0.040
itating+0.038
shadow+0.037
ews+0.036
rig+0.036
Neg logit contributions
 bear-0.022
 robbers-0.021
 mice-0.021
 squirrel-0.020
B-0.020
Token wish
Token ID4601
Feature activation+2.61e-01

Pos logit contributions
inkle+0.005
rig+0.005
itating+0.005
?",+0.004
ossom+0.004
Neg logit contributions
 robbers-0.008
 mice-0.008
B-0.008
 bears-0.008
 rabbits-0.008
Token they
Token ID484
Feature activation-1.71e+00

Pos logit contributions
 robbers+0.011
 bear+0.011
 mice+0.011
pill+0.011
 bears+0.011
Neg logit contributions
inkle-0.010
itating-0.010
ews-0.009
 early-0.009
 yet-0.009
Token listened
Token ID16399
Feature activation+3.32e-01

Pos logit contributions
itating+0.086
inkle+0.084
rig+0.082
shadow+0.081
ews+0.080
Neg logit contributions
 bear-0.057
 robbers-0.054
 bears-0.054
 mice-0.053
 rabbits-0.052
Token to
Token ID284
Feature activation-7.32e-01

Pos logit contributions
 bear+0.010
 bears+0.010
 robbers+0.009
 mice+0.009
 rabbits+0.009
Neg logit contributions
inkle-0.018
itating-0.018
rig-0.017
mmm-0.017
ews-0.017
Token Tim
Token ID5045
Feature activation-1.00e+00

Pos logit contributions
inkle+0.035
itating+0.034
rig+0.033
shadow+0.032
ews+0.032
Neg logit contributions
 bear-0.026
 robbers-0.025
 bears-0.025
 mice-0.024
 rabbits-0.024
Token.
Token ID13
Feature activation-7.42e-01

Pos logit contributions
itating+0.046
inkle+0.046
rig+0.045
shadow+0.044
ews+0.043
Neg logit contributions
 robbers-0.037
 bear-0.037
 bears-0.036
 mice-0.036
 rabbits-0.035
Token They
Token ID1119
Feature activation-1.70e-01

Pos logit contributions
inkle+0.041
itating+0.039
rig+0.038
shadow+0.037
ews+0.037
Neg logit contributions
 bear-0.025
 robbers-0.024
 mice-0.023
 squirrel-0.023
B-0.022
Token couldn
Token ID3521
Feature activation-3.19e-01

Pos logit contributions
itating+0.013
inkle+0.013
rig+0.013
shadow+0.013
ews+0.012
Neg logit contributions
 bear-0.009
 robbers-0.008
 bears-0.008
 mice-0.008
 rabbits-0.008
Token't
Token ID470
Feature activation-7.96e-01

Pos logit contributions
itating+0.012
inkle+0.012
rig+0.012
shadow+0.011
ews+0.011
Neg logit contributions
 bear-0.015
 robbers-0.015
 bears-0.014
 mice-0.014
 rabbits-0.014
Token figure
Token ID3785
Feature activation+5.22e-01

Pos logit contributions
itating+0.036
inkle+0.036
rig+0.036
ews+0.035
shadow+0.035
Neg logit contributions
 bear-0.032
 robbers-0.030
 bears-0.030
 squirrel-0.029
 mice-0.029
Token out
Token ID503
Feature activation-9.66e-01

Pos logit contributions
 bear+0.026
 robbers+0.025
 bears+0.025
 mice+0.025
 rabbits+0.024
Neg logit contributions
itating-0.018
inkle-0.018
rig-0.017
shadow-0.017
ews-0.017
Token what
Token ID644
Feature activation+8.22e-01

Pos logit contributions
itating+0.033
inkle+0.032
rig+0.031
shadow+0.030
ews+0.030
Neg logit contributions
 bear-0.046
 robbers-0.046
 bears-0.044
 mice-0.043
B-0.043
Token it
Token ID340
Feature activation-1.60e+00

Pos logit contributions
 robbers+0.030
 bear+0.030
 bears+0.029
 mice+0.028
 rabbits+0.028
Neg logit contributions
?",-0.035
inkle-0.035
itating-0.035
rig-0.034
ews-0.033
Token was
Token ID373
Feature activation-8.25e-01

Pos logit contributions
inkle+0.068
itating+0.065
rig+0.065
?",+0.065
?!"+0.060
Neg logit contributions
 robbers-0.066
 mice-0.062
 bears-0.061
 villains-0.060
 bear-0.060
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
har+0.051
itating+0.051
inkle+0.051
rig+0.051
shadow+0.050
Neg logit contributions
 bear-0.021
 bears-0.018
 rabbits-0.018
 robbers-0.018
 mice-0.016
Token He
Token ID679
Feature activation+2.35e-01

Pos logit contributions
 bear+0.004
 robbers+0.004
 bears+0.004
 mice+0.004
 rabbits+0.004
Neg logit contributions
itating-0.007
inkle-0.007
rig-0.007
shadow-0.007
ews-0.007
Token looked
Token ID3114
Feature activation-1.57e+00

Pos logit contributions
 bear+0.008
 robbers+0.007
 bears+0.007
 mice+0.007
 rabbits+0.007
Neg logit contributions
itating-0.012
inkle-0.012
rig-0.012
shadow-0.012
ews-0.011
Token around
Token ID1088
Feature activation-1.50e+00

Pos logit contributions
mmm+0.084
shadow+0.079
ews+0.079
inkle+0.076
mmmm+0.076
Neg logit contributions
 bear-0.064
 bears-0.060
 rabbits-0.058
 mice-0.056
 robbers-0.054
Token wanted
Token ID2227
Feature activation+4.10e-01

Pos logit contributions
itating+0.002
inkle+0.002
rig+0.002
shadow+0.002
ews+0.002
Neg logit contributions
 bear-0.001
 robbers-0.001
 mice-0.001
 bears-0.001
 rabbits-0.001
Token to
Token ID284
Feature activation-1.12e-01

Pos logit contributions
 bear+0.018
 robbers+0.017
 bears+0.017
 mice+0.017
 squirrel+0.016
Neg logit contributions
inkle-0.018
itating-0.018
rig-0.017
shadow-0.016
ews-0.016
Token whistle
Token ID16121
Feature activation+2.61e-02

Pos logit contributions
itating+0.006
inkle+0.006
ews+0.005
rig+0.005
shadow+0.005
Neg logit contributions
 bear-0.004
 squirrel-0.004
 robbers-0.004
 bears-0.004
 rabbits-0.004
Token too
Token ID1165
Feature activation-8.08e-01

Pos logit contributions
 bear+0.001
 bears+0.001
 squirrel+0.001
 mice+0.001
 rabbits+0.001
Neg logit contributions
itating-0.002
rig-0.002
ews-0.002
inkle-0.001
shadow-0.001
Token,
Token ID11
Feature activation-6.24e-04

Pos logit contributions
itating+0.046
inkle+0.046
rig+0.045
shadow+0.044
ews+0.044
Neg logit contributions
 bear-0.023
 robbers-0.021
 bears-0.021
 mice-0.021
 squirrel-0.020
Token so
Token ID523
Feature activation-1.54e+00

Pos logit contributions
inkle+0.000
ossom+0.000
itating+0.000
ews+0.000
har+0.000
Neg logit contributions
 bear-0.000
 squirrel-0.000
 robbers-0.000
 rabbits-0.000
 bears-0.000
Token he
Token ID339
Feature activation-8.71e-01

Pos logit contributions
itating+0.108
inkle+0.107
rig+0.106
shadow+0.103
ews+0.103
Neg logit contributions
 bear-0.025
 robbers-0.022
 bears-0.022
 mice-0.020
 squirrel-0.019
Token started
Token ID2067
Feature activation-8.83e-02

Pos logit contributions
itating+0.046
inkle+0.045
rig+0.045
shadow+0.044
?",+0.044
Neg logit contributions
 robbers-0.025
 bear-0.025
 mice-0.025
 bears-0.025
 rabbits-0.024
Token to
Token ID284
Feature activation+3.82e-01

Pos logit contributions
itating+0.003
inkle+0.003
rig+0.003
shadow+0.003
ews+0.003
Neg logit contributions
 bear-0.004
 robbers-0.004
 bears-0.004
 mice-0.004
 rabbits-0.004
Token practice
Token ID3357
Feature activation+2.46e-01

Pos logit contributions
 bear+0.013
 robbers+0.013
 bears+0.013
 mice+0.012
 rabbits+0.012
Neg logit contributions
itating-0.019
inkle-0.019
rig-0.019
shadow-0.018
ews-0.018
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
 bear+0.009
 robbers+0.009
 bears+0.009
 mice+0.009
 rabbits+0.009
Neg logit contributions
itating-0.011
inkle-0.011
rig-0.011
shadow-0.011
ews-0.011
Token nods
Token ID34833
Feature activation+9.07e-01

Pos logit contributions
inkle+0.008
itating+0.008
rig+0.007
shadow+0.007
ews+0.007
Neg logit contributions
 robbers-0.007
 bear-0.007
 mice-0.007
 bears-0.007
 rabbits-0.007
Token.
Token ID13
Feature activation-4.26e-01

Pos logit contributions
 bear+0.026
 bears+0.024
 mice+0.023
 robbers+0.023
 rabbits+0.023
Neg logit contributions
itating-0.053
inkle-0.052
rig-0.052
shadow-0.051
ews-0.051
Token He
Token ID679
Feature activation-2.43e-03

Pos logit contributions
itating+0.021
inkle+0.021
rig+0.021
shadow+0.020
ews+0.020
Neg logit contributions
 bear-0.015
 robbers-0.015
 bears-0.014
 mice-0.014
 rabbits-0.014
Token seems
Token ID2331
Feature activation-5.32e-01

Pos logit contributions
inkle+0.000
rig+0.000
itating+0.000
ews+0.000
?",+0.000
Neg logit contributions
 robbers-0.000
 bear-0.000
 mice-0.000
B-0.000
 bears-0.000
Token to
Token ID284
Feature activation-1.07e-01

Pos logit contributions
inkle+0.024
itating+0.024
shadow+0.023
rig+0.023
ews+0.022
Neg logit contributions
 bear-0.023
 bears-0.021
 mice-0.021
 rabbits-0.021
 robbers-0.021
Token like
Token ID588
Feature activation-1.96e+00

Pos logit contributions
itating+0.005
rig+0.005
ews+0.005
shadow+0.005
inkle+0.005
Neg logit contributions
 bear-0.005
 squirrel-0.004
 robbers-0.004
 bears-0.004
 rabbits-0.004
Token their
Token ID511
Feature activation+2.52e-01

Pos logit contributions
itating+0.074
inkle+0.073
ews+0.072
rig+0.071
 yet+0.071
Neg logit contributions
 robbers-0.080
 bear-0.078
B-0.073
Carl-0.072
 mice-0.072
Token story
Token ID1621
Feature activation-9.60e-01

Pos logit contributions
 robbers+0.008
B+0.008
 bear+0.007
pill+0.007
 mice+0.007
Neg logit contributions
inkle-0.013
rig-0.013
itating-0.013
ews-0.012
 ours-0.012
Token.
Token ID13
Feature activation-6.91e-01

Pos logit contributions
itating+0.053
inkle+0.052
rig+0.052
shadow+0.051
ews+0.050
Neg logit contributions
 bear-0.030
 bears-0.028
 robbers-0.027
 mice-0.027
 rabbits-0.026
Token
Token ID198
Feature activation-4.58e-01

Pos logit contributions
itating+0.033
inkle+0.033
rig+0.032
shadow+0.031
ews+0.031
Neg logit contributions
 bear-0.026
 robbers-0.025
 bears-0.025
 mice-0.024
 rabbits-0.024
Token
Token ID198
Feature activation-3.22e-01

Pos logit contributions
itating+0.021
inkle+0.021
rig+0.020
shadow+0.020
ews+0.019
Neg logit contributions
 bear-0.018
 robbers-0.017
 bears-0.017
 mice-0.017
 rabbits-0.017