TOP ACTIVATIONS
MAX = 5.941

. In no time at all , the
a nice home . In no time at all he had
tried it together . In no time , they were at
make cookies together . In no time , the bakery smelled
into the pond . In no time at all , they
picking up rubbish . In no time , Alice had got
the crazy flood . In no time they crossed the flood
flying like a bird in no time ! â
t weet , tweet , tweet ". Tim and Lily think
Jim . In no time they had collected all
feel very sleepy . In no time , he was asleep
top . It was a goodbye light . The animals waved
she said . " In no time you 'll be able
The beat is like a heartbeat . It goes boom boom
and peaceful dream and was no longer scared . <|endoftext|> Once
take her medicine . In no time at all , Anna
go to work . In no time at all , Amy
to rebuild themselves . In no time the houses were restored
happy . In no time at all , the
Sandy 's knee . In no time she was right as

MIN ACTIVATIONS
MIN = -9.220

." Int rig ued , the little brother
waiting for something ". Int rig ued , the girl asked
around the room . Int rig ued , it began to
water was icy . Int rig ued , she sw am
, dusty house . Int rig ued , M uff in
mushrooms , asking them all sorts of questions .
Now we can mix all sorts of cool things together !"
mom my picked out all sorts of delicious foods .
a hill and liked all sorts of y ummy food .
ay ons to draw all sorts of things . <|endoftext|> Once
filled with decorations and all sorts of fun toys .
auldron where she mixed all sorts of things together . One
happy . She saw all sorts of creatures , and played
street . Tom saw all sorts of things as they drove
<|endoftext|> Billy was learning all sorts of new things , but
mom my picked out all sorts of delicious foods .
She learned to sign all sorts of words , including the
and she taught Clara all sorts of things . She told
used them to draw all sorts of amazing pictures . But
. She tried using all sorts of measures - a ruler

INTERVAL 2.150 - 5.941
CONTAINS 3.063%

replied , " That 's okay , Tim my . You
, or princess es , or cars . They have a
He grabbed it with a smile ! But then
" Thank you , thank you , thank you !"
sailed until it could sail no further . The boat was

INTERVAL -1.640 - 2.150
CONTAINS 89.640%

. The mattress was wet and had a big stain .
followed . The bee was very friendly , and
" Look , Ben , what is this ?" Anna asks
the ant knew that he shouldn 't have been so competitive
But then they hear a loud noise . It

INTERVAL -5.430 - -1.640
CONTAINS 7.288%

smiles . She says they are good kids . She says
tall bag and told her mom what happened . Her mom
After they were done shopping , Tim and his mom
, I â m
They played games and had fun until the rain stopped .

INTERVAL -9.220 - -5.430
CONTAINS 0.008%

. They would see all sorts of animals like lions ,
The person kept trying all sorts of things , but the
store . She saw all sorts of toys that she had
She would often make all sorts of things out of paper
and taught the animals all sorts of things . They taught
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
 Cle+0.015
 tail+0.014
 Horse+0.013
 ears+0.013
 prope+0.013
Neg logit contributions
rig-0.019
pack-0.019
inner-0.019
washer-0.018
prise-0.017
Token
Token ID220
Feature activation+2.82e+00

Pos logit contributions
 Cle+0.007
 tail+0.007
 prope+0.006
 Horse+0.006
 ears+0.006
Neg logit contributions
rig-0.015
pack-0.014
inner-0.014
washer-0.013
prise-0.013
Token
Token ID198
Feature activation+1.97e-01

Pos logit contributions
 Cle+0.060
 tail+0.055
 Horse+0.050
 no+0.048
 ears+0.048
Neg logit contributions
rig-0.151
inner-0.149
pack-0.148
washer-0.143
prise-0.140
Token
Token ID198
Feature activation+6.49e-01

Pos logit contributions
 Cle+0.006
 tail+0.006
 ears+0.005
 prope+0.005
 Horse+0.005
Neg logit contributions
rig-0.009
pack-0.009
inner-0.009
washer-0.008
ade-0.008
TokenIn
Token ID818
Feature activation+9.75e-01

Pos logit contributions
 Cle+0.017
 tail+0.016
 Horse+0.015
 no+0.014
 prope+0.014
Neg logit contributions
rig-0.032
pack-0.031
inner-0.031
washer-0.030
prise-0.029
Token no
Token ID645
Feature activation+5.94e+00

Pos logit contributions
 Cle+0.029
 tail+0.028
 Horse+0.026
 prope+0.026
 ears+0.026
Neg logit contributions
pack-0.043
rig-0.042
inner-0.042
washer-0.040
prise-0.039
Token time
Token ID640
Feature activation-6.68e-01

Pos logit contributions
 Cle+0.197
 tail+0.187
 Horse+0.178
 prope+0.176
 ears+0.173
Neg logit contributions
rig-0.252
pack-0.247
inner-0.242
washer-0.228
prise-0.224
Token at
Token ID379
Feature activation+4.03e-01

Pos logit contributions
pack+0.027
inner+0.026
rig+0.026
washer+0.026
prise+0.024
Neg logit contributions
 Cle-0.022
 tail-0.022
 Horse-0.021
 prope-0.021
 ears-0.020
Token all
Token ID477
Feature activation-2.29e+00

Pos logit contributions
 Cle+0.012
 tail+0.011
 no+0.011
 Horse+0.010
 ear+0.010
Neg logit contributions
rig-0.019
inner-0.019
pack-0.019
washer-0.018
prise-0.017
Token,
Token ID11
Feature activation+7.24e-01

Pos logit contributions
rig+0.129
inner+0.128
pack+0.127
prise+0.118
washer+0.118
Neg logit contributions
 Cle-0.043
 no-0.043
 tail-0.043
 ears-0.041
 ear-0.040
Token the
Token ID262
Feature activation+1.93e-01

Pos logit contributions
 prope+0.027
 tail+0.026
 Cle+0.026
 Horse+0.026
 horns+0.025
Neg logit contributions
rig-0.023
inner-0.022
 else-0.022
pack-0.022
igsaw-0.021
Token a
Token ID257
Feature activation-1.55e-01

Pos logit contributions
 tail+0.020
 no+0.019
 ears+0.018
 heart+0.017
 goodbye+0.017
Neg logit contributions
inner-0.031
rig-0.030
pack-0.029
off-0.027
icy-0.027
Token nice
Token ID3621
Feature activation+3.31e-01

Pos logit contributions
pack+0.006
inner+0.006
rig+0.006
washer+0.006
off+0.005
Neg logit contributions
 tail-0.006
 Cle-0.005
 ears-0.005
 prope-0.005
 no-0.005
Token home
Token ID1363
Feature activation+2.31e-01

Pos logit contributions
 tail+0.011
 Cle+0.010
 ears+0.010
 ear+0.010
 heart+0.009
Neg logit contributions
rig-0.014
inner-0.014
pack-0.014
washer-0.013
prise-0.013
Token.
Token ID13
Feature activation+8.19e-02

Pos logit contributions
 tail+0.006
 Cle+0.006
 no+0.005
 ears+0.005
 Horse+0.005
Neg logit contributions
rig-0.012
inner-0.011
pack-0.011
prise-0.011
washer-0.010
Token In
Token ID554
Feature activation+6.49e-02

Pos logit contributions
 tail+0.002
 Cle+0.002
 prope+0.002
 ears+0.002
 Horse+0.002
Neg logit contributions
rig-0.004
pack-0.004
inner-0.004
washer-0.004
prise-0.004
Token no
Token ID645
Feature activation+5.88e+00

Pos logit contributions
 Cle+0.002
 tail+0.002
 prope+0.002
 ears+0.002
 Horse+0.002
Neg logit contributions
pack-0.003
rig-0.003
inner-0.003
washer-0.003
prise-0.003
Token time
Token ID640
Feature activation-7.29e-01

Pos logit contributions
 Cle+0.206
 tail+0.189
 Horse+0.183
 prope+0.183
 ears+0.178
Neg logit contributions
rig-0.238
pack-0.231
inner-0.225
washer-0.211
prise-0.211
Token at
Token ID379
Feature activation+3.87e-01

Pos logit contributions
pack+0.032
rig+0.031
inner+0.031
washer+0.031
prise+0.029
Neg logit contributions
 Cle-0.022
 tail-0.021
 prope-0.020
 Horse-0.020
 ears-0.020
Token all
Token ID477
Feature activation-1.95e+00

Pos logit contributions
 Cle+0.011
 tail+0.011
 no+0.010
 Horse+0.010
 ear+0.010
Neg logit contributions
rig-0.019
inner-0.018
pack-0.018
washer-0.017
prise-0.017
Token he
Token ID339
Feature activation+4.38e-01

Pos logit contributions
rig+0.116
inner+0.115
pack+0.114
prise+0.107
washer+0.104
Neg logit contributions
 no-0.033
 tail-0.031
 ears-0.030
 Cle-0.030
 ear-0.029
Token had
Token ID550
Feature activation+7.10e-01

Pos logit contributions
 Cle+0.011
 tail+0.011
 no+0.011
 ears+0.010
 Horse+0.010
Neg logit contributions
rig-0.022
inner-0.021
pack-0.021
washer-0.019
igsaw-0.019
Token tried
Token ID3088
Feature activation+6.83e-01

Pos logit contributions
pack+0.004
rig+0.004
inner+0.004
washer+0.004
prise+0.004
Neg logit contributions
 Cle-0.003
 tail-0.003
 Horse-0.003
 prope-0.003
 ears-0.003
Token it
Token ID340
Feature activation-8.00e-01

Pos logit contributions
 Cle+0.027
 tail+0.026
 Horse+0.025
 prope+0.025
 ear+0.024
Neg logit contributions
pack-0.024
rig-0.023
inner-0.022
washer-0.021
ade-0.020
Token together
Token ID1978
Feature activation-7.93e-01

Pos logit contributions
rig+0.032
pack+0.031
inner+0.030
washer+0.029
ade+0.028
Neg logit contributions
 Cle-0.028
 tail-0.027
 Horse-0.026
 prope-0.026
 ears-0.026
Token.
Token ID13
Feature activation+6.25e-01

Pos logit contributions
rig+0.036
pack+0.035
inner+0.034
washer+0.033
ade+0.032
Neg logit contributions
 Cle-0.024
 tail-0.023
 Horse-0.022
 prope-0.021
 ears-0.021
Token In
Token ID554
Feature activation+1.67e-01

Pos logit contributions
 Cle+0.016
 tail+0.015
 Horse+0.014
 ears+0.014
 prope+0.014
Neg logit contributions
rig-0.031
pack-0.031
inner-0.030
washer-0.029
prise-0.028
Token no
Token ID645
Feature activation+5.87e+00

Pos logit contributions
 Cle+0.005
 tail+0.004
 Horse+0.004
 ears+0.004
 prope+0.004
Neg logit contributions
rig-0.008
pack-0.008
inner-0.008
washer-0.007
prise-0.007
Token time
Token ID640
Feature activation-6.93e-01

Pos logit contributions
 Cle+0.175
 tail+0.172
 ears+0.159
 Horse+0.157
 no+0.155
Neg logit contributions
rig-0.267
pack-0.266
inner-0.262
washer-0.252
prise-0.241
Token,
Token ID11
Feature activation+9.74e-01

Pos logit contributions
pack+0.028
inner+0.028
rig+0.028
washer+0.027
 else+0.026
Neg logit contributions
 Cle-0.022
 tail-0.022
 Horse-0.021
 prope-0.021
 ears-0.020
Token they
Token ID484
Feature activation+1.04e+00

Pos logit contributions
 Cle+0.032
 tail+0.032
 prope+0.030
 Horse+0.030
 ears+0.029
Neg logit contributions
pack-0.039
rig-0.039
inner-0.038
washer-0.037
prise-0.035
Token were
Token ID547
Feature activation-1.17e-01

Pos logit contributions
 Cle+0.031
 tail+0.030
 Horse+0.028
 ears+0.028
 prope+0.027
Neg logit contributions
rig-0.047
pack-0.047
inner-0.046
washer-0.045
prise-0.043
Token at
Token ID379
Feature activation+7.47e-01

Pos logit contributions
rig+0.005
pack+0.005
inner+0.005
washer+0.004
prise+0.004
Neg logit contributions
 Cle-0.004
 tail-0.004
 Horse-0.004
 ears-0.004
 prope-0.004
Token make
Token ID787
Feature activation+1.61e+00

Pos logit contributions
 Cle+0.106
 tail+0.102
 Horse+0.097
 ears+0.096
 prope+0.095
Neg logit contributions
rig-0.112
pack-0.111
inner-0.108
washer-0.102
prise-0.098
Token cookies
Token ID14746
Feature activation+1.95e+00

Pos logit contributions
 Cle+0.051
 tail+0.049
 ears+0.046
 Horse+0.046
 prope+0.045
Neg logit contributions
rig-0.071
pack-0.070
inner-0.069
washer-0.065
prise-0.063
Token together
Token ID1978
Feature activation-2.46e-01

Pos logit contributions
 tail+0.055
 no+0.055
 goodbye+0.051
 ears+0.050
 Cle+0.050
Neg logit contributions
rig-0.086
inner-0.083
pack-0.082
off-0.078
washer-0.078
Token.
Token ID13
Feature activation+5.08e-01

Pos logit contributions
rig+0.012
pack+0.012
inner+0.012
washer+0.011
prise+0.011
Neg logit contributions
 tail-0.006
 Cle-0.006
 no-0.006
 ears-0.006
 Horse-0.005
Token In
Token ID554
Feature activation+1.60e-01

Pos logit contributions
 tail+0.014
 Cle+0.014
 prope+0.013
 Horse+0.013
 ears+0.013
Neg logit contributions
rig-0.024
pack-0.023
inner-0.023
washer-0.022
ade-0.021
Token no
Token ID645
Feature activation+5.85e+00

Pos logit contributions
 Cle+0.005
 tail+0.004
 prope+0.004
 Horse+0.004
 ears+0.004
Neg logit contributions
pack-0.007
rig-0.007
inner-0.007
washer-0.007
prise-0.007
Token time
Token ID640
Feature activation-7.20e-01

Pos logit contributions
 Cle+0.209
 tail+0.193
 prope+0.188
 Horse+0.187
 ears+0.178
Neg logit contributions
rig-0.234
pack-0.225
inner-0.221
prise-0.208
washer-0.205
Token,
Token ID11
Feature activation+9.06e-01

Pos logit contributions
pack+0.029
inner+0.028
washer+0.027
rig+0.027
 else+0.026
Neg logit contributions
 tail-0.024
 Cle-0.024
 prope-0.023
 Horse-0.022
 ears-0.022
Token the
Token ID262
Feature activation+4.34e-01

Pos logit contributions
 tail+0.028
 Cle+0.027
 prope+0.027
 ears+0.026
 Horse+0.025
Neg logit contributions
pack-0.038
rig-0.037
inner-0.037
washer-0.036
prise-0.034
Token bakery
Token ID38164
Feature activation-3.97e-01

Pos logit contributions
 Cle+0.016
 prope+0.014
 Horse+0.014
 tail+0.013
ked+0.013
Neg logit contributions
inner-0.016
rig-0.016
washer-0.016
pack-0.016
ade-0.015
Token smelled
Token ID37609
Feature activation-7.66e-01

Pos logit contributions
rig+0.018
pack+0.018
inner+0.017
washer+0.017
prise+0.016
Neg logit contributions
 Cle-0.012
 tail-0.011
 ears-0.011
 Horse-0.011
 no-0.010
Token into
Token ID656
Feature activation-1.58e+00

Pos logit contributions
rig+0.041
pack+0.041
inner+0.040
prise+0.038
washer+0.038
Neg logit contributions
 tail-0.025
 Cle-0.024
 no-0.023
 ears-0.022
 goodbye-0.022
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
rig+0.074
pack+0.074
inner+0.072
washer+0.069
prise+0.067
Neg logit contributions
 Cle-0.044
 tail-0.041
 Horse-0.039
 ears-0.038
 prope-0.038
Token pond
Token ID16723
Feature activation-2.07e+00

Pos logit contributions
 Cle+0.042
 tail+0.041
 ears+0.039
 Horse+0.038
 prope+0.038
Neg logit contributions
pack-0.036
rig-0.036
inner-0.035
washer-0.033
prise-0.032
Token.
Token ID13
Feature activation+6.93e-01

Pos logit contributions
rig+0.102
pack+0.102
inner+0.101
washer+0.095
prise+0.095
Neg logit contributions
 tail-0.053
 Cle-0.051
 ears-0.048
 no-0.047
 Horse-0.046
Token In
Token ID554
Feature activation+2.81e-01

Pos logit contributions
 Cle+0.018
 tail+0.017
 prope+0.016
 ears+0.016
 Horse+0.016
Neg logit contributions
rig-0.034
pack-0.034
inner-0.033
washer-0.032
prise-0.030
Token no
Token ID645
Feature activation+5.84e+00

Pos logit contributions
 Cle+0.008
 tail+0.008
 Horse+0.007
 prope+0.007
 ears+0.007
Neg logit contributions
pack-0.013
rig-0.013
inner-0.012
washer-0.012
prise-0.011
Token time
Token ID640
Feature activation-9.50e-01

Pos logit contributions
 Cle+0.196
 tail+0.183
 Horse+0.176
 prope+0.175
 ears+0.171
Neg logit contributions
rig-0.246
pack-0.238
inner-0.236
washer-0.221
prise-0.217
Token at
Token ID379
Feature activation+2.35e-01

Pos logit contributions
pack+0.036
inner+0.035
washer+0.035
rig+0.035
 else+0.034
Neg logit contributions
 Cle-0.032
 tail-0.032
 prope-0.031
 Horse-0.030
 ears-0.030
Token all
Token ID477
Feature activation-2.26e+00

Pos logit contributions
 Cle+0.006
 tail+0.005
 no+0.005
 ear+0.005
 ears+0.005
Neg logit contributions
rig-0.012
pack-0.012
inner-0.012
washer-0.012
prise-0.011
Token,
Token ID11
Feature activation+5.91e-01

Pos logit contributions
rig+0.131
pack+0.131
inner+0.129
prise+0.122
washer+0.120
Neg logit contributions
 no-0.039
 tail-0.039
 Cle-0.037
 ears-0.036
 ear-0.033
Token they
Token ID484
Feature activation+5.16e-01

Pos logit contributions
 Cle+0.021
 tail+0.020
 prope+0.020
 Horse+0.020
Leave+0.019
Neg logit contributions
pack-0.021
inner-0.021
rig-0.021
washer-0.021
 else-0.020
Token picking
Token ID10868
Feature activation-1.46e+00

Pos logit contributions
inner+0.101
rig+0.099
pack+0.094
icy+0.086
prise+0.086
Neg logit contributions
 no-0.065
 tail-0.064
 goodbye-0.061
 heart-0.060
 Cle-0.059
Token up
Token ID510
Feature activation-2.93e-01

Pos logit contributions
rig+0.059
pack+0.059
inner+0.057
washer+0.055
prise+0.053
Neg logit contributions
 Cle-0.051
 tail-0.050
 ears-0.048
 no-0.047
 ear-0.046
Token rubbish
Token ID35022
Feature activation-2.09e+00

Pos logit contributions
rig+0.014
pack+0.014
inner+0.013
washer+0.013
prise+0.012
Neg logit contributions
 Cle-0.008
 tail-0.008
 ears-0.008
 no-0.007
 Horse-0.007
Token.
Token ID13
Feature activation+6.59e-01

Pos logit contributions
rig+0.109
pack+0.105
inner+0.103
prise+0.101
washer+0.096
Neg logit contributions
 no-0.046
 tail-0.046
 Cle-0.046
 ears-0.042
 goodbye-0.041
Token In
Token ID554
Feature activation+2.19e-01

Pos logit contributions
 Cle+0.019
 tail+0.018
 prope+0.018
 Horse+0.017
 ears+0.016
Neg logit contributions
rig-0.030
pack-0.029
inner-0.028
washer-0.027
off-0.027
Token no
Token ID645
Feature activation+5.83e+00

Pos logit contributions
 Cle+0.006
 tail+0.006
 Horse+0.006
 ears+0.005
 prope+0.005
Neg logit contributions
rig-0.010
pack-0.010
inner-0.010
washer-0.009
prise-0.009
Token time
Token ID640
Feature activation-8.44e-01

Pos logit contributions
 Cle+0.197
 tail+0.185
 Horse+0.177
 prope+0.176
 ears+0.173
Neg logit contributions
rig-0.245
pack-0.238
inner-0.234
washer-0.219
prise-0.217
Token,
Token ID11
Feature activation+8.95e-01

Pos logit contributions
pack+0.034
inner+0.032
washer+0.032
rig+0.032
prise+0.031
Neg logit contributions
 Cle-0.028
 tail-0.028
 prope-0.026
 Horse-0.026
 ears-0.025
Token Alice
Token ID14862
Feature activation+1.18e+00

Pos logit contributions
 Cle+0.029
 tail+0.027
 prope+0.027
 Horse+0.026
 ears+0.025
Neg logit contributions
pack-0.037
rig-0.037
inner-0.036
 else-0.035
washer-0.035
Token had
Token ID550
Feature activation+1.43e+00

Pos logit contributions
 Cle+0.038
 tail+0.036
 prope+0.034
 Horse+0.034
 ears+0.033
Neg logit contributions
rig-0.049
pack-0.049
washer-0.048
inner-0.047
ade-0.045
Token got
Token ID1392
Feature activation-8.29e-01

Pos logit contributions
 Cle+0.049
 tail+0.047
 Horse+0.045
 ears+0.044
 prope+0.044
Neg logit contributions
rig-0.059
pack-0.058
inner-0.057
washer-0.054
prise-0.052
Token the
Token ID262
Feature activation+5.28e-01

Pos logit contributions
 Cle+0.004
 tail+0.003
 Horse+0.003
 prope+0.003
 ears+0.003
Neg logit contributions
pack-0.005
rig-0.005
inner-0.005
washer-0.004
prise-0.004
Token crazy
Token ID7165
Feature activation-1.41e+00

Pos logit contributions
 Cle+0.018
 tail+0.018
 ears+0.018
 ear+0.017
 prope+0.017
Neg logit contributions
pack-0.022
inner-0.021
rig-0.021
washer-0.020
prise-0.020
Token flood
Token ID6947
Feature activation-2.70e+00

Pos logit contributions
rig+0.051
pack+0.051
inner+0.050
washer+0.047
prise+0.045
Neg logit contributions
 Cle-0.055
 tail-0.054
 ears-0.051
 Horse-0.051
 prope-0.050
Token.
Token ID13
Feature activation+6.22e-01

Pos logit contributions
rig+0.132
pack+0.129
inner+0.129
prise+0.121
washer+0.121
Neg logit contributions
 Cle-0.071
 tail-0.070
 ears-0.064
 no-0.063
 Horse-0.062
Token In
Token ID554
Feature activation+3.99e-01

Pos logit contributions
 Cle+0.018
 prope+0.018
 tail+0.017
 Horse+0.017
 ears+0.016
Neg logit contributions
rig-0.028
pack-0.027
inner-0.027
washer-0.025
igsaw-0.024
Token no
Token ID645
Feature activation+5.81e+00

Pos logit contributions
 Cle+0.011
 tail+0.011
 Horse+0.010
 ears+0.010
 prope+0.010
Neg logit contributions
pack-0.018
rig-0.018
inner-0.018
washer-0.017
prise-0.017
Token time
Token ID640
Feature activation-8.41e-01

Pos logit contributions
 Cle+0.198
 tail+0.185
 Horse+0.179
 prope+0.176
 ears+0.173
Neg logit contributions
rig-0.241
pack-0.234
inner-0.228
washer-0.213
ade-0.212
Token they
Token ID484
Feature activation+6.06e-01

Pos logit contributions
pack+0.035
rig+0.034
inner+0.034
washer+0.034
 else+0.032
Neg logit contributions
 Cle-0.027
 tail-0.026
 prope-0.025
 Horse-0.025
 ears-0.024
Token crossed
Token ID12606
Feature activation+1.27e+00

Pos logit contributions
 Cle+0.019
 tail+0.019
 Horse+0.018
 ears+0.017
 prope+0.017
Neg logit contributions
pack-0.026
rig-0.026
inner-0.025
washer-0.025
prise-0.024
Token the
Token ID262
Feature activation+1.52e-01

Pos logit contributions
 Cle+0.044
 Horse+0.039
 tail+0.039
 prope+0.038
Leave+0.038
Neg logit contributions
pack-0.049
rig-0.049
inner-0.047
washer-0.043
ade-0.043
Token flood
Token ID6947
Feature activation-2.36e+00

Pos logit contributions
 Cle+0.006
 tail+0.006
 ears+0.005
 prope+0.005
 no+0.005
Neg logit contributions
pack-0.006
rig-0.006
inner-0.005
prise-0.005
washer-0.005
Token flying
Token ID7348
Feature activation+1.32e+00

Pos logit contributions
 Cle+0.001
 tail+0.001
 Horse+0.001
 ears+0.001
 prope+0.001
Neg logit contributions
rig-0.001
pack-0.001
inner-0.001
washer-0.001
prise-0.001
Token like
Token ID588
Feature activation-1.49e+00

Pos logit contributions
 Cle+0.048
 tail+0.045
 Horse+0.043
 ears+0.043
 prope+0.042
Neg logit contributions
rig-0.052
pack-0.050
inner-0.050
washer-0.047
ade-0.045
Token a
Token ID257
Feature activation+1.04e+00

Pos logit contributions
rig+0.058
pack+0.057
inner+0.057
washer+0.053
prise+0.052
Neg logit contributions
 Cle-0.052
 tail-0.051
 prope-0.047
 ears-0.047
 Horse-0.047
Token bird
Token ID6512
Feature activation+2.73e+00

Pos logit contributions
 Cle+0.034
 tail+0.030
 ears+0.030
 Horse+0.030
Leave+0.029
Neg logit contributions
rig-0.044
inner-0.042
pack-0.041
washer-0.040
prise-0.039
Token in
Token ID287
Feature activation+8.32e-01

Pos logit contributions
 Cle+0.095
 tail+0.090
 Horse+0.085
 ears+0.085
 prope+0.085
Neg logit contributions
rig-0.111
pack-0.108
inner-0.106
washer-0.102
prise-0.097
Token no
Token ID645
Feature activation+5.80e+00

Pos logit contributions
 Cle+0.024
 tail+0.023
 Horse+0.021
 ears+0.021
 prope+0.021
Neg logit contributions
rig-0.038
pack-0.038
inner-0.037
washer-0.035
prise-0.034
Token time
Token ID640
Feature activation-1.60e+00

Pos logit contributions
 Cle+0.223
 Horse+0.198
 prope+0.198
 tail+0.196
ked+0.187
Neg logit contributions
rig-0.215
pack-0.207
inner-0.199
prise-0.194
off-0.192
Token!
Token ID0
Feature activation-3.57e-01

Pos logit contributions
rig+0.066
pack+0.065
inner+0.065
washer+0.062
prise+0.059
Neg logit contributions
 Cle-0.053
 tail-0.050
 prope-0.048
 Horse-0.048
 ears-0.047
Tokenâ
Token ID22940
Feature activation-8.44e-01

Pos logit contributions
rig+0.015
pack+0.014
inner+0.014
washer+0.013
prise+0.013
Neg logit contributions
 tail-0.012
 prope-0.011
 ears-0.011
 Cle-0.011
 horns-0.010
Token
Token ID26391
Feature activation+1.01e+00

Pos logit contributions
rig+0.033
pack+0.033
inner+0.032
washer+0.031
prise+0.030
Neg logit contributions
 Cle-0.030
 tail-0.028
 Horse-0.027
 ear-0.026
 ears-0.026
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
 Cle+0.030
 tail+0.030
 prope+0.028
 ear+0.028
 ears+0.027
Neg logit contributions
rig-0.045
pack-0.044
inner-0.043
washer-0.041
prise-0.039
Tokent
Token ID83
Feature activation+1.02e+00

Pos logit contributions
 Cle+0.038
 tail+0.037
 ears+0.034
 Horse+0.034
 prope+0.034
Neg logit contributions
rig-0.050
pack-0.049
inner-0.049
washer-0.046
prise-0.045
Tokenweet
Token ID7277
Feature activation+1.45e+00

Pos logit contributions
 Cle+0.034
 tail+0.033
 Horse+0.031
 ears+0.031
 prope+0.030
Neg logit contributions
rig-0.044
pack-0.043
inner-0.042
washer-0.040
prise-0.039
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
 Cle+0.051
joy+0.049
 prope+0.045
 stub+0.043
 goodbye+0.042
Neg logit contributions
inner-0.053
rig-0.053
ade-0.051
off-0.050
pack-0.049
Token tweet
Token ID6126
Feature activation+5.61e+00

Pos logit contributions
 Cle+0.043
joy+0.040
 Horse+0.040
 tail+0.039
 owners+0.038
Neg logit contributions
rig-0.042
inner-0.040
washer-0.038
 else-0.037
pack-0.037
Token,
Token ID11
Feature activation+1.34e+00

Pos logit contributions
 Cle+0.216
joy+0.201
 tail+0.200
 prope+0.197
 ear+0.196
Neg logit contributions
rig-0.205
inner-0.194
pack-0.185
off-0.182
ade-0.181
Token tweet
Token ID6126
Feature activation+5.78e+00

Pos logit contributions
 Cle+0.041
joy+0.037
 tail+0.036
 Horse+0.036
 owners+0.034
Neg logit contributions
rig-0.057
inner-0.055
pack-0.052
washer-0.052
prise-0.051
Token".
Token ID1911
Feature activation-3.13e-02

Pos logit contributions
 Cle+0.226
joy+0.212
 tail+0.211
 prope+0.206
 ear+0.205
Neg logit contributions
rig-0.206
inner-0.197
pack-0.187
off-0.184
ade-0.183
Token Tim
Token ID5045
Feature activation-1.75e+00

Pos logit contributions
rig+0.001
pack+0.001
inner+0.001
ade+0.001
washer+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 Horse-0.001
 prope-0.001
 ear-0.001
Token and
Token ID290
Feature activation-3.55e-01

Pos logit contributions
rig+0.084
pack+0.083
inner+0.081
washer+0.078
ade+0.075
Neg logit contributions
 Cle-0.048
 tail-0.045
 Horse-0.042
 prope-0.042
 ears-0.041
Token Lily
Token ID20037
Feature activation-1.35e+00

Pos logit contributions
pack+0.012
rig+0.012
washer+0.012
inner+0.012
 else+0.011
Neg logit contributions
 Cle-0.013
 Horse-0.012
 prope-0.012
 tail-0.012
itive-0.012
Token think
Token ID892
Feature activation-1.19e+00

Pos logit contributions
rig+0.054
pack+0.052
inner+0.051
washer+0.049
prise+0.047
Neg logit contributions
 Cle-0.048
 tail-0.045
 Horse-0.044
 prope-0.042
joy-0.042
Token Jim
Token ID5395
Feature activation-8.67e-01

Pos logit contributions
rig+0.012
pack+0.011
igsaw+0.011
inner+0.011
 else+0.011
Neg logit contributions
 prope-0.014
 tail-0.013
 Horse-0.013
 Cle-0.013
 ears-0.012
Token.
Token ID13
Feature activation-4.03e-01

Pos logit contributions
rig+0.036
pack+0.035
washer+0.033
inner+0.032
ade+0.031
Neg logit contributions
 Cle-0.029
 prope-0.027
 tail-0.026
 Horse-0.026
Leave-0.026
Token
Token ID198
Feature activation-1.01e-01

Pos logit contributions
rig+0.017
pack+0.016
inner+0.016
washer+0.016
 else+0.015
Neg logit contributions
 prope-0.012
 Cle-0.012
 tail-0.012
 ears-0.011
 Horse-0.011
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
rig+0.005
pack+0.005
inner+0.005
washer+0.005
prise+0.004
Neg logit contributions
 Cle-0.003
 tail-0.003
 Horse-0.002
 ears-0.002
 prope-0.002
TokenIn
Token ID818
Feature activation+9.14e-01

Pos logit contributions
 Cle+0.009
 tail+0.009
 Horse+0.008
 no+0.008
 ears+0.008
Neg logit contributions
rig-0.016
pack-0.016
inner-0.016
washer-0.015
prise-0.015
Token no
Token ID645
Feature activation+5.78e+00

Pos logit contributions
 Cle+0.026
 tail+0.025
 Horse+0.023
 prope+0.023
 ears+0.023
Neg logit contributions
pack-0.042
rig-0.041
inner-0.040
washer-0.039
prise-0.038
Token time
Token ID640
Feature activation-9.87e-01

Pos logit contributions
 Cle+0.193
 tail+0.180
 Horse+0.173
 prope+0.172
 ears+0.167
Neg logit contributions
rig-0.244
pack-0.239
inner-0.235
washer-0.221
prise-0.218
Token they
Token ID484
Feature activation+3.46e-01

Pos logit contributions
pack+0.037
washer+0.036
inner+0.036
rig+0.036
 else+0.035
Neg logit contributions
 Cle-0.035
 tail-0.034
 prope-0.033
 Horse-0.033
 ears-0.032
Token had
Token ID550
Feature activation+8.90e-01

Pos logit contributions
 Cle+0.010
 tail+0.010
 Horse+0.009
 ears+0.009
 prope+0.009
Neg logit contributions
rig-0.016
pack-0.015
inner-0.015
washer-0.015
prise-0.014
Token collected
Token ID7723
Feature activation-1.43e+00

Pos logit contributions
 Cle+0.028
 tail+0.028
 no+0.028
 ears+0.027
 goodbye+0.025
Neg logit contributions
rig-0.039
inner-0.038
pack-0.038
washer-0.036
prise-0.034
Token all
Token ID477
Feature activation-2.71e+00

Pos logit contributions
rig+0.070
pack+0.070
inner+0.069
washer+0.066
prise+0.064
Neg logit contributions
 Cle-0.037
 tail-0.037
 ears-0.034
 no-0.034
 Horse-0.033
Token feel
Token ID1254
Feature activation+1.19e-01

Pos logit contributions
 Cle+0.002
 tail+0.002
 Horse+0.002
 prope+0.002
joy+0.002
Neg logit contributions
pack-0.002
rig-0.002
inner-0.002
washer-0.002
prise-0.002
Token very
Token ID845
Feature activation-1.79e+00

Pos logit contributions
 Cle+0.004
 tail+0.004
 Horse+0.004
 ears+0.004
 prope+0.004
Neg logit contributions
rig-0.005
pack-0.005
inner-0.005
washer-0.004
prise-0.004
Token sleepy
Token ID42023
Feature activation+6.01e-01

Pos logit contributions
rig+0.075
pack+0.073
inner+0.072
washer+0.069
prise+0.066
Neg logit contributions
 Cle-0.060
 tail-0.058
 Horse-0.055
 ears-0.054
 prope-0.054
Token.
Token ID13
Feature activation+5.31e-01

Pos logit contributions
 Cle+0.022
 tail+0.021
 prope+0.020
 Horse+0.020
 ears+0.019
Neg logit contributions
pack-0.022
inner-0.022
washer-0.022
rig-0.022
ade-0.020
Token In
Token ID554
Feature activation+4.57e-03

Pos logit contributions
 Cle+0.013
 tail+0.012
 prope+0.011
 Horse+0.010
 ears+0.010
Neg logit contributions
rig-0.027
pack-0.027
inner-0.027
washer-0.026
prise-0.024
Token no
Token ID645
Feature activation+5.76e+00

Pos logit contributions
 Cle+0.000
 tail+0.000
 prope+0.000
 ears+0.000
 Horse+0.000
Neg logit contributions
pack-0.000
inner-0.000
rig-0.000
washer-0.000
prise-0.000
Token time
Token ID640
Feature activation-8.94e-01

Pos logit contributions
 Cle+0.198
 tail+0.184
 Horse+0.178
 prope+0.177
 ears+0.172
Neg logit contributions
rig-0.236
pack-0.231
inner-0.228
washer-0.213
prise-0.211
Token,
Token ID11
Feature activation+8.16e-01

Pos logit contributions
washer+0.033
pack+0.032
inner+0.030
 else+0.030
prise+0.029
Neg logit contributions
 Cle-0.033
 tail-0.032
 prope-0.031
Leave-0.029
 Horse-0.029
Token he
Token ID339
Feature activation+1.34e+00

Pos logit contributions
 Cle+0.027
 tail+0.026
 prope+0.024
joy+0.023
 ears+0.023
Neg logit contributions
pack-0.033
rig-0.033
inner-0.032
washer-0.032
prise-0.029
Token was
Token ID373
Feature activation+1.19e-01

Pos logit contributions
 Cle+0.036
 tail+0.034
 Horse+0.032
 prope+0.031
 ears+0.031
Neg logit contributions
rig-0.065
pack-0.064
inner-0.063
washer-0.062
prise-0.059
Token asleep
Token ID16039
Feature activation+3.26e+00

Pos logit contributions
 Cle+0.004
 tail+0.004
 Horse+0.003
 prope+0.003
 ears+0.003
Neg logit contributions
pack-0.005
rig-0.005
washer-0.005
inner-0.005
prise-0.004
Token top
Token ID1353
Feature activation+1.03e+00

Pos logit contributions
 Cle+0.042
 tail+0.039
 Horse+0.038
 ears+0.037
 Wo+0.036
Neg logit contributions
inner-0.034
rig-0.034
pack-0.033
washer-0.033
ade-0.029
Token.
Token ID13
Feature activation+5.76e-01

Pos logit contributions
 Cle+0.031
 tail+0.030
 ears+0.028
 Horse+0.028
 no+0.027
Neg logit contributions
rig-0.046
pack-0.046
inner-0.045
washer-0.042
prise-0.042
Token It
Token ID632
Feature activation+2.22e-01

Pos logit contributions
 Cle+0.013
 tail+0.012
 Horse+0.011
 prope+0.011
 ears+0.010
Neg logit contributions
rig-0.031
pack-0.030
inner-0.030
washer-0.029
ade-0.027
Token was
Token ID373
Feature activation-1.64e-01

Pos logit contributions
 Cle+0.007
 tail+0.007
 Horse+0.006
 ears+0.006
 prope+0.006
Neg logit contributions
rig-0.010
pack-0.009
inner-0.009
washer-0.009
ade-0.009
Token a
Token ID257
Feature activation+8.97e-01

Pos logit contributions
rig+0.007
pack+0.006
inner+0.006
washer+0.006
prise+0.006
Neg logit contributions
 Cle-0.006
 tail-0.005
 Horse-0.005
 prope-0.005
 ears-0.005
Token goodbye
Token ID24829
Feature activation+5.76e+00

Pos logit contributions
 Cle+0.032
 tail+0.031
 Horse+0.029
 ears+0.029
 prope+0.028
Neg logit contributions
rig-0.036
pack-0.035
inner-0.035
washer-0.033
prise-0.032
Token light
Token ID1657
Feature activation-6.43e-01

Pos logit contributions
 Cle+0.255
Leave+0.245
 prope+0.245
 tail+0.231
 Horse+0.230
Neg logit contributions
pack-0.172
rig-0.171
washer-0.158
inner-0.152
off-0.137
Token.
Token ID13
Feature activation+3.17e-01

Pos logit contributions
rig+0.029
pack+0.028
inner+0.028
washer+0.027
prise+0.025
Neg logit contributions
 Cle-0.020
 tail-0.019
 Horse-0.018
 ears-0.017
 prope-0.017
Token The
Token ID383
Feature activation+4.14e-01

Pos logit contributions
 Cle+0.007
 tail+0.007
 prope+0.006
 Horse+0.006
 ears+0.006
Neg logit contributions
rig-0.017
pack-0.016
inner-0.016
washer-0.016
off-0.015
Token animals
Token ID4695
Feature activation+1.46e+00

Pos logit contributions
 Cle+0.016
 tail+0.015
 Horse+0.014
 ears+0.014
 prope+0.014
Neg logit contributions
rig-0.015
pack-0.015
inner-0.015
washer-0.014
prise-0.013
Token waved
Token ID26834
Feature activation+1.26e+00

Pos logit contributions
 Cle+0.049
 tail+0.045
 Horse+0.042
 ears+0.042
joy+0.042
Neg logit contributions
pack-0.061
rig-0.060
inner-0.059
washer-0.059
prise-0.055
Token she
Token ID673
Feature activation-1.96e-01

Pos logit contributions
 Cle+0.031
 tail+0.030
 ears+0.027
 Horse+0.027
 prope+0.027
Neg logit contributions
rig-0.051
pack-0.051
inner-0.050
washer-0.048
prise-0.046
Token said
Token ID531
Feature activation-4.19e-01

Pos logit contributions
rig+0.007
pack+0.007
inner+0.007
washer+0.006
ade+0.006
Neg logit contributions
 Cle-0.008
 tail-0.008
 Horse-0.007
 prope-0.007
 ears-0.007
Token.
Token ID13
Feature activation-5.13e-01

Pos logit contributions
pack+0.016
rig+0.016
washer+0.016
inner+0.015
 else+0.014
Neg logit contributions
 Cle-0.016
 Horse-0.015
 tail-0.014
 prope-0.014
Leave-0.014
Token "
Token ID366
Feature activation+8.26e-01

Pos logit contributions
rig+0.028
pack+0.028
inner+0.027
washer+0.026
prise+0.025
Neg logit contributions
 Cle-0.010
 tail-0.010
 prope-0.009
 Horse-0.009
 ears-0.009
TokenIn
Token ID818
Feature activation+1.04e+00

Pos logit contributions
 Cle+0.027
 tail+0.026
 ears+0.026
 Horse+0.024
 ear+0.024
Neg logit contributions
rig-0.036
pack-0.036
inner-0.035
washer-0.033
off-0.032
Token no
Token ID645
Feature activation+5.76e+00

Pos logit contributions
 Cle+0.031
 tail+0.030
 no+0.029
 ears+0.028
 Horse+0.028
Neg logit contributions
rig-0.048
inner-0.047
pack-0.047
washer-0.044
ade-0.043
Token time
Token ID640
Feature activation-1.01e+00

Pos logit contributions
 Cle+0.202
 tail+0.188
 prope+0.182
 Horse+0.181
 ears+0.174
Neg logit contributions
rig-0.231
pack-0.228
inner-0.224
prise-0.211
washer-0.210
Token you
Token ID345
Feature activation+2.18e-01

Pos logit contributions
pack+0.042
inner+0.041
rig+0.041
washer+0.040
prise+0.038
Neg logit contributions
 Cle-0.034
 tail-0.032
 prope-0.031
 Horse-0.031
 ears-0.029
Token'll
Token ID1183
Feature activation+1.75e+00

Pos logit contributions
 Cle+0.007
 tail+0.007
 ears+0.007
 Horse+0.007
 no+0.007
Neg logit contributions
rig-0.009
pack-0.009
inner-0.009
washer-0.008
prise-0.008
Token be
Token ID307
Feature activation-2.65e-01

Pos logit contributions
 Cle+0.062
 tail+0.060
 Horse+0.059
joy+0.058
 ears+0.057
Neg logit contributions
pack-0.067
rig-0.067
inner-0.064
prise-0.060
washer-0.059
Token able
Token ID1498
Feature activation+6.06e-01

Pos logit contributions
rig+0.010
pack+0.010
inner+0.010
washer+0.010
prise+0.009
Neg logit contributions
 Cle-0.009
 tail-0.009
 Horse-0.009
 prope-0.008
 ears-0.008
Token The
Token ID383
Feature activation+1.04e+00

Pos logit contributions
rig+0.013
inner+0.012
pack+0.012
washer+0.011
off+0.011
Neg logit contributions
 Cle-0.012
joy-0.012
 tail-0.012
itive-0.011
ously-0.011
Token beat
Token ID4405
Feature activation+5.78e-01

Pos logit contributions
 Cle+0.037
joy+0.033
 Horse+0.033
ked+0.033
 no+0.032
Neg logit contributions
rig-0.041
inner-0.041
pack-0.039
washer-0.038
ade-0.034
Token is
Token ID318
Feature activation-8.96e-01

Pos logit contributions
 Cle+0.021
 tail+0.021
 Horse+0.019
 ears+0.019
 prope+0.019
Neg logit contributions
rig-0.022
pack-0.022
inner-0.022
washer-0.021
prise-0.020
Token like
Token ID588
Feature activation-1.34e+00

Pos logit contributions
rig+0.035
pack+0.034
inner+0.034
washer+0.032
prise+0.031
Neg logit contributions
 Cle-0.032
 tail-0.031
 Horse-0.030
 ears-0.029
 prope-0.029
Token a
Token ID257
Feature activation+1.02e+00

Pos logit contributions
rig+0.053
pack+0.052
inner+0.052
washer+0.049
prise+0.047
Neg logit contributions
 Cle-0.046
 tail-0.044
 Horse-0.042
 prope-0.041
 ears-0.041
Token heartbeat
Token ID36051
Feature activation+5.75e+00

Pos logit contributions
 Cle+0.036
ked+0.032
 Horse+0.032
 tail+0.031
Leave+0.031
Neg logit contributions
rig-0.040
inner-0.038
pack-0.037
washer-0.037
prise-0.035
Token.
Token ID13
Feature activation+7.13e-02

Pos logit contributions
 Cle+0.202
joy+0.179
 tail+0.178
 Horse+0.173
 prope+0.170
Neg logit contributions
inner-0.231
rig-0.230
pack-0.225
washer-0.224
ade-0.209
Token It
Token ID632
Feature activation+4.32e-01

Pos logit contributions
 Cle+0.002
joy+0.002
 tail+0.002
itive+0.002
ously+0.002
Neg logit contributions
rig-0.003
inner-0.002
pack-0.002
washer-0.002
prise-0.002
Token goes
Token ID2925
Feature activation-8.11e-02

Pos logit contributions
 tail+0.014
 Cle+0.014
 ears+0.014
 no+0.013
 prope+0.013
Neg logit contributions
pack-0.018
rig-0.018
inner-0.018
prise-0.017
igsaw-0.016
Token boom
Token ID14166
Feature activation+5.55e-01

Pos logit contributions
rig+0.003
pack+0.003
inner+0.003
washer+0.003
prise+0.003
Neg logit contributions
 Cle-0.003
 tail-0.003
 Horse-0.003
 ears-0.003
 prope-0.003
Token boom
Token ID14166
Feature activation+4.84e-01

Pos logit contributions
 Cle+0.015
 tail+0.015
 Horse+0.014
 ears+0.014
 prope+0.014
Neg logit contributions
rig-0.026
pack-0.026
inner-0.025
washer-0.024
prise-0.024
Token and
Token ID290
Feature activation+3.39e-01

Pos logit contributions
 Cle+0.074
 prope+0.067
 tail+0.067
 Horse+0.066
Leave+0.066
Neg logit contributions
rig-0.079
inner-0.077
pack-0.075
washer-0.072
prise-0.070
Token peaceful
Token ID12309
Feature activation+1.06e+00

Pos logit contributions
 Cle+0.012
 tail+0.011
 prope+0.011
 Horse+0.011
 ears+0.011
Neg logit contributions
rig-0.013
pack-0.013
inner-0.013
washer-0.013
prise-0.012
Token dream
Token ID4320
Feature activation+2.30e+00

Pos logit contributions
 Cle+0.041
 prope+0.036
Leave+0.036
 tail+0.036
 Horse+0.035
Neg logit contributions
rig-0.039
pack-0.038
inner-0.038
washer-0.035
ade-0.034
Token and
Token ID290
Feature activation+6.27e-01

Pos logit contributions
 Cle+0.087
 tail+0.084
 ears+0.080
 prope+0.079
 Horse+0.079
Neg logit contributions
rig-0.088
inner-0.087
pack-0.087
washer-0.083
ade-0.078
Token was
Token ID373
Feature activation+8.36e-01

Pos logit contributions
 Cle+0.021
 tail+0.020
 prope+0.020
 Horse+0.020
 ears+0.019
Neg logit contributions
washer-0.025
pack-0.024
rig-0.024
inner-0.024
prise-0.022
Token no
Token ID645
Feature activation+5.75e+00

Pos logit contributions
 Cle+0.028
 tail+0.027
 ears+0.025
 prope+0.025
Leave+0.025
Neg logit contributions
pack-0.033
rig-0.033
washer-0.032
inner-0.031
prise-0.030
Token longer
Token ID2392
Feature activation+2.19e+00

Pos logit contributions
 Cle+0.183
 tail+0.169
 Horse+0.165
 prope+0.156
 ears+0.155
Neg logit contributions
rig-0.250
pack-0.243
inner-0.242
prise-0.229
washer-0.229
Token scared
Token ID12008
Feature activation+1.18e+00

Pos logit contributions
 Cle+0.074
 tail+0.068
 Horse+0.067
 prope+0.065
 Wo+0.063
Neg logit contributions
rig-0.086
washer-0.085
pack-0.084
inner-0.082
prise-0.076
Token.
Token ID13
Feature activation+6.94e-01

Pos logit contributions
 Cle+0.044
 tail+0.042
 prope+0.040
 Horse+0.039
 ears+0.038
Neg logit contributions
rig-0.042
washer-0.042
inner-0.042
pack-0.041
off-0.038
Token<|endoftext|>
Token ID50256
Feature activation-1.86e+00

Pos logit contributions
 tail+0.020
 prope+0.020
 Cle+0.020
 ears+0.019
 Horse+0.019
Neg logit contributions
rig-0.031
pack-0.030
inner-0.029
washer-0.029
prise-0.027
TokenOnce
Token ID7454
Feature activation-4.92e-02

Pos logit contributions
pack+0.074
inner+0.073
rig+0.072
washer+0.068
ade+0.066
Neg logit contributions
 Cle-0.065
 prope-0.064
 tail-0.064
 ears-0.062
 ear-0.059
Token take
Token ID1011
Feature activation+1.10e+00

Pos logit contributions
pack+0.038
rig+0.036
inner+0.035
prise+0.033
washer+0.032
Neg logit contributions
 Cle-0.040
joy-0.040
 Horse-0.039
 tail-0.039
 prope-0.038
Token her
Token ID607
Feature activation+1.60e-01

Pos logit contributions
 Cle+0.038
 tail+0.038
 prope+0.038
 Horse+0.036
 ears+0.035
Neg logit contributions
pack-0.041
inner-0.040
rig-0.040
prise-0.038
off-0.038
Token medicine
Token ID9007
Feature activation+1.50e+00

Pos logit contributions
 Cle+0.005
 tail+0.005
 ears+0.005
 Horse+0.005
 prope+0.005
Neg logit contributions
rig-0.007
pack-0.007
inner-0.006
washer-0.006
prise-0.006
Token.
Token ID13
Feature activation+2.79e-01

Pos logit contributions
 Cle+0.042
 tail+0.042
 no+0.038
 Horse+0.038
 ears+0.038
Neg logit contributions
rig-0.070
pack-0.069
inner-0.068
prise-0.064
washer-0.063
Token In
Token ID554
Feature activation+1.79e-01

Pos logit contributions
 Cle+0.008
 tail+0.007
 prope+0.007
 Horse+0.007
 ears+0.007
Neg logit contributions
rig-0.013
pack-0.013
inner-0.013
washer-0.012
igsaw-0.012
Token no
Token ID645
Feature activation+5.74e+00

Pos logit contributions
 Cle+0.005
 tail+0.005
 prope+0.005
 Horse+0.005
 ears+0.005
Neg logit contributions
pack-0.008
rig-0.008
inner-0.008
washer-0.007
prise-0.007
Token time
Token ID640
Feature activation-7.39e-01

Pos logit contributions
 Cle+0.207
 tail+0.189
 prope+0.186
 Horse+0.185
 ears+0.177
Neg logit contributions
rig-0.223
pack-0.218
inner-0.213
prise-0.200
ade-0.198
Token at
Token ID379
Feature activation+3.42e-01

Pos logit contributions
pack+0.029
washer+0.027
inner+0.027
 else+0.027
rig+0.027
Neg logit contributions
 tail-0.025
 Cle-0.025
 prope-0.024
 Horse-0.023
 ears-0.023
Token all
Token ID477
Feature activation-2.16e+00

Pos logit contributions
 Cle+0.010
 tail+0.010
 Horse+0.009
 no+0.009
 ear+0.009
Neg logit contributions
rig-0.016
pack-0.015
inner-0.015
washer-0.014
prise-0.014
Token,
Token ID11
Feature activation+6.64e-01

Pos logit contributions
rig+0.122
pack+0.121
inner+0.120
washer+0.111
prise+0.111
Neg logit contributions
 Cle-0.041
 tail-0.040
 no-0.040
 ears-0.039
 ear-0.038
Token Anna
Token ID11735
Feature activation-1.14e-01

Pos logit contributions
 Cle+0.025
 prope+0.023
 tail+0.023
 Horse+0.023
 horns+0.021
Neg logit contributions
inner-0.024
pack-0.024
rig-0.024
 else-0.024
washer-0.023
Token go
Token ID467
Feature activation-1.37e+00

Pos logit contributions
 Cle+0.017
 tail+0.017
 Horse+0.016
 ears+0.016
 prope+0.015
Neg logit contributions
rig-0.023
pack-0.023
inner-0.022
washer-0.021
prise-0.020
Token to
Token ID284
Feature activation-5.28e-01

Pos logit contributions
rig+0.066
inner+0.065
pack+0.063
washer+0.062
prise+0.061
Neg logit contributions
 Cle-0.037
 tail-0.034
 ear-0.032
 Horse-0.032
 no-0.031
Token work
Token ID670
Feature activation-1.78e+00

Pos logit contributions
rig+0.025
pack+0.024
inner+0.024
washer+0.023
prise+0.022
Neg logit contributions
 Cle-0.015
 tail-0.015
 Horse-0.013
 ears-0.013
 prope-0.013
Token.
Token ID13
Feature activation+3.52e-01

Pos logit contributions
rig+0.087
pack+0.085
inner+0.084
washer+0.081
prise+0.079
Neg logit contributions
 Cle-0.046
 tail-0.045
 no-0.042
 ears-0.040
 Horse-0.040
Token In
Token ID554
Feature activation+1.49e-01

Pos logit contributions
 Cle+0.009
 tail+0.009
 Horse+0.008
 ears+0.008
 prope+0.008
Neg logit contributions
rig-0.017
pack-0.017
inner-0.017
washer-0.016
prise-0.016
Token no
Token ID645
Feature activation+5.74e+00

Pos logit contributions
 Cle+0.004
 tail+0.004
 Horse+0.004
 prope+0.004
 ears+0.004
Neg logit contributions
pack-0.007
rig-0.007
inner-0.007
washer-0.006
prise-0.006
Token time
Token ID640
Feature activation-8.15e-01

Pos logit contributions
 Cle+0.188
 tail+0.179
 Horse+0.170
 prope+0.168
 ears+0.166
Neg logit contributions
rig-0.244
pack-0.241
inner-0.237
washer-0.222
prise-0.218
Token at
Token ID379
Feature activation+2.89e-01

Pos logit contributions
pack+0.034
inner+0.033
rig+0.032
washer+0.032
prise+0.031
Neg logit contributions
 Cle-0.026
 tail-0.026
 Horse-0.025
 prope-0.025
 ears-0.024
Token all
Token ID477
Feature activation-2.17e+00

Pos logit contributions
 Cle+0.008
 tail+0.007
 no+0.007
 ear+0.007
 ears+0.007
Neg logit contributions
rig-0.014
inner-0.014
pack-0.014
washer-0.013
prise-0.013
Token,
Token ID11
Feature activation+6.37e-01

Pos logit contributions
rig+0.126
inner+0.123
pack+0.123
washer+0.114
prise+0.114
Neg logit contributions
 no-0.039
 Cle-0.037
 tail-0.036
 ears-0.035
 ear-0.034
Token Amy
Token ID14235
Feature activation-6.51e-01

Pos logit contributions
 Cle+0.026
 Horse+0.025
 prope+0.025
 tail+0.024
 ears+0.023
Neg logit contributions
rig-0.021
pack-0.021
inner-0.021
 else-0.020
washer-0.019
Token to
Token ID284
Feature activation-4.31e-01

Pos logit contributions
pack+0.007
rig+0.007
washer+0.006
inner+0.006
ade+0.006
Neg logit contributions
 Cle-0.010
 Horse-0.010
 tail-0.010
 prope-0.009
 ear-0.009
Token rebuild
Token ID17884
Feature activation+1.25e+00

Pos logit contributions
rig+0.016
pack+0.016
inner+0.016
washer+0.015
prise+0.014
Neg logit contributions
 Cle-0.016
 tail-0.015
 Horse-0.015
 ears-0.015
 ear-0.014
Token themselves
Token ID2405
Feature activation-9.26e-01

Pos logit contributions
 Cle+0.036
 tail+0.035
 Horse+0.033
 ears+0.032
 prope+0.032
Neg logit contributions
rig-0.058
pack-0.057
inner-0.056
washer-0.054
prise-0.052
Token.
Token ID13
Feature activation+4.44e-01

Pos logit contributions
rig+0.052
inner+0.051
prise+0.051
pack+0.050
washer+0.047
Neg logit contributions
 tail-0.018
 no-0.017
 ears-0.017
 heart-0.014
 prope-0.014
Token In
Token ID554
Feature activation+8.80e-03

Pos logit contributions
 Cle+0.011
 tail+0.011
 Horse+0.010
 prope+0.010
 ears+0.010
Neg logit contributions
rig-0.022
pack-0.022
inner-0.022
washer-0.021
prise-0.020
Token no
Token ID645
Feature activation+5.74e+00

Pos logit contributions
 Cle+0.000
 tail+0.000
 Horse+0.000
 ears+0.000
 prope+0.000
Neg logit contributions
pack-0.000
rig-0.000
inner-0.000
washer-0.000
prise-0.000
Token time
Token ID640
Feature activation-9.78e-01

Pos logit contributions
 Cle+0.212
 tail+0.191
 Horse+0.189
 prope+0.186
 ears+0.178
Neg logit contributions
rig-0.218
pack-0.213
inner-0.206
prise-0.195
ade-0.193
Token the
Token ID262
Feature activation-2.05e-01

Pos logit contributions
pack+0.038
washer+0.036
inner+0.036
 else+0.035
rig+0.035
Neg logit contributions
 Cle-0.034
 tail-0.033
 Horse-0.032
 prope-0.031
 ears-0.031
Token houses
Token ID7777
Feature activation+1.45e+00

Pos logit contributions
rig+0.007
inner+0.007
pack+0.007
washer+0.007
prise+0.007
Neg logit contributions
 Cle-0.008
 Horse-0.007
 tail-0.007
 Wo-0.007
 Paw-0.007
Token were
Token ID547
Feature activation-8.41e-01

Pos logit contributions
 Cle+0.039
 tail+0.037
 Horse+0.034
 ears+0.034
 prope+0.034
Neg logit contributions
rig-0.070
pack-0.069
inner-0.068
washer-0.065
prise-0.063
Token restored
Token ID15032
Feature activation+7.25e-01

Pos logit contributions
rig+0.032
pack+0.031
inner+0.031
washer+0.029
prise+0.028
Neg logit contributions
 Cle-0.032
 tail-0.031
 Horse-0.029
 ears-0.029
 prope-0.028
Token happy
Token ID3772
Feature activation-2.16e-01

Pos logit contributions
 tail+0.020
 Cle+0.019
 ears+0.019
 no+0.018
 ear+0.018
Neg logit contributions
inner-0.035
pack-0.035
rig-0.034
washer-0.032
prise-0.032
Token.
Token ID13
Feature activation+2.83e-01

Pos logit contributions
rig+0.010
pack+0.010
inner+0.010
washer+0.009
prise+0.009
Neg logit contributions
 Cle-0.006
 tail-0.006
 Horse-0.005
 ears-0.005
 prope-0.005
Token
Token ID198
Feature activation+2.11e-01

Pos logit contributions
 Cle+0.007
 tail+0.007
 prope+0.007
 ears+0.007
Leave+0.007
Neg logit contributions
rig-0.013
pack-0.013
inner-0.013
washer-0.013
off-0.012
Token
Token ID198
Feature activation+6.61e-01

Pos logit contributions
 Cle+0.006
 tail+0.006
 Horse+0.005
 ears+0.005
 prope+0.005
Neg logit contributions
rig-0.010
pack-0.010
inner-0.010
washer-0.009
prise-0.009
TokenIn
Token ID818
Feature activation+1.00e+00

Pos logit contributions
 Cle+0.017
 tail+0.016
 Horse+0.015
 ears+0.015
 prope+0.015
Neg logit contributions
rig-0.033
pack-0.032
inner-0.032
washer-0.031
prise-0.030
Token no
Token ID645
Feature activation+5.74e+00

Pos logit contributions
 Cle+0.030
 tail+0.029
 ears+0.027
 Horse+0.026
 prope+0.026
Neg logit contributions
pack-0.043
rig-0.042
inner-0.042
washer-0.041
prise-0.039
Token time
Token ID640
Feature activation-8.99e-01

Pos logit contributions
 Cle+0.199
 tail+0.184
 Horse+0.177
 prope+0.176
 ears+0.173
Neg logit contributions
rig-0.232
pack-0.228
inner-0.223
washer-0.208
prise-0.207
Token at
Token ID379
Feature activation+2.19e-01

Pos logit contributions
pack+0.035
washer+0.035
inner+0.034
rig+0.032
 else+0.032
Neg logit contributions
 Cle-0.031
 tail-0.030
 prope-0.028
 ears-0.028
 Horse-0.027
Token all
Token ID477
Feature activation-2.34e+00

Pos logit contributions
 Cle+0.006
 tail+0.006
 no+0.005
 Horse+0.005
 prope+0.005
Neg logit contributions
rig-0.011
pack-0.011
inner-0.011
washer-0.010
prise-0.010
Token,
Token ID11
Feature activation+5.96e-01

Pos logit contributions
rig+0.139
pack+0.135
inner+0.134
prise+0.125
washer+0.123
Neg logit contributions
 no-0.042
 tail-0.041
 ears-0.039
 Cle-0.038
 ear-0.037
Token the
Token ID262
Feature activation+1.35e-01

Pos logit contributions
 Cle+0.021
 tail+0.020
 prope+0.020
Leave+0.020
 Horse+0.019
Neg logit contributions
washer-0.020
rig-0.020
pack-0.020
inner-0.019
 else-0.019
Token Sandy
Token ID17581
Feature activation-2.54e+00

Pos logit contributions
 Cle+0.083
 tail+0.081
 prope+0.076
 Horse+0.076
Leave+0.074
Neg logit contributions
rig-0.093
pack-0.092
inner-0.090
washer-0.086
ade-0.082
Token's
Token ID338
Feature activation+1.85e-01

Pos logit contributions
rig+0.099
pack+0.098
inner+0.096
washer+0.091
prise+0.087
Neg logit contributions
 Cle-0.092
 tail-0.089
 Horse-0.084
 ears-0.083
 prope-0.083
Token knee
Token ID10329
Feature activation+2.57e+00

Pos logit contributions
 Cle+0.005
 tail+0.005
 Horse+0.004
 prope+0.004
 Paw+0.004
Neg logit contributions
pack-0.009
rig-0.009
inner-0.009
washer-0.008
prise-0.008
Token.
Token ID13
Feature activation+3.48e-01

Pos logit contributions
 Cle+0.083
 tail+0.078
joy+0.076
 Horse+0.076
 ear+0.073
Neg logit contributions
pack-0.108
rig-0.107
inner-0.104
washer-0.104
ade-0.099
Token In
Token ID554
Feature activation-2.92e-02

Pos logit contributions
 tail+0.010
 Cle+0.010
 prope+0.010
 Horse+0.009
 ears+0.009
Neg logit contributions
rig-0.016
pack-0.015
inner-0.015
washer-0.014
igsaw-0.014
Token no
Token ID645
Feature activation+5.73e+00

Pos logit contributions
pack+0.001
rig+0.001
inner+0.001
washer+0.001
prise+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 Horse-0.001
 ears-0.001
 prope-0.001
Token time
Token ID640
Feature activation-8.45e-01

Pos logit contributions
 Cle+0.178
 tail+0.173
 Horse+0.161
 ears+0.160
 prope+0.158
Neg logit contributions
rig-0.254
pack-0.251
inner-0.248
washer-0.236
prise-0.227
Token she
Token ID673
Feature activation+5.95e-01

Pos logit contributions
pack+0.035
inner+0.035
rig+0.034
washer+0.034
prise+0.032
Neg logit contributions
 tail-0.027
 Cle-0.027
 prope-0.025
 Horse-0.025
 ears-0.024
Token was
Token ID373
Feature activation-8.16e-02

Pos logit contributions
 Cle+0.017
 tail+0.016
 ears+0.015
 no+0.015
 Horse+0.015
Neg logit contributions
rig-0.028
inner-0.028
pack-0.028
washer-0.026
prise-0.025
Token right
Token ID826
Feature activation+1.10e-01

Pos logit contributions
rig+0.003
pack+0.003
inner+0.003
washer+0.003
prise+0.003
Neg logit contributions
 Cle-0.003
 tail-0.003
 Horse-0.003
 prope-0.003
 ears-0.003
Token as
Token ID355
Feature activation-7.95e-01

Pos logit contributions
 Cle+0.004
 tail+0.004
 prope+0.004
 Horse+0.004
Leave+0.004
Neg logit contributions
pack-0.004
rig-0.004
inner-0.004
washer-0.004
prise-0.004
Token."
Token ID526
Feature activation-4.40e-02

Pos logit contributions
rig+0.006
pack+0.006
inner+0.006
washer+0.005
prise+0.005
Neg logit contributions
 Cle-0.005
 tail-0.005
 ears-0.004
 Horse-0.004
 no-0.004
Token
Token ID220
Feature activation+1.31e+00

Pos logit contributions
rig+0.002
pack+0.002
inner+0.002
washer+0.002
prise+0.002
Neg logit contributions
 Cle-0.001
 tail-0.001
 prope-0.001
 Horse-0.001
 ears-0.001
Token
Token ID198
Feature activation-4.39e-01

Pos logit contributions
 Cle+0.028
 tail+0.027
 Horse+0.024
 ears+0.024
 no+0.023
Neg logit contributions
rig-0.069
pack-0.069
inner-0.068
washer-0.065
prise-0.064
Token
Token ID198
Feature activation+2.69e-01

Pos logit contributions
rig+0.022
pack+0.021
inner+0.021
washer+0.020
prise+0.019
Neg logit contributions
 Cle-0.012
 tail-0.011
 ears-0.010
 prope-0.010
 Horse-0.010
TokenInt
Token ID5317
Feature activation-7.48e-01

Pos logit contributions
 Cle+0.007
 tail+0.006
 Horse+0.006
 no+0.006
 prope+0.005
Neg logit contributions
rig-0.014
inner-0.013
pack-0.013
washer-0.013
ade-0.012
Tokenrig
Token ID4359
Feature activation-6.89e+00

Pos logit contributions
prise+0.012
inner+0.012
pack+0.012
washer+0.010
ade+0.010
Neg logit contributions
 Cle-0.039
 tail-0.038
 no-0.038
 Horse-0.038
 Big-0.037
Tokenued
Token ID1739
Feature activation-1.10e-01

Pos logit contributions
rig+0.270
pack+0.264
inner+0.255
washer+0.242
prise+0.238
Neg logit contributions
 Cle-0.241
 no-0.227
 tail-0.225
 goodbye-0.224
 prope-0.221
Token,
Token ID11
Feature activation+5.03e-01

Pos logit contributions
rig+0.005
pack+0.005
inner+0.004
washer+0.004
prise+0.004
Neg logit contributions
 Cle-0.004
 prope-0.003
 tail-0.003
 Horse-0.003
 ears-0.003
Token the
Token ID262
Feature activation+2.79e-01

Pos logit contributions
 Cle+0.016
 tail+0.016
 prope+0.016
 Horse+0.015
 ears+0.015
Neg logit contributions
rig-0.020
pack-0.020
inner-0.019
washer-0.019
prise-0.017
Token little
Token ID1310
Feature activation-1.35e+00

Pos logit contributions
 Cle+0.008
 prope+0.007
 tail+0.007
 Horse+0.007
Leave+0.007
Neg logit contributions
rig-0.013
washer-0.013
inner-0.013
pack-0.012
prise-0.011
Token brother
Token ID3956
Feature activation+2.58e+00

Pos logit contributions
washer+0.054
rig+0.053
inner+0.053
pack+0.053
igsaw+0.048
Neg logit contributions
 Cle-0.044
 prope-0.041
 tail-0.040
Leave-0.039
 Horse-0.039
Token waiting
Token ID4953
Feature activation-1.58e-01

Pos logit contributions
rig+0.035
pack+0.034
inner+0.034
washer+0.032
prise+0.031
Neg logit contributions
 Cle-0.027
 tail-0.026
 Horse-0.025
 ears-0.025
 prope-0.024
Token for
Token ID329
Feature activation-4.56e-01

Pos logit contributions
rig+0.006
pack+0.006
inner+0.006
washer+0.005
prise+0.005
Neg logit contributions
 Cle-0.006
 tail-0.006
 Horse-0.005
 ears-0.005
 prope-0.005
Token something
Token ID1223
Feature activation-1.73e+00

Pos logit contributions
pack+0.016
rig+0.016
inner+0.016
washer+0.015
prise+0.015
Neg logit contributions
 Cle-0.018
 tail-0.017
 prope-0.016
 Horse-0.016
 ears-0.016
Token".
Token ID1911
Feature activation-2.39e-01

Pos logit contributions
pack+0.078
inner+0.078
rig+0.078
igsaw+0.072
washer+0.069
Neg logit contributions
 no-0.053
 Cle-0.052
 tail-0.051
 goodbye-0.049
 ears-0.048
Token Int
Token ID2558
Feature activation-2.18e+00

Pos logit contributions
rig+0.014
pack+0.014
inner+0.014
washer+0.013
prise+0.013
Neg logit contributions
 Cle-0.004
 tail-0.004
 ears-0.004
 Horse-0.004
 ear-0.003
Tokenrig
Token ID4359
Feature activation-6.70e+00

Pos logit contributions
pack+0.033
washer+0.032
inner+0.029
prise+0.025
oons+0.019
Neg logit contributions
 Cle-0.120
 tail-0.111
Leave-0.110
By-0.110
 Paw-0.109
Tokenued
Token ID1739
Feature activation-1.04e+00

Pos logit contributions
rig+0.267
pack+0.254
inner+0.247
washer+0.234
prise+0.225
Neg logit contributions
 Cle-0.240
 tail-0.222
 goodbye-0.221
 no-0.218
 ear-0.218
Token,
Token ID11
Feature activation-1.98e-01

Pos logit contributions
rig+0.038
inner+0.037
pack+0.037
washer+0.036
ade+0.035
Neg logit contributions
 prope-0.038
 tail-0.037
 Cle-0.035
 Horse-0.034
 ears-0.033
Token the
Token ID262
Feature activation-2.06e-01

Pos logit contributions
washer+0.006
rig+0.006
pack+0.006
inner+0.006
 else+0.006
Neg logit contributions
 prope-0.007
 tail-0.007
 Cle-0.007
 Horse-0.007
 ears-0.007
Token girl
Token ID2576
Feature activation-4.50e-01

Pos logit contributions
inner+0.009
rig+0.009
pack+0.009
washer+0.009
prise+0.008
Neg logit contributions
 Cle-0.006
 tail-0.006
 prope-0.006
 Horse-0.006
 ears-0.006
Token asked
Token ID1965
Feature activation-3.93e-01

Pos logit contributions
rig+0.021
inner+0.021
pack+0.020
washer+0.019
prise+0.019
Neg logit contributions
 Cle-0.013
 tail-0.013
 ears-0.012
 Horse-0.012
 no-0.012
Token around
Token ID1088
Feature activation+8.99e-02

Pos logit contributions
 Cle+0.002
 tail+0.002
 Horse+0.002
 prope+0.002
 ears+0.002
Neg logit contributions
pack-0.002
rig-0.002
inner-0.002
washer-0.002
prise-0.002
Token the
Token ID262
Feature activation+4.08e-01

Pos logit contributions
 Cle+0.003
 tail+0.003
 Horse+0.003
 prope+0.003
 ears+0.003
Neg logit contributions
pack-0.004
inner-0.004
rig-0.003
washer-0.003
 else-0.003
Token room
Token ID2119
Feature activation-2.12e+00

Pos logit contributions
 Cle+0.017
 tail+0.016
 ears+0.016
 Horse+0.015
 prope+0.015
Neg logit contributions
rig-0.014
pack-0.014
inner-0.014
washer-0.013
prise-0.012
Token.
Token ID13
Feature activation+2.66e-01

Pos logit contributions
pack+0.091
rig+0.090
inner+0.089
washer+0.087
ade+0.083
Neg logit contributions
 Cle-0.069
 tail-0.064
 Horse-0.063
 prope-0.060
 ears-0.058
Token Int
Token ID2558
Feature activation-1.50e+00

Pos logit contributions
 tail+0.007
 Cle+0.007
 prope+0.007
 ears+0.007
 Horse+0.006
Neg logit contributions
rig-0.013
pack-0.012
inner-0.012
washer-0.011
igsaw-0.011
Tokenrig
Token ID4359
Feature activation-6.61e+00

Pos logit contributions
washer+0.019
pack+0.019
inner+0.017
prise+0.017
ade+0.012
Neg logit contributions
 Cle-0.086
 prope-0.082
 no-0.081
 tail-0.081
By-0.080
Tokenued
Token ID1739
Feature activation-2.78e-01

Pos logit contributions
rig+0.238
pack+0.233
inner+0.227
washer+0.215
prise+0.208
Neg logit contributions
 Cle-0.259
 tail-0.251
 prope-0.238
 Horse-0.238
 no-0.236
Token,
Token ID11
Feature activation+3.82e-01

Pos logit contributions
rig+0.011
pack+0.011
inner+0.011
washer+0.011
ade+0.010
Neg logit contributions
 Cle-0.009
 prope-0.009
 tail-0.009
 Horse-0.008
Leave-0.008
Token it
Token ID340
Feature activation+6.38e-01

Pos logit contributions
 tail+0.012
 prope+0.012
 Cle+0.012
 ear+0.012
 ears+0.011
Neg logit contributions
rig-0.015
pack-0.014
inner-0.014
washer-0.014
 else-0.013
Token began
Token ID2540
Feature activation+4.97e-01

Pos logit contributions
 Cle+0.019
 tail+0.019
 Horse+0.017
 ears+0.017
 prope+0.017
Neg logit contributions
rig-0.029
pack-0.028
inner-0.028
washer-0.027
prise-0.026
Token to
Token ID284
Feature activation+3.02e-01

Pos logit contributions
 Cle+0.020
 tail+0.019
 Horse+0.018
 prope+0.018
 ears+0.018
Neg logit contributions
rig-0.018
pack-0.018
inner-0.017
washer-0.016
ade-0.015
Token water
Token ID1660
Feature activation-1.31e+00

Pos logit contributions
 Cle+0.014
 tail+0.013
 Horse+0.013
 prope+0.013
 ears+0.013
Neg logit contributions
rig-0.012
inner-0.012
pack-0.012
washer-0.011
ade-0.010
Token was
Token ID373
Feature activation-1.17e+00

Pos logit contributions
rig+0.059
pack+0.058
inner+0.058
washer+0.055
prise+0.053
Neg logit contributions
 Cle-0.039
 tail-0.038
 Horse-0.035
 ears-0.035
 prope-0.035
Token icy
Token ID30284
Feature activation-1.74e+00

Pos logit contributions
rig+0.045
pack+0.044
inner+0.043
washer+0.041
prise+0.039
Neg logit contributions
 Cle-0.043
 tail-0.042
 Horse-0.040
 ears-0.040
 prope-0.039
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
rig+0.089
pack+0.089
inner+0.086
prise+0.086
washer+0.082
Neg logit contributions
 tail-0.042
 Cle-0.040
 ears-0.039
 no-0.037
 Horse-0.036
Token Int
Token ID2558
Feature activation-1.85e+00

Pos logit contributions
 Cle+0.005
 tail+0.005
 prope+0.005
 Horse+0.005
 ears+0.005
Neg logit contributions
rig-0.009
pack-0.009
inner-0.009
washer-0.008
ade-0.008
Tokenrig
Token ID4359
Feature activation-6.44e+00

Pos logit contributions
pack+0.027
washer+0.027
prise+0.024
inner+0.022
igsaw+0.016
Neg logit contributions
 Cle-0.104
 tail-0.103
 prope-0.100
Leave-0.098
 no-0.098
Tokenued
Token ID1739
Feature activation-1.10e+00

Pos logit contributions
rig+0.229
pack+0.224
inner+0.219
washer+0.206
prise+0.198
Neg logit contributions
 Cle-0.258
 tail-0.250
 Horse-0.237
 prope-0.236
 ears-0.236
Token,
Token ID11
Feature activation-1.75e-01

Pos logit contributions
rig+0.039
inner+0.038
pack+0.037
ade+0.036
off+0.036
Neg logit contributions
 prope-0.042
 tail-0.039
 Cle-0.039
 Horse-0.038
 horns-0.036
Token she
Token ID673
Feature activation-6.21e-01

Pos logit contributions
 else+0.004
inner+0.004
rig+0.004
pack+0.004
washer+0.004
Neg logit contributions
 prope-0.008
 tail-0.007
 Horse-0.007
 Cle-0.007
 ears-0.007
Token sw
Token ID1509
Feature activation-9.27e-01

Pos logit contributions
rig+0.027
pack+0.026
inner+0.026
washer+0.025
ade+0.024
Neg logit contributions
 Cle-0.020
 tail-0.019
 Horse-0.018
 prope-0.018
 ear-0.018
Tokenam
Token ID321
Feature activation-3.32e-01

Pos logit contributions
rig+0.029
pack+0.028
inner+0.028
washer+0.026
prise+0.025
Neg logit contributions
 Cle-0.041
 tail-0.041
 ears-0.039
 Horse-0.038
 ear-0.038
Token,
Token ID11
Feature activation+1.02e+00

Pos logit contributions
rig+0.038
pack+0.037
inner+0.037
washer+0.034
prise+0.033
Neg logit contributions
 Cle-0.034
 tail-0.033
 Horse-0.031
 ears-0.031
 prope-0.030
Token dusty
Token ID36972
Feature activation-1.17e+00

Pos logit contributions
 Cle+0.036
 tail+0.035
 Horse+0.033
 ears+0.033
 prope+0.033
Neg logit contributions
rig-0.040
pack-0.040
inner-0.039
washer-0.037
prise-0.036
Token house
Token ID2156
Feature activation-1.07e+00

Pos logit contributions
rig+0.044
pack+0.042
inner+0.042
prise+0.040
washer+0.038
Neg logit contributions
 tail-0.045
 Cle-0.045
 ears-0.042
 ear-0.042
 prope-0.041
Token.
Token ID13
Feature activation+7.00e-02

Pos logit contributions
rig+0.052
inner+0.048
prise+0.047
pack+0.047
igsaw+0.045
Neg logit contributions
 tail-0.029
 Cle-0.028
 no-0.028
 ears-0.027
 ear-0.026
Token Int
Token ID2558
Feature activation-1.73e+00

Pos logit contributions
 Cle+0.002
 tail+0.001
 ears+0.001
 Horse+0.001
 ear+0.001
Neg logit contributions
rig-0.004
pack-0.004
inner-0.004
washer-0.003
prise-0.003
Tokenrig
Token ID4359
Feature activation-6.37e+00

Pos logit contributions
pack+0.028
washer+0.028
prise+0.025
inner+0.023
 belongs+0.021
Neg logit contributions
 Cle-0.088
stretched-0.085
 crashing-0.083
By-0.082
 prope-0.082
Tokenued
Token ID1739
Feature activation-1.05e+00

Pos logit contributions
rig+0.244
pack+0.233
inner+0.227
washer+0.215
prise+0.210
Neg logit contributions
 Cle-0.239
 tail-0.227
 prope-0.219
 no-0.217
 Horse-0.217
Token,
Token ID11
Feature activation-2.78e-01

Pos logit contributions
pack+0.041
rig+0.041
inner+0.041
washer+0.040
prise+0.038
Neg logit contributions
 prope-0.036
 tail-0.035
 Cle-0.034
 Horse-0.032
Leave-0.032
Token M
Token ID337
Feature activation-4.27e-01

Pos logit contributions
rig+0.014
pack+0.013
inner+0.013
washer+0.013
prise+0.012
Neg logit contributions
 Cle-0.007
 tail-0.007
 Horse-0.006
 prope-0.006
 ears-0.006
Tokenuff
Token ID1648
Feature activation-2.79e+00

Pos logit contributions
pack+0.017
rig+0.017
inner+0.016
prise+0.016
washer+0.016
Neg logit contributions
 Cle-0.015
 tail-0.014
 ears-0.014
 Horse-0.013
 prope-0.013
Tokenin
Token ID259
Feature activation+3.12e-01

Pos logit contributions
rig+0.079
pack+0.078
inner+0.077
washer+0.073
ade+0.067
Neg logit contributions
 Cle-0.131
 tail-0.128
 Horse-0.122
 ears-0.122
 prope-0.121
Token mushrooms
Token ID23452
Feature activation-2.87e-01

Pos logit contributions
 Cle+0.008
 tail+0.007
 prope+0.007
 Horse+0.007
Leave+0.007
Neg logit contributions
inner-0.007
rig-0.007
pack-0.007
washer-0.006
prise-0.006
Token,
Token ID11
Feature activation-6.70e-02

Pos logit contributions
rig+0.013
pack+0.013
inner+0.013
washer+0.012
prise+0.012
Neg logit contributions
 Cle-0.008
 tail-0.008
 ears-0.008
 Horse-0.008
 no-0.008
Token asking
Token ID4737
Feature activation-1.65e-01

Pos logit contributions
rig+0.003
pack+0.003
washer+0.003
inner+0.003
 else+0.002
Neg logit contributions
 Cle-0.002
 tail-0.002
 Horse-0.002
 prope-0.002
 ear-0.002
Token them
Token ID606
Feature activation-2.17e+00

Pos logit contributions
pack+0.006
washer+0.006
rig+0.006
inner+0.005
 else+0.005
Neg logit contributions
 Cle-0.006
 tail-0.006
 prope-0.006
Leave-0.006
 Horse-0.006
Token all
Token ID477
Feature activation-4.05e+00

Pos logit contributions
rig+0.075
pack+0.074
inner+0.071
washer+0.071
prise+0.065
Neg logit contributions
 Cle-0.086
 tail-0.084
 prope-0.081
 Horse-0.079
Leave-0.077
Token sorts
Token ID10524
Feature activation-6.32e+00

Pos logit contributions
pack+0.178
inner+0.176
rig+0.176
washer+0.165
prise+0.160
Neg logit contributions
 tail-0.126
 Cle-0.125
 ears-0.117
 ear-0.116
 no-0.114
Token of
Token ID286
Feature activation-1.47e+00

Pos logit contributions
pack+0.289
rig+0.286
inner+0.278
washer+0.259
prise+0.256
Neg logit contributions
 tail-0.180
 Cle-0.180
 goodbye-0.172
 no-0.171
 ear-0.168
Token questions
Token ID2683
Feature activation+1.25e+00

Pos logit contributions
pack+0.065
inner+0.064
rig+0.064
washer+0.061
prise+0.058
Neg logit contributions
 tail-0.045
 Cle-0.045
 ears-0.043
 ear-0.041
 Horse-0.041
Token.
Token ID13
Feature activation-3.21e-01

Pos logit contributions
 tail+0.031
 Cle+0.031
 no+0.029
 ears+0.028
 Horse+0.028
Neg logit contributions
rig-0.062
pack-0.061
inner-0.060
prise-0.056
washer-0.056
Token
Token ID220
Feature activation+1.83e+00

Pos logit contributions
rig+0.016
pack+0.016
inner+0.016
washer+0.016
off+0.015
Neg logit contributions
 Cle-0.007
 tail-0.007
 prope-0.007
 Horse-0.007
 ears-0.006
Token
Token ID198
Feature activation-5.75e-01

Pos logit contributions
 Cle+0.040
 tail+0.037
 Horse+0.034
 ears+0.033
 no+0.032
Neg logit contributions
rig-0.097
pack-0.097
inner-0.096
washer-0.092
prise-0.090
TokenNow
Token ID3844
Feature activation-1.69e+00

Pos logit contributions
 Cle+0.014
 tail+0.014
 ears+0.013
 Horse+0.013
 prope+0.012
Neg logit contributions
rig-0.021
pack-0.021
inner-0.020
washer-0.019
prise-0.018
Token we
Token ID356
Feature activation-4.93e-01

Pos logit contributions
rig+0.067
pack+0.066
inner+0.065
washer+0.062
prise+0.059
Neg logit contributions
 Cle-0.059
 tail-0.058
 Horse-0.054
 prope-0.054
 ears-0.054
Token can
Token ID460
Feature activation-2.18e-02

Pos logit contributions
rig+0.023
pack+0.022
inner+0.022
washer+0.020
igsaw+0.020
Neg logit contributions
 Cle-0.014
 tail-0.014
 no-0.014
 ear-0.013
 prope-0.013
Token mix
Token ID5022
Feature activation-1.24e+00

Pos logit contributions
rig+0.001
inner+0.001
washer+0.001
pack+0.001
igsaw+0.001
Neg logit contributions
 no-0.001
 tail-0.001
 Cle-0.001
 ear-0.001
 ears-0.001
Token all
Token ID477
Feature activation-3.13e+00

Pos logit contributions
rig+0.071
pack+0.067
washer+0.064
inner+0.063
prise+0.063
Neg logit contributions
 no-0.023
 ears-0.022
 tail-0.020
 Cle-0.019
 Big-0.018
Token sorts
Token ID10524
Feature activation-6.29e+00

Pos logit contributions
rig+0.172
pack+0.160
prise+0.160
inner+0.155
washer+0.151
Neg logit contributions
 no-0.062
 tail-0.052
 ears-0.049
 Big-0.049
 ear-0.048
Token of
Token ID286
Feature activation-1.24e+00

Pos logit contributions
rig+0.319
pack+0.317
inner+0.291
washer+0.284
prise+0.275
Neg logit contributions
 no-0.148
 goodbye-0.142
 tail-0.138
 ear-0.136
 ears-0.135
Token cool
Token ID3608
Feature activation-3.14e+00

Pos logit contributions
rig+0.054
pack+0.053
inner+0.051
washer+0.049
prise+0.047
Neg logit contributions
 ears-0.038
 no-0.035
 tail-0.033
 prope-0.033
 ear-0.033
Token things
Token ID1243
Feature activation-1.38e+00

Pos logit contributions
rig+0.139
pack+0.131
inner+0.122
washer+0.121
prise+0.120
Neg logit contributions
 ears-0.099
 tail-0.095
 Cle-0.093
 Horse-0.088
 no-0.087
Token together
Token ID1978
Feature activation-1.24e+00

Pos logit contributions
rig+0.072
pack+0.067
inner+0.064
prise+0.064
igsaw+0.061
Neg logit contributions
 no-0.034
 tail-0.031
 goodbye-0.029
 ears-0.028
 ear-0.027
Token!"
Token ID2474
Feature activation+1.06e-01

Pos logit contributions
rig+0.056
pack+0.054
inner+0.053
washer+0.050
prise+0.049
Neg logit contributions
 tail-0.038
 Cle-0.036
 no-0.035
 ears-0.035
 Horse-0.034
Token mom
Token ID1995
Feature activation+3.14e-01

Pos logit contributions
 Cle+0.014
 tail+0.013
 prope+0.012
 Horse+0.012
Leave+0.011
Neg logit contributions
pack-0.037
rig-0.037
inner-0.036
washer-0.035
ade-0.033
Tokenmy
Token ID1820
Feature activation-3.04e-01

Pos logit contributions
 Cle+0.011
 tail+0.011
 Horse+0.010
 ears+0.010
 prope+0.010
Neg logit contributions
rig-0.013
pack-0.012
inner-0.012
washer-0.012
prise-0.011
Token picked
Token ID6497
Feature activation-1.28e+00

Pos logit contributions
rig+0.013
pack+0.013
inner+0.013
washer+0.012
prise+0.012
Neg logit contributions
 Cle-0.010
 tail-0.010
 Horse-0.009
 ears-0.009
 no-0.009
Token out
Token ID503
Feature activation-2.37e+00

Pos logit contributions
rig+0.048
pack+0.047
inner+0.046
washer+0.044
prise+0.042
Neg logit contributions
 Cle-0.049
 tail-0.047
 Horse-0.045
 ears-0.045
 ear-0.044
Token all
Token ID477
Feature activation-3.46e+00

Pos logit contributions
pack+0.094
rig+0.093
inner+0.093
washer+0.089
ade+0.086
Neg logit contributions
 Cle-0.082
 tail-0.077
 Horse-0.073
 prope-0.073
Leave-0.070
Token sorts
Token ID10524
Feature activation-6.22e+00

Pos logit contributions
rig+0.207
pack+0.201
inner+0.200
prise+0.197
washer+0.193
Neg logit contributions
 Cle-0.045
 ear-0.044
 goodbye-0.044
 tail-0.042
 no-0.041
Token of
Token ID286
Feature activation-1.24e+00

Pos logit contributions
pack+0.286
rig+0.285
inner+0.273
washer+0.259
prise+0.257
Neg logit contributions
 Cle-0.175
 tail-0.172
 goodbye-0.169
 ear-0.164
 no-0.164
Token delicious
Token ID12625
Feature activation-2.39e+00

Pos logit contributions
rig+0.056
inner+0.055
pack+0.055
washer+0.054
prise+0.051
Neg logit contributions
 ears-0.036
 Cle-0.035
 tail-0.034
 ear-0.033
 horns-0.033
Token foods
Token ID9013
Feature activation-4.08e-01

Pos logit contributions
rig+0.100
pack+0.096
inner+0.092
washer+0.091
prise+0.086
Neg logit contributions
 Cle-0.082
 tail-0.081
 ears-0.080
 Horse-0.076
joy-0.075
Token.
Token ID13
Feature activation-1.98e-01

Pos logit contributions
rig+0.023
pack+0.022
inner+0.022
prise+0.021
igsaw+0.020
Neg logit contributions
 no-0.008
 Cle-0.007
 tail-0.007
 goodbye-0.007
 ears-0.006
Token
Token ID198
Feature activation-1.51e-01

Pos logit contributions
rig+0.010
pack+0.010
inner+0.009
washer+0.009
ade+0.009
Neg logit contributions
 Cle-0.005
 tail-0.005
 prope-0.005
 Horse-0.005
 ears-0.005
Token a
Token ID257
Feature activation+2.18e-01

Pos logit contributions
 Cle+0.057
 tail+0.055
 Horse+0.051
 ears+0.050
 prope+0.050
Neg logit contributions
rig-0.095
pack-0.094
inner-0.092
washer-0.088
prise-0.085
Token hill
Token ID12788
Feature activation-2.49e+00

Pos logit contributions
 tail+0.008
 Cle+0.007
 no+0.007
 Horse+0.007
 prope+0.007
Neg logit contributions
pack-0.009
rig-0.009
inner-0.009
prise-0.008
washer-0.008
Token and
Token ID290
Feature activation-8.23e-01

Pos logit contributions
rig+0.117
pack+0.115
inner+0.114
prise+0.108
washer+0.107
Neg logit contributions
 tail-0.068
 Cle-0.068
 no-0.063
 Horse-0.061
 ears-0.061
Token liked
Token ID8288
Feature activation-5.38e-01

Pos logit contributions
pack+0.034
rig+0.034
inner+0.033
washer+0.033
ade+0.031
Neg logit contributions
 Cle-0.026
 tail-0.025
 Horse-0.024
 prope-0.024
 ears-0.023
Token all
Token ID477
Feature activation-2.64e+00

Pos logit contributions
rig+0.022
pack+0.022
inner+0.021
washer+0.020
prise+0.020
Neg logit contributions
 Cle-0.019
 tail-0.018
 Horse-0.017
 ears-0.017
 prope-0.017
Token sorts
Token ID10524
Feature activation-6.14e+00

Pos logit contributions
pack+0.136
inner+0.134
rig+0.134
prise+0.132
washer+0.126
Neg logit contributions
 tail-0.063
 Cle-0.061
 no-0.057
 Horse-0.057
 ears-0.057
Token of
Token ID286
Feature activation-1.26e+00

Pos logit contributions
pack+0.268
rig+0.268
inner+0.259
washer+0.246
prise+0.241
Neg logit contributions
 Cle-0.191
 tail-0.187
 no-0.175
 ears-0.174
 ear-0.173
Token y
Token ID331
Feature activation-1.97e+00

Pos logit contributions
inner+0.056
pack+0.056
rig+0.055
washer+0.054
prise+0.052
Neg logit contributions
 tail-0.040
 ears-0.038
 Cle-0.038
 ear-0.036
 horns-0.035
Tokenummy
Token ID13513
Feature activation-3.69e+00

Pos logit contributions
washer+0.082
rig+0.081
pack+0.080
inner+0.074
prise+0.071
Neg logit contributions
 ears-0.066
 tail-0.064
 Cle-0.063
ness-0.061
joy-0.060
Token food
Token ID2057
Feature activation-3.65e-01

Pos logit contributions
pack+0.154
rig+0.150
inner+0.144
washer+0.139
prise+0.132
Neg logit contributions
 tail-0.126
 ears-0.124
 Cle-0.123
 Horse-0.116
 horns-0.114
Token.
Token ID13
Feature activation-2.50e-01

Pos logit contributions
rig+0.020
pack+0.020
inner+0.020
prise+0.018
igsaw+0.018
Neg logit contributions
 tail-0.007
 Cle-0.007
 no-0.007
 ears-0.006
 goodbye-0.006
Tokenay
Token ID323
Feature activation-1.65e+00

Pos logit contributions
 Cle+0.052
 tail+0.052
 ears+0.048
 prope+0.047
 Horse+0.047
Neg logit contributions
rig-0.082
pack-0.080
inner-0.078
washer-0.075
prise-0.075
Tokenons
Token ID684
Feature activation+3.59e-01

Pos logit contributions
rig+0.053
inner+0.049
pack+0.049
washer+0.044
prise+0.041
Neg logit contributions
 Cle-0.071
 tail-0.071
 ears-0.068
 no-0.067
 Horse-0.067
Token to
Token ID284
Feature activation-5.94e-01

Pos logit contributions
 tail+0.009
 Cle+0.009
 no+0.009
 ears+0.008
 Horse+0.008
Neg logit contributions
rig-0.018
inner-0.018
pack-0.017
prise-0.016
washer-0.016
Token draw
Token ID3197
Feature activation+5.07e-01

Pos logit contributions
rig+0.024
inner+0.023
pack+0.022
washer+0.021
prise+0.020
Neg logit contributions
 Cle-0.021
 tail-0.021
 ears-0.020
 no-0.020
 ear-0.020
Token all
Token ID477
Feature activation-3.09e+00

Pos logit contributions
 Cle+0.016
 tail+0.015
 Horse+0.014
 ears+0.014
 prope+0.014
Neg logit contributions
rig-0.022
pack-0.022
inner-0.022
washer-0.021
ade-0.020
Token sorts
Token ID10524
Feature activation-6.13e+00

Pos logit contributions
rig+0.156
pack+0.152
inner+0.151
prise+0.144
washer+0.140
Neg logit contributions
 Cle-0.075
 tail-0.075
 ear-0.070
 no-0.070
 Horse-0.068
Token of
Token ID286
Feature activation-1.28e+00

Pos logit contributions
rig+0.276
pack+0.271
inner+0.264
prise+0.248
washer+0.245
Neg logit contributions
 Cle-0.177
 tail-0.177
 no-0.168
 ears-0.166
 ear-0.166
Token things
Token ID1243
Feature activation-1.20e+00

Pos logit contributions
rig+0.056
pack+0.055
inner+0.054
washer+0.051
prise+0.049
Neg logit contributions
 tail-0.040
 Cle-0.040
 ears-0.039
 ear-0.038
 prope-0.037
Token.
Token ID13
Feature activation+3.93e-02

Pos logit contributions
rig+0.067
inner+0.064
pack+0.064
prise+0.062
igsaw+0.058
Neg logit contributions
 no-0.024
 Cle-0.022
 tail-0.022
 ears-0.020
 goodbye-0.019
Token<|endoftext|>
Token ID50256
Feature activation-1.90e+00

Pos logit contributions
 Cle+0.001
 tail+0.001
 Horse+0.001
 ears+0.001
 no+0.001
Neg logit contributions
rig-0.002
pack-0.002
inner-0.002
washer-0.002
prise-0.002
TokenOnce
Token ID7454
Feature activation-3.58e-01

Pos logit contributions
pack+0.082
rig+0.080
inner+0.079
washer+0.075
ade+0.073
Neg logit contributions
 Cle-0.061
 prope-0.059
 tail-0.059
 ears-0.057
 ear-0.055
Token filled
Token ID5901
Feature activation-2.53e+00

Pos logit contributions
rig+0.206
pack+0.197
inner+0.195
prise+0.184
washer+0.182
Neg logit contributions
 tail-0.115
 Cle-0.110
 no-0.109
 ears-0.106
 goodbye-0.102
Token with
Token ID351
Feature activation-7.15e-01

Pos logit contributions
rig+0.123
inner+0.118
pack+0.117
washer+0.114
prise+0.113
Neg logit contributions
 tail-0.067
 Cle-0.064
 ears-0.061
 no-0.060
 ear-0.059
Token decorations
Token ID39011
Feature activation-9.84e-01

Pos logit contributions
rig+0.029
pack+0.028
inner+0.028
washer+0.027
prise+0.026
Neg logit contributions
 Cle-0.025
 tail-0.023
 Horse-0.023
 prope-0.022
 ears-0.021
Token and
Token ID290
Feature activation-6.60e-01

Pos logit contributions
rig+0.052
pack+0.051
inner+0.049
prise+0.047
washer+0.047
Neg logit contributions
 tail-0.022
 Cle-0.021
 no-0.020
 ears-0.020
 goodbye-0.019
Token all
Token ID477
Feature activation-2.60e+00

Pos logit contributions
rig+0.026
pack+0.026
inner+0.026
washer+0.024
prise+0.023
Neg logit contributions
 Cle-0.023
 tail-0.023
 Horse-0.021
 prope-0.021
 ears-0.021
Token sorts
Token ID10524
Feature activation-6.07e+00

Pos logit contributions
rig+0.133
pack+0.129
inner+0.127
prise+0.121
washer+0.115
Neg logit contributions
 tail-0.061
 no-0.060
 goodbye-0.058
 Cle-0.058
 ears-0.057
Token of
Token ID286
Feature activation-1.55e+00

Pos logit contributions
rig+0.271
pack+0.270
inner+0.259
washer+0.245
prise+0.242
Neg logit contributions
 Cle-0.178
 tail-0.175
 no-0.168
 goodbye-0.167
 ears-0.165
Token fun
Token ID1257
Feature activation-3.72e+00

Pos logit contributions
pack+0.060
rig+0.060
inner+0.060
washer+0.056
prise+0.053
Neg logit contributions
 tail-0.054
 ears-0.053
 Cle-0.052
 goodbye-0.051
 ear-0.051
Token toys
Token ID14958
Feature activation-1.32e-01

Pos logit contributions
rig+0.177
pack+0.169
inner+0.166
prise+0.157
washer+0.156
Neg logit contributions
 tail-0.100
 ears-0.097
 Cle-0.095
 no-0.089
joy-0.089
Token.
Token ID13
Feature activation-1.37e-01

Pos logit contributions
rig+0.007
inner+0.007
pack+0.007
prise+0.007
igsaw+0.006
Neg logit contributions
 tail-0.003
 Cle-0.003
 no-0.003
 ears-0.002
 goodbye-0.002
Token
Token ID198
Feature activation+4.40e-01

Pos logit contributions
rig+0.007
pack+0.007
inner+0.006
washer+0.006
prise+0.006
Neg logit contributions
 Cle-0.004
 tail-0.003
 prope-0.003
 ears-0.003
 Horse-0.003
Tokenauldron
Token ID45637
Feature activation-3.97e+00

Pos logit contributions
rig+0.154
inner+0.147
igsaw+0.142
prise+0.136
ade+0.132
Neg logit contributions
 no-0.070
 Cle-0.059
 tail-0.054
 owners-0.054
 goodbye-0.053
Token where
Token ID810
Feature activation-3.14e+00

Pos logit contributions
rig+0.186
pack+0.184
inner+0.181
washer+0.172
prise+0.168
Neg logit contributions
 Cle-0.111
 tail-0.108
 ears-0.100
 Horse-0.099
 no-0.098
Token she
Token ID673
Feature activation-7.79e-01

Pos logit contributions
rig+0.155
pack+0.152
inner+0.148
washer+0.139
prise+0.136
Neg logit contributions
 Cle-0.085
 tail-0.082
 no-0.078
 ears-0.076
 Horse-0.074
Token mixed
Token ID7668
Feature activation-1.36e+00

Pos logit contributions
rig+0.039
pack+0.038
inner+0.038
igsaw+0.035
washer+0.035
Neg logit contributions
 tail-0.019
 Cle-0.019
 no-0.019
 ears-0.018
 ear-0.018
Token all
Token ID477
Feature activation-2.95e+00

Pos logit contributions
rig+0.077
pack+0.072
inner+0.071
washer+0.070
prise+0.069
Neg logit contributions
 no-0.026
 Cle-0.026
 tail-0.026
 ears-0.025
 ear-0.023
Token sorts
Token ID10524
Feature activation-6.05e+00

Pos logit contributions
rig+0.159
pack+0.153
inner+0.149
prise+0.145
washer+0.144
Neg logit contributions
 no-0.063
 tail-0.059
 Cle-0.058
 ear-0.055
 goodbye-0.054
Token of
Token ID286
Feature activation-1.65e+00

Pos logit contributions
rig+0.285
pack+0.284
inner+0.270
washer+0.258
prise+0.253
Neg logit contributions
 Cle-0.160
 tail-0.158
 no-0.158
 goodbye-0.152
 ears-0.150
Token things
Token ID1243
Feature activation-1.62e+00

Pos logit contributions
rig+0.068
pack+0.068
inner+0.067
washer+0.064
prise+0.060
Neg logit contributions
 tail-0.053
 ears-0.053
 Cle-0.052
 no-0.051
 ear-0.050
Token together
Token ID1978
Feature activation-1.43e+00

Pos logit contributions
rig+0.091
pack+0.086
inner+0.085
prise+0.082
washer+0.078
Neg logit contributions
 no-0.034
 Cle-0.028
 tail-0.027
 goodbye-0.026
 ears-0.025
Token.
Token ID13
Feature activation-4.99e-01

Pos logit contributions
rig+0.077
pack+0.073
inner+0.073
washer+0.069
prise+0.069
Neg logit contributions
 tail-0.031
 no-0.031
 Cle-0.030
 ears-0.028
 ear-0.027
Token One
Token ID1881
Feature activation+1.00e-01

Pos logit contributions
rig+0.024
pack+0.024
inner+0.024
washer+0.023
prise+0.022
Neg logit contributions
 Cle-0.013
 tail-0.013
 prope-0.012
 ears-0.011
 Horse-0.011
Token happy
Token ID3772
Feature activation-1.74e+00

Pos logit contributions
rig+0.154
pack+0.152
inner+0.150
washer+0.143
prise+0.138
Neg logit contributions
 Cle-0.110
 tail-0.106
 ears-0.099
 Horse-0.098
 prope-0.097
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
rig+0.076
pack+0.075
inner+0.074
washer+0.070
prise+0.068
Neg logit contributions
 Cle-0.055
 tail-0.053
 Horse-0.049
 ears-0.049
 prope-0.049
Token She
Token ID1375
Feature activation-4.40e-01

Pos logit contributions
rig+0.060
pack+0.058
inner+0.057
washer+0.056
prise+0.053
Neg logit contributions
 Cle-0.035
 tail-0.034
 prope-0.033
 ears-0.032
 Horse-0.031
Token saw
Token ID2497
Feature activation-1.02e+00

Pos logit contributions
rig+0.020
pack+0.020
inner+0.020
washer+0.019
prise+0.018
Neg logit contributions
 Cle-0.013
 tail-0.012
 ears-0.011
 Horse-0.011
 prope-0.011
Token all
Token ID477
Feature activation-2.54e+00

Pos logit contributions
rig+0.040
pack+0.039
inner+0.039
washer+0.038
ade+0.036
Neg logit contributions
 Cle-0.035
 tail-0.034
 Horse-0.032
 prope-0.031
 ears-0.031
Token sorts
Token ID10524
Feature activation-6.03e+00

Pos logit contributions
pack+0.123
rig+0.122
inner+0.122
prise+0.116
washer+0.113
Neg logit contributions
 tail-0.068
 Cle-0.067
 ear-0.063
 ears-0.063
 no-0.062
Token of
Token ID286
Feature activation-1.17e+00

Pos logit contributions
rig+0.256
pack+0.256
inner+0.249
washer+0.235
prise+0.228
Neg logit contributions
 Cle-0.195
 tail-0.191
 ears-0.179
 no-0.178
 prope-0.176
Token creatures
Token ID8109
Feature activation-9.35e-02

Pos logit contributions
pack+0.048
rig+0.048
inner+0.047
washer+0.045
prise+0.043
Neg logit contributions
 Cle-0.039
 tail-0.039
 ears-0.037
 Horse-0.036
 ear-0.036
Token,
Token ID11
Feature activation+2.09e-01

Pos logit contributions
rig+0.005
pack+0.005
inner+0.005
washer+0.004
prise+0.004
Neg logit contributions
 tail-0.002
 Cle-0.002
 ears-0.002
 no-0.002
 Horse-0.002
Token and
Token ID290
Feature activation-1.92e-01

Pos logit contributions
 Cle+0.007
 tail+0.006
 Horse+0.006
 prope+0.006
 ear+0.006
Neg logit contributions
rig-0.009
pack-0.009
inner-0.008
washer-0.008
ade-0.008
Token played
Token ID2826
Feature activation+1.50e+00

Pos logit contributions
rig+0.007
washer+0.007
pack+0.007
 else+0.007
inner+0.007
Neg logit contributions
 Cle-0.006
 tail-0.006
 Horse-0.006
 prope-0.006
joy-0.006
Token street
Token ID4675
Feature activation-3.69e+00

Pos logit contributions
rig+0.058
pack+0.057
inner+0.056
washer+0.052
prise+0.051
Neg logit contributions
 Cle-0.053
 tail-0.053
 ears-0.049
 Horse-0.049
 prope-0.049
Token.
Token ID13
Feature activation-1.12e+00

Pos logit contributions
rig+0.166
pack+0.166
inner+0.162
washer+0.157
ade+0.149
Neg logit contributions
 Cle-0.111
 tail-0.104
 Horse-0.100
 prope-0.097
 ears-0.096
Token Tom
Token ID4186
Feature activation-9.99e-01

Pos logit contributions
rig+0.051
pack+0.049
inner+0.049
washer+0.047
igsaw+0.044
Neg logit contributions
 tail-0.030
 Cle-0.030
 prope-0.030
 ears-0.028
 Horse-0.028
Token saw
Token ID2497
Feature activation-1.51e+00

Pos logit contributions
rig+0.047
pack+0.047
inner+0.047
washer+0.044
prise+0.043
Neg logit contributions
 Cle-0.027
 tail-0.027
 ears-0.025
 Horse-0.024
 no-0.024
Token all
Token ID477
Feature activation-2.69e+00

Pos logit contributions
rig+0.065
pack+0.064
inner+0.063
washer+0.061
ade+0.058
Neg logit contributions
 Cle-0.048
 tail-0.047
 Horse-0.044
 prope-0.043
 ears-0.043
Token sorts
Token ID10524
Feature activation-6.03e+00

Pos logit contributions
inner+0.145
pack+0.145
prise+0.144
rig+0.144
washer+0.134
Neg logit contributions
 tail-0.056
 Cle-0.055
 ear-0.050
 ears-0.050
 no-0.049
Token of
Token ID286
Feature activation-1.18e+00

Pos logit contributions
pack+0.265
rig+0.265
inner+0.257
washer+0.240
prise+0.239
Neg logit contributions
 Cle-0.186
 tail-0.182
 no-0.171
 ears-0.170
 ear-0.167
Token things
Token ID1243
Feature activation-1.27e+00

Pos logit contributions
pack+0.050
inner+0.050
rig+0.050
washer+0.047
prise+0.046
Neg logit contributions
 Cle-0.038
 tail-0.038
 ears-0.036
 ear-0.034
 horns-0.034
Token as
Token ID355
Feature activation-1.61e+00

Pos logit contributions
rig+0.070
inner+0.068
pack+0.067
prise+0.065
igsaw+0.062
Neg logit contributions
 no-0.027
 Cle-0.025
 tail-0.024
 ears-0.022
 goodbye-0.022
Token they
Token ID484
Feature activation-6.34e-01

Pos logit contributions
rig+0.070
pack+0.069
inner+0.069
washer+0.066
ade+0.063
Neg logit contributions
 Cle-0.050
 tail-0.048
 Horse-0.045
 ears-0.045
 prope-0.045
Token drove
Token ID10357
Feature activation+2.18e-01

Pos logit contributions
pack+0.027
rig+0.027
inner+0.026
washer+0.026
prise+0.024
Neg logit contributions
 Cle-0.020
 tail-0.020
 Horse-0.019
 prope-0.018
 ears-0.018
Token<|endoftext|>
Token ID50256
Feature activation-2.06e+00

Pos logit contributions
 Cle+0.005
 tail+0.005
 prope+0.005
 Horse+0.005
 ears+0.005
Neg logit contributions
rig-0.007
pack-0.007
inner-0.007
washer-0.007
igsaw-0.006
TokenBilly
Token ID49640
Feature activation+4.93e-01

Pos logit contributions
pack+0.067
inner+0.066
rig+0.063
washer+0.061
ade+0.058
Neg logit contributions
 prope-0.087
 Cle-0.086
 tail-0.086
 ears-0.083
 ear-0.080
Token was
Token ID373
Feature activation-7.20e-02

Pos logit contributions
 Cle+0.014
 tail+0.013
 Horse+0.012
 ears+0.012
 ear+0.012
Neg logit contributions
rig-0.023
pack-0.023
inner-0.023
washer-0.022
prise-0.021
Token learning
Token ID4673
Feature activation-5.26e-01

Pos logit contributions
rig+0.003
inner+0.003
pack+0.003
washer+0.003
prise+0.003
Neg logit contributions
 Cle-0.002
 tail-0.002
 ears-0.002
 Horse-0.002
 no-0.002
Token all
Token ID477
Feature activation-3.70e+00

Pos logit contributions
rig+0.022
pack+0.022
inner+0.022
washer+0.020
prise+0.020
Neg logit contributions
 Cle-0.017
 tail-0.017
 no-0.016
 ears-0.016
 Horse-0.016
Token sorts
Token ID10524
Feature activation-6.03e+00

Pos logit contributions
rig+0.169
pack+0.166
inner+0.165
prise+0.165
washer+0.152
Neg logit contributions
 tail-0.106
 Cle-0.101
 ear-0.099
 no-0.099
 goodbye-0.097
Token of
Token ID286
Feature activation-1.30e+00

Pos logit contributions
rig+0.274
pack+0.274
inner+0.265
prise+0.250
washer+0.248
Neg logit contributions
 Cle-0.172
 tail-0.168
 no-0.164
 goodbye-0.162
 ear-0.157
Token new
Token ID649
Feature activation-1.83e+00

Pos logit contributions
inner+0.052
rig+0.051
pack+0.051
washer+0.050
prise+0.047
Neg logit contributions
 tail-0.046
 Cle-0.044
 ears-0.044
 ear-0.042
joy-0.041
Token things
Token ID1243
Feature activation-1.45e+00

Pos logit contributions
rig+0.072
pack+0.071
inner+0.069
washer+0.066
ade+0.064
Neg logit contributions
 Cle-0.065
 tail-0.063
 Horse-0.060
 prope-0.059
 no-0.058
Token,
Token ID11
Feature activation-1.52e-03

Pos logit contributions
rig+0.080
pack+0.078
inner+0.078
prise+0.075
washer+0.071
Neg logit contributions
 Cle-0.028
 no-0.028
 tail-0.026
 goodbye-0.024
 Horse-0.023
Token but
Token ID475
Feature activation+7.92e-01

Pos logit contributions
rig+0.000
pack+0.000
inner+0.000
washer+0.000
prise+0.000
Neg logit contributions
 Cle-0.000
 tail-0.000
 Horse-0.000
 ears-0.000
 prope-0.000
Token mom
Token ID1995
Feature activation+5.21e-01

Pos logit contributions
 Cle+0.017
 tail+0.016
 prope+0.015
 Horse+0.014
Leave+0.014
Neg logit contributions
rig-0.046
pack-0.046
inner-0.045
washer-0.044
ade-0.042
Tokenmy
Token ID1820
Feature activation-9.36e-02

Pos logit contributions
 Cle+0.018
 tail+0.017
 Horse+0.016
 ears+0.016
 prope+0.016
Neg logit contributions
rig-0.021
pack-0.021
inner-0.021
washer-0.019
prise-0.019
Token picked
Token ID6497
Feature activation-9.61e-01

Pos logit contributions
rig+0.004
inner+0.004
pack+0.004
washer+0.004
prise+0.004
Neg logit contributions
 Cle-0.003
 tail-0.003
 Horse-0.003
 ears-0.003
 no-0.003
Token out
Token ID503
Feature activation-2.07e+00

Pos logit contributions
rig+0.036
pack+0.035
inner+0.034
washer+0.033
prise+0.031
Neg logit contributions
 Cle-0.037
 tail-0.036
 Horse-0.034
 ears-0.034
 prope-0.033
Token all
Token ID477
Feature activation-3.23e+00

Pos logit contributions
rig+0.081
pack+0.081
inner+0.081
washer+0.077
ade+0.074
Neg logit contributions
 Cle-0.072
 tail-0.067
 Horse-0.063
 prope-0.063
Leave-0.062
Token sorts
Token ID10524
Feature activation-5.95e+00

Pos logit contributions
rig+0.194
pack+0.188
inner+0.187
prise+0.185
washer+0.180
Neg logit contributions
 Cle-0.042
 ear-0.041
 goodbye-0.040
 tail-0.039
 no-0.038
Token of
Token ID286
Feature activation-1.02e+00

Pos logit contributions
pack+0.273
rig+0.272
inner+0.261
washer+0.248
prise+0.246
Neg logit contributions
 Cle-0.168
 tail-0.165
 goodbye-0.162
 ear-0.157
 ears-0.157
Token delicious
Token ID12625
Feature activation-2.09e+00

Pos logit contributions
rig+0.045
inner+0.045
pack+0.045
washer+0.044
prise+0.042
Neg logit contributions
 ears-0.030
 Cle-0.030
 tail-0.029
 ear-0.028
 horns-0.027
Token foods
Token ID9013
Feature activation-1.21e-01

Pos logit contributions
rig+0.087
pack+0.084
inner+0.081
washer+0.079
prise+0.075
Neg logit contributions
 Cle-0.073
 tail-0.071
 ears-0.071
 Horse-0.067
 horns-0.066
Token.
Token ID13
Feature activation-3.86e-02

Pos logit contributions
rig+0.007
pack+0.007
inner+0.006
prise+0.006
igsaw+0.006
Neg logit contributions
 no-0.002
 Cle-0.002
 tail-0.002
 goodbye-0.002
 ears-0.002
Token
Token ID198
Feature activation+1.05e-01

Pos logit contributions
rig+0.002
pack+0.002
inner+0.002
washer+0.002
ade+0.002
Neg logit contributions
 Cle-0.001
 tail-0.001
 prope-0.001
 Horse-0.001
 ears-0.001
Token She
Token ID1375
Feature activation-1.64e-01

Pos logit contributions
rig+0.007
pack+0.007
inner+0.007
washer+0.006
prise+0.006
Neg logit contributions
 Cle-0.004
 tail-0.004
 Horse-0.003
 ears-0.003
 prope-0.003
Token learned
Token ID4499
Feature activation+4.54e-01

Pos logit contributions
rig+0.007
inner+0.007
pack+0.007
washer+0.006
prise+0.006
Neg logit contributions
 Cle-0.005
 tail-0.005
 ears-0.005
 no-0.005
 Horse-0.005
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
 Cle+0.018
 tail+0.017
 ears+0.016
 Horse+0.016
 prope+0.016
Neg logit contributions
rig-0.016
pack-0.016
inner-0.016
washer-0.015
prise-0.014
Token sign
Token ID1051
Feature activation-2.82e+00

Pos logit contributions
rig+0.064
pack+0.063
inner+0.062
washer+0.058
prise+0.057
Neg logit contributions
 Cle-0.051
 tail-0.050
 Horse-0.047
 ears-0.046
 prope-0.046
Token all
Token ID477
Feature activation-3.29e+00

Pos logit contributions
rig+0.115
pack+0.113
inner+0.111
washer+0.105
ade+0.101
Neg logit contributions
 Cle-0.096
 tail-0.093
 Horse-0.088
 prope-0.086
 ears-0.086
Token sorts
Token ID10524
Feature activation-5.94e+00

Pos logit contributions
pack+0.145
rig+0.144
inner+0.144
washer+0.137
prise+0.135
Neg logit contributions
 Cle-0.101
 tail-0.100
 ears-0.093
 ear-0.092
 Horse-0.092
Token of
Token ID286
Feature activation-1.02e+00

Pos logit contributions
rig+0.253
pack+0.252
inner+0.246
washer+0.233
prise+0.228
Neg logit contributions
 Cle-0.190
 tail-0.186
 ears-0.175
 no-0.174
 ear-0.172
Token words
Token ID2456
Feature activation+6.56e-01

Pos logit contributions
rig+0.045
pack+0.044
inner+0.044
washer+0.042
prise+0.040
Neg logit contributions
 Cle-0.032
 tail-0.031
 Horse-0.029
 ears-0.029
 prope-0.028
Token,
Token ID11
Feature activation+4.95e-02

Pos logit contributions
 Cle+0.019
 tail+0.018
 Horse+0.017
 ears+0.017
 prope+0.017
Neg logit contributions
rig-0.030
pack-0.030
inner-0.030
washer-0.028
prise-0.027
Token including
Token ID1390
Feature activation-1.21e+00

Pos logit contributions
 Cle+0.002
 tail+0.001
 Horse+0.001
 prope+0.001
 ear+0.001
Neg logit contributions
rig-0.002
pack-0.002
inner-0.002
washer-0.002
ade-0.002
Token the
Token ID262
Feature activation+9.65e-02

Pos logit contributions
rig+0.051
pack+0.051
inner+0.050
washer+0.048
prise+0.046
Neg logit contributions
 Cle-0.038
 tail-0.037
 Horse-0.035
 prope-0.034
 ears-0.034
Token and
Token ID290
Feature activation+2.27e-01

Pos logit contributions
 Cle+0.069
 tail+0.067
 Horse+0.062
 ears+0.062
 prope+0.062
Neg logit contributions
rig-0.095
pack-0.094
inner-0.092
washer-0.088
prise-0.085
Token she
Token ID673
Feature activation+1.03e+00

Pos logit contributions
 Cle+0.008
 tail+0.007
 prope+0.007
 Horse+0.007
 ears+0.007
Neg logit contributions
rig-0.009
pack-0.009
inner-0.009
washer-0.009
prise-0.008
Token taught
Token ID7817
Feature activation+1.42e+00

Pos logit contributions
 Cle+0.029
 tail+0.028
 Horse+0.025
 ears+0.025
 no+0.025
Neg logit contributions
rig-0.049
inner-0.048
pack-0.048
washer-0.045
prise-0.045
Token Clara
Token ID27443
Feature activation-3.01e+00

Pos logit contributions
 Cle+0.047
 tail+0.046
 prope+0.045
 Horse+0.043
 ears+0.041
Neg logit contributions
rig-0.059
inner-0.057
pack-0.057
off-0.053
prise-0.052
Token all
Token ID477
Feature activation-4.08e+00

Pos logit contributions
rig+0.130
pack+0.128
inner+0.127
washer+0.120
prise+0.116
Neg logit contributions
 Cle-0.096
 tail-0.093
 ears-0.087
 Horse-0.087
 prope-0.085
Token sorts
Token ID10524
Feature activation-5.93e+00

Pos logit contributions
rig+0.162
pack+0.162
inner+0.158
washer+0.151
prise+0.146
Neg logit contributions
 Cle-0.142
 tail-0.141
 ears-0.132
 Horse-0.131
 ear-0.130
Token of
Token ID286
Feature activation-8.95e-01

Pos logit contributions
pack+0.264
rig+0.264
inner+0.255
washer+0.241
prise+0.236
Neg logit contributions
 Cle-0.175
 tail-0.173
 no-0.164
 goodbye-0.164
 ear-0.163
Token things
Token ID1243
Feature activation-1.50e+00

Pos logit contributions
rig+0.038
pack+0.038
inner+0.038
washer+0.036
prise+0.034
Neg logit contributions
 tail-0.028
 Cle-0.028
 ears-0.027
 ear-0.026
 Horse-0.026
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
rig+0.083
inner+0.082
pack+0.081
prise+0.077
washer+0.075
Neg logit contributions
 no-0.028
 goodbye-0.026
 tail-0.025
 Cle-0.025
 ears-0.023
Token She
Token ID1375
Feature activation-6.19e-02

Pos logit contributions
rig+0.020
pack+0.019
inner+0.019
washer+0.018
prise+0.018
Neg logit contributions
 Cle-0.012
 tail-0.011
 prope-0.011
 Horse-0.010
 ears-0.010
Token told
Token ID1297
Feature activation+3.20e-01

Pos logit contributions
rig+0.003
inner+0.003
pack+0.003
prise+0.003
washer+0.003
Neg logit contributions
 Cle-0.002
 tail-0.002
 no-0.002
 Horse-0.002
 ears-0.002
Token used
Token ID973
Feature activation-1.81e-01

Pos logit contributions
pack+0.003
washer+0.003
inner+0.003
ade+0.003
 else+0.003
Neg logit contributions
 Horse-0.003
 Cle-0.003
joy-0.003
 tail-0.003
 prope-0.003
Token them
Token ID606
Feature activation-2.49e-01

Pos logit contributions
rig+0.008
pack+0.008
inner+0.008
washer+0.008
prise+0.007
Neg logit contributions
 Cle-0.005
 tail-0.005
 Horse-0.005
 ears-0.005
 prope-0.005
Token to
Token ID284
Feature activation-7.13e-01

Pos logit contributions
rig+0.011
inner+0.010
pack+0.010
washer+0.010
prise+0.010
Neg logit contributions
 Cle-0.008
 tail-0.008
 ears-0.008
 no-0.007
 ear-0.007
Token draw
Token ID3197
Feature activation+6.92e-01

Pos logit contributions
rig+0.029
inner+0.028
pack+0.028
washer+0.027
prise+0.025
Neg logit contributions
 Cle-0.025
 tail-0.025
 ears-0.023
 no-0.023
 prope-0.023
Token all
Token ID477
Feature activation-2.94e+00

Pos logit contributions
 Cle+0.024
 tail+0.022
 Horse+0.022
 prope+0.021
 ear+0.021
Neg logit contributions
pack-0.028
rig-0.028
inner-0.027
washer-0.026
ade-0.026
Token sorts
Token ID10524
Feature activation-5.92e+00

Pos logit contributions
rig+0.143
inner+0.140
pack+0.139
prise+0.135
washer+0.133
Neg logit contributions
 tail-0.077
 Cle-0.073
 ear-0.072
 no-0.071
 ears-0.068
Token of
Token ID286
Feature activation-1.05e+00

Pos logit contributions
rig+0.279
pack+0.275
inner+0.266
washer+0.252
prise+0.250
Neg logit contributions
 tail-0.160
 Cle-0.157
 no-0.153
 ear-0.151
 ears-0.149
Token amazing
Token ID4998
Feature activation-3.56e+00

Pos logit contributions
rig+0.047
pack+0.047
inner+0.047
washer+0.044
prise+0.042
Neg logit contributions
 tail-0.031
 Cle-0.031
 ears-0.030
 ear-0.029
 prope-0.028
Token pictures
Token ID5986
Feature activation-3.51e-01

Pos logit contributions
rig+0.140
pack+0.139
inner+0.136
washer+0.129
ade+0.126
Neg logit contributions
 Cle-0.127
 tail-0.121
 Horse-0.116
 prope-0.113
 no-0.113
Token.
Token ID13
Feature activation+1.28e-01

Pos logit contributions
rig+0.019
pack+0.018
inner+0.018
prise+0.017
washer+0.017
Neg logit contributions
 tail-0.007
 Cle-0.007
 no-0.007
 ears-0.007
 ear-0.007
Token But
Token ID887
Feature activation+1.15e+00

Pos logit contributions
 prope+0.004
 tail+0.004
 Cle+0.004
 Horse+0.004
Leave+0.004
Neg logit contributions
pack-0.005
rig-0.005
inner-0.005
washer-0.005
off-0.005
Token.
Token ID13
Feature activation+4.76e-02

Pos logit contributions
rig+0.048
inner+0.047
pack+0.046
prise+0.044
washer+0.043
Neg logit contributions
 Cle-0.028
 tail-0.028
 no-0.025
 ears-0.025
 Horse-0.025
Token She
Token ID1375
Feature activation-1.89e-02

Pos logit contributions
 Cle+0.001
 tail+0.001
joy+0.001
 ear+0.001
 No+0.001
Neg logit contributions
rig-0.003
pack-0.003
prise-0.003
inner-0.003
washer-0.003
Token tried
Token ID3088
Feature activation-2.03e-01

Pos logit contributions
rig+0.001
inner+0.001
pack+0.001
igsaw+0.001
prise+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 ears-0.001
 no-0.001
 ear-0.001
Token using
Token ID1262
Feature activation-8.58e-01

Pos logit contributions
pack+0.008
rig+0.007
inner+0.007
washer+0.007
ade+0.007
Neg logit contributions
 Cle-0.008
 tail-0.007
 Horse-0.007
 prope-0.007
Leave-0.007
Token all
Token ID477
Feature activation-3.42e+00

Pos logit contributions
rig+0.044
pack+0.043
inner+0.043
washer+0.041
prise+0.040
Neg logit contributions
 Cle-0.021
 tail-0.021
 ears-0.019
 Horse-0.018
 no-0.018
Token sorts
Token ID10524
Feature activation-5.92e+00

Pos logit contributions
rig+0.164
inner+0.160
pack+0.159
prise+0.153
washer+0.152
Neg logit contributions
 Cle-0.092
 tail-0.091
 no-0.087
 ear-0.086
 ears-0.085
Token of
Token ID286
Feature activation-1.00e+00

Pos logit contributions
pack+0.264
rig+0.263
inner+0.256
washer+0.247
prise+0.238
Neg logit contributions
 Cle-0.176
 tail-0.174
 no-0.164
 ears-0.163
 ear-0.162
Token measures
Token ID5260
Feature activation+3.64e-01

Pos logit contributions
inner+0.043
rig+0.043
pack+0.042
washer+0.041
prise+0.038
Neg logit contributions
 Cle-0.032
 tail-0.032
 ears-0.031
 ear-0.030
 prope-0.029
Token -
Token ID532
Feature activation-1.46e+00

Pos logit contributions
 Cle+0.010
 tail+0.010
 ears+0.009
 no+0.009
 Horse+0.009
Neg logit contributions
rig-0.018
pack-0.017
inner-0.017
washer-0.016
prise-0.016
Token a
Token ID257
Feature activation+7.45e-01

Pos logit contributions
pack+0.061
rig+0.060
inner+0.059
washer+0.057
ade+0.053
Neg logit contributions
 Cle-0.047
 tail-0.045
 Horse-0.043
 prope-0.041
 ears-0.041
Token ruler
Token ID22740
Feature activation+2.33e+00

Pos logit contributions
 Cle+0.028
 tail+0.027
 Horse+0.026
 ears+0.026
 prope+0.025
Neg logit contributions
rig-0.027
pack-0.027
inner-0.026
washer-0.025
prise-0.024
Token replied
Token ID8712
Feature activation-3.21e-01

Pos logit contributions
rig+0.002
pack+0.002
inner+0.002
washer+0.002
prise+0.002
Neg logit contributions
 Cle-0.002
 tail-0.002
 prope-0.002
 Horse-0.002
 ears-0.002
Token,
Token ID11
Feature activation-1.10e+00

Pos logit contributions
inner+0.013
pack+0.013
washer+0.013
rig+0.013
ade+0.012
Neg logit contributions
 Cle-0.011
 tail-0.010
 Horse-0.010
 prope-0.010
Leave-0.009
Token "
Token ID366
Feature activation+5.04e-01

Pos logit contributions
pack+0.045
washer+0.044
inner+0.043
rig+0.041
 cream+0.038
Neg logit contributions
 prope-0.033
 Cle-0.033
 Horse-0.031
Leave-0.030
 tail-0.030
TokenThat
Token ID2504
Feature activation-1.27e+00

Pos logit contributions
 Cle+0.013
 tail+0.013
 Horse+0.012
 ears+0.012
 no+0.011
Neg logit contributions
rig-0.025
pack-0.024
inner-0.024
washer-0.023
prise-0.022
Token's
Token ID338
Feature activation-7.97e-01

Pos logit contributions
rig+0.053
pack+0.052
inner+0.050
prise+0.048
washer+0.047
Neg logit contributions
 Cle-0.043
 tail-0.043
 ears-0.041
 no-0.040
 Horse-0.040
Token okay
Token ID8788
Feature activation+3.77e+00

Pos logit contributions
pack+0.041
rig+0.041
inner+0.040
washer+0.039
off+0.037
Neg logit contributions
 Cle-0.021
 tail-0.020
 no-0.020
 ears-0.018
 ear-0.017
Token,
Token ID11
Feature activation+8.05e-02

Pos logit contributions
 Cle+0.117
 tail+0.114
 prope+0.112
 Horse+0.108
 ear+0.103
Neg logit contributions
pack-0.158
rig-0.158
inner-0.156
washer-0.151
prise-0.148
Token Tim
Token ID5045
Feature activation-1.39e+00

Pos logit contributions
 Cle+0.002
 tail+0.002
 ears+0.002
 no+0.002
 Horse+0.002
Neg logit contributions
rig-0.004
pack-0.004
inner-0.004
washer-0.003
prise-0.003
Tokenmy
Token ID1820
Feature activation+1.12e+00

Pos logit contributions
pack+0.046
rig+0.046
inner+0.044
washer+0.044
ade+0.041
Neg logit contributions
 Cle-0.058
 tail-0.056
 prope-0.055
 Horse-0.053
 ears-0.053
Token.
Token ID13
Feature activation-3.62e-01

Pos logit contributions
 prope+0.044
 Cle+0.044
Leave+0.042
 tail+0.041
 Horse+0.040
Neg logit contributions
pack-0.038
washer-0.037
rig-0.037
inner-0.036
ade-0.034
Token You
Token ID921
Feature activation-4.51e-02

Pos logit contributions
inner+0.014
rig+0.014
pack+0.014
washer+0.014
off+0.013
Neg logit contributions
 tail-0.012
 Cle-0.012
joy-0.011
 prope-0.011
 ears-0.011
Token,
Token ID11
Feature activation+4.67e-01

Pos logit contributions
 tail+0.037
 Cle+0.037
 ears+0.034
 Horse+0.033
 no+0.033
Neg logit contributions
rig-0.078
pack-0.075
inner-0.075
prise-0.070
washer-0.070
Token or
Token ID393
Feature activation+2.41e+00

Pos logit contributions
 Cle+0.015
 tail+0.014
 Horse+0.014
 prope+0.013
 ear+0.013
Neg logit contributions
rig-0.020
pack-0.019
inner-0.019
washer-0.019
prise-0.018
Token princess
Token ID21752
Feature activation+3.14e+00

Pos logit contributions
 Cle+0.081
 tail+0.074
 Horse+0.073
joy+0.070
 prope+0.069
Neg logit contributions
pack-0.097
rig-0.095
washer-0.095
inner-0.093
prise-0.090
Tokenes
Token ID274
Feature activation+2.80e+00

Pos logit contributions
 Cle+0.089
 tail+0.081
 prope+0.080
joy+0.075
 Horse+0.074
Neg logit contributions
pack-0.144
rig-0.143
inner-0.142
washer-0.140
ade-0.132
Token,
Token ID11
Feature activation+3.91e-01

Pos logit contributions
 Cle+0.085
 tail+0.081
 prope+0.077
 Horse+0.075
 ears+0.075
Neg logit contributions
rig-0.123
pack-0.123
inner-0.121
washer-0.116
ade-0.112
Token or
Token ID393
Feature activation+2.52e+00

Pos logit contributions
 Cle+0.012
 tail+0.011
 Horse+0.011
 prope+0.011
 ear+0.010
Neg logit contributions
rig-0.017
pack-0.017
inner-0.017
washer-0.016
prise-0.015
Token cars
Token ID5006
Feature activation+2.31e+00

Pos logit contributions
 Cle+0.083
 tail+0.077
 Horse+0.074
 prope+0.071
joy+0.071
Neg logit contributions
pack-0.103
rig-0.102
washer-0.101
inner-0.100
prise-0.096
Token.
Token ID13
Feature activation-1.31e-01

Pos logit contributions
 tail+0.057
 Cle+0.057
 ears+0.052
 Horse+0.051
 no+0.051
Neg logit contributions
rig-0.118
pack-0.114
inner-0.112
washer-0.106
prise-0.106
Token They
Token ID1119
Feature activation-3.87e-02

Pos logit contributions
rig+0.006
pack+0.006
inner+0.006
washer+0.006
ade+0.005
Neg logit contributions
 Cle-0.004
 tail-0.004
 prope-0.003
 Horse-0.003
 ears-0.003
Token have
Token ID423
Feature activation-2.49e-01

Pos logit contributions
rig+0.002
pack+0.002
inner+0.002
washer+0.001
prise+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 ears-0.001
 Horse-0.001
 prope-0.001
Token a
Token ID257
Feature activation+1.37e-01

Pos logit contributions
rig+0.008
pack+0.008
inner+0.008
washer+0.008
prise+0.007
Neg logit contributions
 Cle-0.011
 tail-0.010
 Horse-0.010
 ears-0.010
 prope-0.010
Token He
Token ID679
Feature activation+8.22e-01

Pos logit contributions
 Cle+0.004
 tail+0.004
 prope+0.004
 ears+0.004
 Horse+0.004
Neg logit contributions
rig-0.008
pack-0.008
inner-0.008
washer-0.008
ade-0.008
Token grabbed
Token ID13176
Feature activation-8.20e-01

Pos logit contributions
 Cle+0.025
 tail+0.024
 Horse+0.023
 prope+0.022
 ears+0.022
Neg logit contributions
rig-0.037
pack-0.036
inner-0.035
washer-0.034
prise-0.033
Token it
Token ID340
Feature activation+4.29e-01

Pos logit contributions
rig+0.041
pack+0.041
inner+0.040
washer+0.038
prise+0.037
Neg logit contributions
 Cle-0.021
 tail-0.020
 Horse-0.018
 ears-0.018
 prope-0.018
Token with
Token ID351
Feature activation-3.05e-01

Pos logit contributions
 tail+0.008
 no+0.007
 Cle+0.007
 ears+0.007
 ear+0.006
Neg logit contributions
rig-0.025
inner-0.025
prise-0.024
pack-0.024
washer-0.023
Token a
Token ID257
Feature activation-3.02e-02

Pos logit contributions
rig+0.014
pack+0.014
inner+0.014
washer+0.013
prise+0.013
Neg logit contributions
 Cle-0.009
 tail-0.008
 Horse-0.008
 ears-0.008
 prope-0.008
Token smile
Token ID8212
Feature activation+2.78e+00

Pos logit contributions
rig+0.001
pack+0.001
inner+0.001
washer+0.001
prise+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 Horse-0.001
 ears-0.001
 prope-0.001
Token!
Token ID0
Feature activation-6.60e-01

Pos logit contributions
 Cle+0.083
 tail+0.074
 Horse+0.074
 prope+0.073
Leave+0.071
Neg logit contributions
pack-0.123
inner-0.123
rig-0.121
washer-0.117
ade-0.114
Token
Token ID198
Feature activation+1.58e-02

Pos logit contributions
rig+0.033
pack+0.033
inner+0.033
washer+0.031
ade+0.030
Neg logit contributions
 Cle-0.016
 tail-0.015
 prope-0.015
 ears-0.014
 Horse-0.014
Token
Token ID198
Feature activation+4.66e-01

Pos logit contributions
 Cle+0.000
 tail+0.000
 ears+0.000
 prope+0.000
 Horse+0.000
Neg logit contributions
rig-0.001
pack-0.001
inner-0.001
washer-0.001
ade-0.001
TokenBut
Token ID1537
Feature activation+1.33e+00

Pos logit contributions
 Cle+0.012
 tail+0.012
 Horse+0.011
 ears+0.011
 prope+0.011
Neg logit contributions
rig-0.023
pack-0.022
inner-0.022
washer-0.021
prise-0.021
Token then
Token ID788
Feature activation+1.50e+00

Pos logit contributions
 Cle+0.046
 prope+0.046
Leave+0.044
 tail+0.044
 Horse+0.043
Neg logit contributions
pack-0.048
washer-0.045
inner-0.043
rig-0.042
 else-0.041
Token
Token ID198
Feature activation+8.66e-04

Pos logit contributions
rig+0.030
pack+0.030
inner+0.029
washer+0.028
prise+0.027
Neg logit contributions
 Cle-0.017
 tail-0.017
 ears-0.016
 prope-0.016
 Horse-0.015
Token"
Token ID1
Feature activation+4.71e-01

Pos logit contributions
 Cle+0.000
 tail+0.000
 Horse+0.000
 no+0.000
 prope+0.000
Neg logit contributions
rig-0.000
inner-0.000
pack-0.000
washer-0.000
prise-0.000
TokenThank
Token ID10449
Feature activation+1.08e+00

Pos logit contributions
 Cle+0.013
 tail+0.013
 ears+0.012
 Horse+0.012
 prope+0.012
Neg logit contributions
rig-0.022
pack-0.022
inner-0.022
washer-0.021
prise-0.020
Token you
Token ID345
Feature activation+3.27e-02

Pos logit contributions
 Cle+0.046
 tail+0.045
 no+0.043
 Horse+0.043
 ear+0.043
Neg logit contributions
rig-0.036
pack-0.034
inner-0.033
washer-0.032
ade-0.030
Token,
Token ID11
Feature activation+1.16e-01

Pos logit contributions
 Cle+0.001
 tail+0.001
Leave+0.001
 prope+0.001
 Horse+0.001
Neg logit contributions
rig-0.001
inner-0.001
pack-0.001
washer-0.001
prise-0.001
Token thank
Token ID5875
Feature activation+2.88e+00

Pos logit contributions
 Cle+0.003
 tail+0.003
 Horse+0.003
 ears+0.003
 prope+0.003
Neg logit contributions
rig-0.005
pack-0.005
inner-0.005
washer-0.005
prise-0.005
Token you
Token ID345
Feature activation+5.56e-02

Pos logit contributions
 Cle+0.141
 tail+0.140
 prope+0.134
 ears+0.133
 Horse+0.133
Neg logit contributions
pack-0.074
rig-0.073
inner-0.071
washer-0.065
prise-0.064
Token,
Token ID11
Feature activation+2.69e-01

Pos logit contributions
 Cle+0.002
 tail+0.002
 prope+0.002
Leave+0.002
 Horse+0.002
Neg logit contributions
rig-0.002
pack-0.002
inner-0.002
washer-0.002
prise-0.002
Token thank
Token ID5875
Feature activation+2.87e+00

Pos logit contributions
 Cle+0.008
 tail+0.007
 Horse+0.007
 ears+0.007
 prope+0.007
Neg logit contributions
rig-0.013
pack-0.013
inner-0.012
washer-0.012
prise-0.011
Token you
Token ID345
Feature activation-2.94e-02

Pos logit contributions
 Cle+0.138
 tail+0.136
 prope+0.130
 ears+0.130
 Horse+0.130
Neg logit contributions
rig-0.077
pack-0.076
inner-0.074
washer-0.068
prise-0.066
Token!"
Token ID2474
Feature activation+6.79e-01

Pos logit contributions
rig+0.001
pack+0.001
inner+0.001
washer+0.001
prise+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 prope-0.001
 Horse-0.001
 ears-0.001
Token sailed
Token ID33835
Feature activation+6.70e-01

Pos logit contributions
 Cle+0.012
 tail+0.012
 ears+0.012
 ear+0.011
 Horse+0.011
Neg logit contributions
pack-0.015
inner-0.014
rig-0.014
washer-0.014
ade-0.013
Token until
Token ID1566
Feature activation+1.44e-01

Pos logit contributions
 Cle+0.028
 Horse+0.025
Leave+0.025
itive+0.025
bee+0.024
Neg logit contributions
pack-0.021
ade-0.020
inner-0.020
rig-0.019
 else-0.018
Token it
Token ID340
Feature activation+3.88e-01

Pos logit contributions
 tail+0.005
 Cle+0.005
 ears+0.005
 Horse+0.004
 ear+0.004
Neg logit contributions
inner-0.006
pack-0.005
washer-0.005
rig-0.005
ade-0.005
Token could
Token ID714
Feature activation+2.52e+00

Pos logit contributions
 Cle+0.012
 tail+0.011
 Horse+0.011
 ears+0.011
 prope+0.011
Neg logit contributions
rig-0.017
pack-0.017
inner-0.017
washer-0.016
ade-0.016
Token sail
Token ID14936
Feature activation+7.63e-02

Pos logit contributions
 Cle+0.096
 Horse+0.088
 tail+0.087
 ears+0.086
 prope+0.084
Neg logit contributions
pack-0.092
rig-0.092
inner-0.089
washer-0.081
ade-0.080
Token no
Token ID645
Feature activation+4.38e+00

Pos logit contributions
 Cle+0.003
 Horse+0.003
 tail+0.003
 ears+0.003
 prope+0.002
Neg logit contributions
pack-0.003
rig-0.003
inner-0.003
ade-0.003
washer-0.003
Token further
Token ID2252
Feature activation-1.74e+00

Pos logit contributions
 Cle+0.146
 tail+0.130
 Horse+0.128
 ears+0.121
 Paw+0.119
Neg logit contributions
pack-0.178
rig-0.177
inner-0.176
prise-0.167
washer-0.166
Token.
Token ID13
Feature activation+7.37e-01

Pos logit contributions
rig+0.073
pack+0.071
inner+0.069
washer+0.067
ade+0.064
Neg logit contributions
 Cle-0.058
 tail-0.055
 Horse-0.052
 ears-0.051
 ear-0.050
Token The
Token ID383
Feature activation+8.12e-01

Pos logit contributions
 Cle+0.018
 tail+0.017
 prope+0.016
 Horse+0.016
 ears+0.016
Neg logit contributions
rig-0.037
inner-0.037
pack-0.036
washer-0.035
ade-0.033
Token boat
Token ID8848
Feature activation+1.30e-01

Pos logit contributions
 Cle+0.029
 tail+0.027
 Horse+0.026
 ears+0.025
 prope+0.024
Neg logit contributions
inner-0.033
pack-0.033
rig-0.032
washer-0.032
ade-0.029
Token was
Token ID373
Feature activation-2.18e-01

Pos logit contributions
 Cle+0.005
 tail+0.004
 Horse+0.004
 ears+0.004
 ear+0.004
Neg logit contributions
pack-0.005
rig-0.005
washer-0.005
inner-0.005
ade-0.005
Token.
Token ID13
Feature activation-2.27e+00

Pos logit contributions
 tail+0.014
 Cle+0.012
 no+0.012
 ears+0.011
 ear+0.011
Neg logit contributions
rig-0.035
pack-0.034
inner-0.034
washer-0.033
prise-0.031
Token The
Token ID383
Feature activation-6.65e-01

Pos logit contributions
rig+0.106
pack+0.103
inner+0.101
washer+0.099
prise+0.094
Neg logit contributions
 Cle-0.060
 tail-0.059
 prope-0.056
 ears-0.054
 Horse-0.054
Token mattress
Token ID33388
Feature activation-1.47e+00

Pos logit contributions
rig+0.029
inner+0.028
pack+0.028
washer+0.027
prise+0.026
Neg logit contributions
 Cle-0.020
 tail-0.019
 Horse-0.018
 prope-0.018
 ears-0.018
Token was
Token ID373
Feature activation-3.55e-01

Pos logit contributions
rig+0.069
pack+0.067
inner+0.066
prise+0.062
washer+0.061
Neg logit contributions
 tail-0.042
 Cle-0.041
 ears-0.039
 no-0.039
 prope-0.037
Token wet
Token ID9583
Feature activation-8.48e-01

Pos logit contributions
rig+0.014
pack+0.014
inner+0.013
washer+0.013
prise+0.012
Neg logit contributions
 Cle-0.013
 tail-0.013
 Horse-0.012
 ears-0.012
 prope-0.012
Token and
Token ID290
Feature activation-8.97e-01

Pos logit contributions
rig+0.039
pack+0.039
inner+0.038
washer+0.037
ade+0.035
Neg logit contributions
 Cle-0.025
 tail-0.023
 Horse-0.022
 prope-0.022
 ears-0.022
Token had
Token ID550
Feature activation+6.72e-01

Pos logit contributions
rig+0.031
pack+0.031
inner+0.031
washer+0.029
ade+0.027
Neg logit contributions
 Cle-0.036
 tail-0.034
 Horse-0.033
 prope-0.032
 ears-0.032
Token a
Token ID257
Feature activation-2.21e-02

Pos logit contributions
 Cle+0.024
 tail+0.022
 Horse+0.022
 ear+0.021
 prope+0.021
Neg logit contributions
pack-0.026
rig-0.026
inner-0.025
washer-0.024
ade-0.024
Token big
Token ID1263
Feature activation-1.70e+00

Pos logit contributions
rig+0.001
pack+0.001
inner+0.001
washer+0.001
ade+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 Horse-0.001
 prope-0.001
 ears-0.001
Token stain
Token ID18746
Feature activation+2.45e-01

Pos logit contributions
inner+0.065
rig+0.065
pack+0.065
washer+0.062
ade+0.060
Neg logit contributions
 Cle-0.060
 Horse-0.053
 tail-0.051
Leave-0.050
ked-0.049
Token.
Token ID13
Feature activation-3.37e-02

Pos logit contributions
 Cle+0.007
 tail+0.007
 Horse+0.006
 ears+0.006
 prope+0.006
Neg logit contributions
rig-0.011
pack-0.011
inner-0.011
washer-0.011
prise-0.010
Token followed
Token ID3940
Feature activation+1.01e+00

Pos logit contributions
 Cle+0.038
 tail+0.035
 prope+0.034
 Horse+0.034
 ears+0.033
Neg logit contributions
rig-0.051
pack-0.049
washer-0.047
ade-0.047
inner-0.047
Token.
Token ID13
Feature activation+3.29e-01

Pos logit contributions
 prope+0.039
 Horse+0.037
 tail+0.036
 ears+0.035
 Cle+0.034
Neg logit contributions
rig-0.034
pack-0.034
ade-0.031
inner-0.031
off-0.031
Token
Token ID198
Feature activation+2.77e-01

Pos logit contributions
 Cle+0.009
 tail+0.008
 Horse+0.008
 prope+0.008
 ears+0.008
Neg logit contributions
rig-0.016
pack-0.016
inner-0.016
washer-0.015
ade-0.014
Token
Token ID198
Feature activation+6.91e-01

Pos logit contributions
 Cle+0.007
 tail+0.006
 Horse+0.006
 ears+0.006
 prope+0.006
Neg logit contributions
rig-0.014
pack-0.014
inner-0.014
washer-0.013
prise-0.013
TokenThe
Token ID464
Feature activation+8.20e-01

Pos logit contributions
 Cle+0.018
 tail+0.017
Leave+0.016
 no+0.016
 Horse+0.015
Neg logit contributions
rig-0.033
inner-0.033
pack-0.032
washer-0.032
prise-0.030
Token bee
Token ID20697
Feature activation+1.26e+00

Pos logit contributions
 Cle+0.024
 tail+0.022
 Horse+0.021
 prope+0.021
 ears+0.020
Neg logit contributions
rig-0.039
inner-0.038
pack-0.038
washer-0.036
prise-0.035
Token was
Token ID373
Feature activation-1.07e-01

Pos logit contributions
 Cle+0.040
 tail+0.037
 prope+0.035
 ear+0.035
 Horse+0.035
Neg logit contributions
rig-0.055
pack-0.052
inner-0.050
washer-0.050
ade-0.049
Token very
Token ID845
Feature activation-1.91e+00

Pos logit contributions
rig+0.004
pack+0.004
inner+0.003
washer+0.003
ade+0.003
Neg logit contributions
 Cle-0.004
 prope-0.004
 tail-0.004
 Horse-0.004
 ears-0.004
Token friendly
Token ID8030
Feature activation+2.32e-01

Pos logit contributions
rig+0.082
pack+0.081
inner+0.079
washer+0.075
prise+0.073
Neg logit contributions
 Cle-0.062
 tail-0.060
 Horse-0.056
 ears-0.056
 prope-0.055
Token,
Token ID11
Feature activation+8.63e-01

Pos logit contributions
 Cle+0.008
 prope+0.008
 Horse+0.007
 tail+0.007
Leave+0.007
Neg logit contributions
rig-0.009
pack-0.009
inner-0.008
washer-0.008
ade-0.008
Token and
Token ID290
Feature activation+2.41e-01

Pos logit contributions
 Cle+0.029
 prope+0.028
 Horse+0.027
 tail+0.027
 ear+0.027
Neg logit contributions
rig-0.035
pack-0.031
inner-0.031
ade-0.029
washer-0.029
Token"
Token ID1
Feature activation+4.74e-01

Pos logit contributions
 tail+0.002
 Cle+0.002
 no+0.001
 Horse+0.001
 ears+0.001
Neg logit contributions
rig-0.003
pack-0.003
inner-0.003
washer-0.003
prise-0.003
TokenLook
Token ID8567
Feature activation+1.44e-01

Pos logit contributions
 Cle+0.013
 tail+0.013
 ears+0.012
 Horse+0.012
 prope+0.012
Neg logit contributions
pack-0.023
inner-0.022
rig-0.022
prise-0.021
washer-0.020
Token,
Token ID11
Feature activation-1.22e-01

Pos logit contributions
 Cle+0.003
 tail+0.003
 ears+0.003
 ear+0.003
 no+0.003
Neg logit contributions
rig-0.008
pack-0.008
inner-0.007
washer-0.007
ade-0.007
Token Ben
Token ID3932
Feature activation+7.44e-01

Pos logit contributions
rig+0.007
pack+0.006
inner+0.006
washer+0.006
ade+0.006
Neg logit contributions
 Cle-0.003
 tail-0.003
 no-0.003
 ears-0.003
 ear-0.003
Token,
Token ID11
Feature activation-1.57e-01

Pos logit contributions
 Cle+0.022
 tail+0.021
 prope+0.021
 Horse+0.020
 ears+0.020
Neg logit contributions
rig-0.033
pack-0.033
inner-0.032
washer-0.031
prise-0.030
Token what
Token ID644
Feature activation-2.26e-02

Pos logit contributions
rig+0.007
pack+0.007
inner+0.007
ade+0.006
washer+0.006
Neg logit contributions
 Cle-0.005
 no-0.005
 tail-0.005
 ear-0.004
 ears-0.004
Token is
Token ID318
Feature activation-1.67e+00

Pos logit contributions
rig+0.001
pack+0.001
inner+0.001
washer+0.001
igsaw+0.001
Neg logit contributions
 no-0.001
 Cle-0.001
 tail-0.001
 ears-0.001
 ear-0.001
Token this
Token ID428
Feature activation-1.16e+00

Pos logit contributions
rig+0.092
inner+0.078
washer+0.076
pack+0.075
ade+0.075
Neg logit contributions
 Cle-0.050
 ear-0.049
 no-0.047
 tail-0.043
 Snow-0.040
Token?"
Token ID1701
Feature activation+9.84e-01

Pos logit contributions
rig+0.042
pack+0.039
inner+0.038
washer+0.036
prise+0.034
Neg logit contributions
 Cle-0.047
 tail-0.046
 no-0.045
 ear-0.044
 ears-0.043
Token Anna
Token ID11735
Feature activation-1.80e-01

Pos logit contributions
 Cle+0.028
 tail+0.027
 Horse+0.025
 prope+0.024
 ears+0.024
Neg logit contributions
rig-0.046
pack-0.046
inner-0.045
washer-0.043
prise-0.042
Token asks
Token ID7893
Feature activation-5.08e-02

Pos logit contributions
inner+0.008
rig+0.008
pack+0.008
washer+0.007
prise+0.007
Neg logit contributions
 Cle-0.006
 tail-0.006
 ears-0.006
 ear-0.006
 Horse-0.005
Token the
Token ID262
Feature activation+2.30e-01

Pos logit contributions
 Cle+0.006
 tail+0.006
 prope+0.005
 ear+0.005
 ears+0.005
Neg logit contributions
pack-0.007
rig-0.006
washer-0.006
inner-0.006
 else-0.006
Token ant
Token ID1885
Feature activation-1.08e+00

Pos logit contributions
 Cle+0.007
 tail+0.007
 Horse+0.006
 ears+0.006
 ear+0.006
Neg logit contributions
rig-0.011
pack-0.011
inner-0.010
washer-0.010
prise-0.010
Token knew
Token ID2993
Feature activation+2.53e-01

Pos logit contributions
rig+0.049
pack+0.048
inner+0.047
washer+0.046
ade+0.044
Neg logit contributions
 Cle-0.032
 tail-0.030
 prope-0.028
 Horse-0.028
 ears-0.028
Token that
Token ID326
Feature activation-2.25e+00

Pos logit contributions
 tail+0.012
 Cle+0.011
 prope+0.011
 ears+0.011
 Horse+0.011
Neg logit contributions
pack-0.007
rig-0.007
washer-0.007
inner-0.006
ade-0.006
Token he
Token ID339
Feature activation-9.44e-01

Pos logit contributions
pack+0.088
washer+0.087
rig+0.084
inner+0.082
 else+0.082
Neg logit contributions
 Cle-0.073
 tail-0.073
 prope-0.069
 ears-0.068
 ear-0.067
Token shouldn
Token ID6584
Feature activation-1.90e-01

Pos logit contributions
rig+0.044
pack+0.044
inner+0.043
washer+0.041
prise+0.040
Neg logit contributions
 Cle-0.027
 tail-0.026
 prope-0.024
 Horse-0.024
 ears-0.024
Token't
Token ID470
Feature activation+5.02e-01

Pos logit contributions
pack+0.008
rig+0.008
inner+0.008
washer+0.008
ade+0.008
Neg logit contributions
 tail-0.006
 Cle-0.006
 ears-0.006
 prope-0.005
joy-0.005
Token have
Token ID423
Feature activation-4.69e-01

Pos logit contributions
 Cle+0.018
 tail+0.017
 Horse+0.016
 ears+0.016
 prope+0.016
Neg logit contributions
rig-0.020
pack-0.020
inner-0.019
washer-0.018
prise-0.017
Token been
Token ID587
Feature activation+2.70e-02

Pos logit contributions
rig+0.021
inner+0.021
pack+0.020
washer+0.019
prise+0.018
Neg logit contributions
 Cle-0.015
 tail-0.015
 no-0.014
 ears-0.013
 Horse-0.013
Token so
Token ID523
Feature activation-2.32e+00

Pos logit contributions
 Cle+0.001
 tail+0.001
 prope+0.001
 Horse+0.001
 ears+0.001
Neg logit contributions
rig-0.001
pack-0.001
inner-0.001
washer-0.001
prise-0.001
Token competitive
Token ID7606
Feature activation-1.55e+00

Pos logit contributions
rig+0.088
pack+0.085
inner+0.084
washer+0.081
ade+0.076
Neg logit contributions
 Cle-0.087
 tail-0.084
 Horse-0.080
 prope-0.080
 ears-0.080
Token
Token ID198
Feature activation-5.90e-02

Pos logit contributions
 Cle+0.010
 prope+0.009
itive+0.009
 tail+0.009
 Horse+0.009
Neg logit contributions
rig-0.010
inner-0.010
pack-0.010
 else-0.009
washer-0.009
Token
Token ID198
Feature activation+3.73e-01

Pos logit contributions
rig+0.003
pack+0.003
inner+0.003
washer+0.003
prise+0.003
Neg logit contributions
 Cle-0.001
 tail-0.001
 Horse-0.001
 ears-0.001
 prope-0.001
TokenBut
Token ID1537
Feature activation+1.34e+00

Pos logit contributions
 tail+0.010
 Cle+0.010
 Horse+0.009
 no+0.009
 ears+0.009
Neg logit contributions
rig-0.018
pack-0.017
inner-0.017
washer-0.017
ade-0.016
Token then
Token ID788
Feature activation+1.37e+00

Pos logit contributions
 Cle+0.047
 tail+0.045
 prope+0.044
 Horse+0.043
joy+0.043
Neg logit contributions
pack-0.051
inner-0.049
 else-0.047
washer-0.047
prise-0.047
Token they
Token ID484
Feature activation+7.01e-01

Pos logit contributions
 Cle+0.046
 tail+0.046
 prope+0.044
 Horse+0.042
Leave+0.041
Neg logit contributions
inner-0.053
pack-0.052
washer-0.051
prise-0.051
 else-0.050
Token hear
Token ID3285
Feature activation+5.87e-01

Pos logit contributions
 Cle+0.015
 tail+0.014
 Horse+0.013
 ears+0.013
 prope+0.012
Neg logit contributions
rig-0.038
pack-0.037
inner-0.037
washer-0.036
prise-0.035
Token a
Token ID257
Feature activation+1.58e-01

Pos logit contributions
 Cle+0.022
 tail+0.020
 prope+0.020
 Horse+0.020
joy+0.019
Neg logit contributions
inner-0.022
rig-0.021
pack-0.021
washer-0.020
prise-0.019
Token loud
Token ID7812
Feature activation+1.62e+00

Pos logit contributions
 Cle+0.003
 tail+0.003
 ears+0.003
 prope+0.003
 Horse+0.003
Neg logit contributions
pack-0.009
rig-0.009
inner-0.008
washer-0.008
prise-0.008
Token noise
Token ID7838
Feature activation-4.85e-01

Pos logit contributions
 tail+0.045
 Cle+0.045
 ears+0.042
 Horse+0.041
 ear+0.041
Neg logit contributions
rig-0.077
pack-0.076
inner-0.075
washer-0.072
prise-0.070
Token.
Token ID13
Feature activation+3.98e-01

Pos logit contributions
rig+0.027
pack+0.027
inner+0.026
igsaw+0.026
prise+0.026
Neg logit contributions
 tail-0.009
 Cle-0.008
 ear-0.008
 ears-0.008
 horns-0.008
Token It
Token ID632
Feature activation+3.65e-01

Pos logit contributions
 Cle+0.011
 tail+0.010
 Horse+0.009
 prope+0.009
 ears+0.009
Neg logit contributions
rig-0.019
inner-0.019
pack-0.019
washer-0.018
prise-0.017
Token smiles
Token ID21845
Feature activation+1.74e+00

Pos logit contributions
 ears+0.015
 tail+0.014
 Cle+0.014
 no+0.014
 ear+0.013
Neg logit contributions
rig-0.027
inner-0.026
pack-0.026
washer-0.025
igsaw-0.025
Token.
Token ID13
Feature activation-4.89e-01

Pos logit contributions
 Cle+0.073
 Horse+0.062
 prope+0.062
 tail+0.060
Leave+0.058
Neg logit contributions
pack-0.058
rig-0.057
washer-0.056
inner-0.056
prise-0.052
Token She
Token ID1375
Feature activation-1.93e-01

Pos logit contributions
rig+0.020
pack+0.019
inner+0.019
washer+0.018
ade+0.017
Neg logit contributions
 tail-0.016
 prope-0.015
 Cle-0.015
 Horse-0.015
 ears-0.014
Token says
Token ID1139
Feature activation-1.88e+00

Pos logit contributions
inner+0.009
pack+0.008
rig+0.008
igsaw+0.008
washer+0.008
Neg logit contributions
 ears-0.006
 tail-0.006
 Cle-0.006
 no-0.006
 ear-0.005
Token they
Token ID484
Feature activation-1.57e+00

Pos logit contributions
inner+0.060
 else+0.059
washer+0.059
prise+0.056
ade+0.055
Neg logit contributions
 tail-0.074
 Cle-0.071
 ears-0.067
 Horse-0.067
 prope-0.066
Token are
Token ID389
Feature activation-1.96e+00

Pos logit contributions
rig+0.066
pack+0.064
inner+0.064
washer+0.060
prise+0.058
Neg logit contributions
 Cle-0.053
 tail-0.051
 ears-0.048
 Horse-0.048
 prope-0.047
Token good
Token ID922
Feature activation+2.59e-01

Pos logit contributions
rig+0.085
pack+0.084
inner+0.083
washer+0.079
prise+0.076
Neg logit contributions
 Cle-0.063
 tail-0.061
 Horse-0.056
 ears-0.056
 prope-0.055
Token kids
Token ID3988
Feature activation-1.12e+00

Pos logit contributions
 Cle+0.008
 prope+0.008
 tail+0.008
 Horse+0.007
Leave+0.007
Neg logit contributions
pack-0.011
inner-0.011
washer-0.011
prise-0.011
rig-0.011
Token.
Token ID13
Feature activation-4.64e-01

Pos logit contributions
rig+0.052
pack+0.051
inner+0.051
washer+0.049
prise+0.047
Neg logit contributions
 Cle-0.032
 tail-0.031
 Horse-0.029
 ears-0.029
 prope-0.028
Token She
Token ID1375
Feature activation+2.44e-02

Pos logit contributions
rig+0.019
pack+0.018
inner+0.018
washer+0.017
prise+0.016
Neg logit contributions
 tail-0.015
 prope-0.015
 Cle-0.014
 ears-0.014
 Horse-0.014
Token says
Token ID1139
Feature activation-1.75e+00

Pos logit contributions
 Cle+0.001
 ears+0.001
 tail+0.001
 no+0.001
 owners+0.001
Neg logit contributions
pack-0.001
inner-0.001
igsaw-0.001
rig-0.001
washer-0.001
Token tall
Token ID7331
Feature activation-5.28e+00

Pos logit contributions
 Cle+0.035
 tail+0.033
 Horse+0.031
 prope+0.030
 ears+0.030
Neg logit contributions
pack-0.042
rig-0.041
inner-0.041
washer-0.039
prise-0.037
Token bag
Token ID6131
Feature activation-4.21e+00

Pos logit contributions
rig+0.218
pack+0.213
inner+0.212
washer+0.202
ade+0.193
Neg logit contributions
 Cle-0.178
 tail-0.166
 Horse-0.161
 prope-0.157
 ears-0.155
Token and
Token ID290
Feature activation-2.00e+00

Pos logit contributions
rig+0.185
pack+0.183
inner+0.180
washer+0.172
prise+0.165
Neg logit contributions
 Cle-0.131
 tail-0.126
 Horse-0.118
 ears-0.117
 prope-0.116
Token told
Token ID1297
Feature activation-1.34e-01

Pos logit contributions
rig+0.088
pack+0.086
inner+0.085
washer+0.080
prise+0.078
Neg logit contributions
 Cle-0.063
 tail-0.062
 ears-0.058
 no-0.057
 ear-0.057
Token her
Token ID607
Feature activation-2.10e+00

Pos logit contributions
rig+0.005
pack+0.005
inner+0.005
washer+0.005
ade+0.005
Neg logit contributions
 tail-0.004
 Cle-0.004
 prope-0.004
Leave-0.004
 Horse-0.004
Token mom
Token ID1995
Feature activation-2.03e+00

Pos logit contributions
rig+0.100
pack+0.098
inner+0.097
washer+0.095
prise+0.091
Neg logit contributions
 Cle-0.057
 tail-0.055
 Horse-0.051
 prope-0.051
 ears-0.050
Token what
Token ID644
Feature activation-1.85e+00

Pos logit contributions
rig+0.072
pack+0.072
inner+0.071
washer+0.069
ade+0.064
Neg logit contributions
 Cle-0.080
 tail-0.078
 prope-0.075
 Horse-0.073
 ears-0.072
Token happened
Token ID3022
Feature activation+4.11e-02

Pos logit contributions
rig+0.090
pack+0.088
inner+0.087
washer+0.081
prise+0.080
Neg logit contributions
 Cle-0.052
 tail-0.049
 no-0.046
 Horse-0.045
 ears-0.045
Token.
Token ID13
Feature activation-8.77e-01

Pos logit contributions
 Cle+0.001
 tail+0.001
 prope+0.001
 Horse+0.001
 ears+0.001
Neg logit contributions
pack-0.002
rig-0.002
inner-0.002
washer-0.002
prise-0.002
Token Her
Token ID2332
Feature activation+1.19e+00

Pos logit contributions
rig+0.041
pack+0.040
inner+0.039
washer+0.038
prise+0.036
Neg logit contributions
 tail-0.023
 Cle-0.023
 prope-0.022
 Horse-0.021
 ears-0.021
Token mom
Token ID1995
Feature activation+4.39e-01

Pos logit contributions
 Cle+0.023
 tail+0.021
 Horse+0.021
 prope+0.020
Leave+0.019
Neg logit contributions
rig-0.065
pack-0.064
inner-0.063
washer-0.062
prise-0.060
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
rig+0.006
pack+0.006
inner+0.006
washer+0.006
prise+0.006
Neg logit contributions
 Cle-0.002
 tail-0.002
 Horse-0.002
 no-0.002
 ears-0.002
TokenAfter
Token ID3260
Feature activation-8.33e-01

Pos logit contributions
 Cle+0.009
 tail+0.009
 no+0.008
Leave+0.008
 Horse+0.007
Neg logit contributions
rig-0.017
inner-0.016
pack-0.016
washer-0.016
prise-0.015
Token they
Token ID484
Feature activation+3.31e-01

Pos logit contributions
pack+0.035
inner+0.034
rig+0.034
washer+0.033
prise+0.032
Neg logit contributions
 Cle-0.027
 tail-0.026
 Horse-0.025
 prope-0.025
 ears-0.024
Token were
Token ID547
Feature activation-8.04e-01

Pos logit contributions
 Cle+0.011
 no+0.011
 ear+0.010
 goodbye+0.010
 tail+0.010
Neg logit contributions
rig-0.015
inner-0.013
pack-0.013
washer-0.013
igsaw-0.012
Token done
Token ID1760
Feature activation-3.68e-01

Pos logit contributions
rig+0.024
inner+0.022
pack+0.021
washer+0.020
off+0.019
Neg logit contributions
 Cle-0.038
 tail-0.037
 no-0.036
 ears-0.036
 ear-0.035
Token shopping
Token ID9735
Feature activation-2.16e+00

Pos logit contributions
rig+0.016
pack+0.016
inner+0.016
washer+0.015
prise+0.014
Neg logit contributions
 Cle-0.011
 tail-0.011
 Horse-0.010
 ears-0.010
 prope-0.010
Token,
Token ID11
Feature activation+9.96e-01

Pos logit contributions
rig+0.120
inner+0.114
pack+0.114
prise+0.108
washer+0.107
Neg logit contributions
 Cle-0.045
 tail-0.042
 no-0.041
 ears-0.039
 goodbye-0.038
Token Tim
Token ID5045
Feature activation-8.11e-01

Pos logit contributions
 prope+0.041
 Cle+0.041
 tail+0.041
 Horse+0.040
 ear+0.039
Neg logit contributions
pack-0.030
rig-0.029
inner-0.028
washer-0.028
ade-0.026
Token and
Token ID290
Feature activation+2.07e-01

Pos logit contributions
rig+0.036
inner+0.036
pack+0.035
prise+0.033
washer+0.033
Neg logit contributions
 Cle-0.025
 tail-0.024
 ears-0.023
 Horse-0.023
 no-0.022
Token his
Token ID465
Feature activation+1.95e+00

Pos logit contributions
 prope+0.007
 Cle+0.007
 tail+0.007
 Horse+0.006
Leave+0.006
Neg logit contributions
pack-0.008
rig-0.008
washer-0.008
inner-0.007
ade-0.007
Token mom
Token ID1995
Feature activation+1.09e+00

Pos logit contributions
 Cle+0.047
 Horse+0.043
 prope+0.043
Leave+0.043
 tail+0.042
Neg logit contributions
pack-0.094
washer-0.094
rig-0.091
inner-0.091
ade-0.087
Token,
Token ID11
Feature activation-3.98e-01

Pos logit contributions
 tail+0.007
 Cle+0.006
 Horse+0.006
 ears+0.006
 prope+0.006
Neg logit contributions
inner-0.008
washer-0.008
rig-0.008
pack-0.008
ade-0.008
Token
Token ID6184
Feature activation+7.34e-01

Pos logit contributions
rig+0.017
pack+0.016
washer+0.016
inner+0.016
 else+0.013
Neg logit contributions
 Cle-0.011
 tail-0.011
Leave-0.011
 prope-0.011
 ears-0.011
Token
Token ID95
Feature activation+1.24e-01

Pos logit contributions
 Cle+0.026
 tail+0.024
 Horse+0.023
 ear+0.023
 prope+0.023
Neg logit contributions
rig-0.030
pack-0.029
inner-0.028
washer-0.028
prise-0.027
Token
Token ID26391
Feature activation+1.80e+00

Pos logit contributions
 Cle+0.004
 tail+0.004
 Horse+0.004
 ears+0.004
 ear+0.004
Neg logit contributions
rig-0.005
pack-0.005
inner-0.005
washer-0.005
prise-0.004
Token
Token ID129
Feature activation+2.17e+00

Pos logit contributions
 Cle+0.058
 tail+0.057
 prope+0.055
 ear+0.055
 ears+0.053
Neg logit contributions
rig-0.075
pack-0.075
inner-0.072
washer-0.069
prise-0.066
Token
Token ID241
Feature activation-1.96e+00

Pos logit contributions
 Cle+0.074
 tail+0.072
 ears+0.067
 Horse+0.066
 ear+0.066
Neg logit contributions
rig-0.089
pack-0.089
inner-0.088
washer-0.085
prise-0.083
TokenI
Token ID40
Feature activation-2.93e-02

Pos logit contributions
rig+0.080
inner+0.078
pack+0.075
washer+0.066
off+0.066
Neg logit contributions
 tail-0.067
 ears-0.067
 Cle-0.066
 prope-0.065
 ear-0.062
Tokenâ
Token ID22940
Feature activation-1.70e-01

Pos logit contributions
pack+0.001
rig+0.001
inner+0.001
washer+0.001
prise+0.001
Neg logit contributions
 Cle-0.001
 tail-0.001
 no-0.001
 Horse-0.001
 ear-0.001
Token
Token ID26391
Feature activation+1.41e+00

Pos logit contributions
rig+0.007
pack+0.007
inner+0.006
washer+0.006
prise+0.006
Neg logit contributions
 Cle-0.006
 tail-0.006
 Horse-0.005
 ear-0.005
 ears-0.005
Token
Token ID8151
Feature activation+8.16e-01

Pos logit contributions
 Cle+0.045
 tail+0.045
 prope+0.043
 ear+0.042
 ears+0.042
Neg logit contributions
rig-0.059
pack-0.058
inner-0.057
washer-0.055
prise-0.053
Tokenm
Token ID76
Feature activation+1.33e+00

Pos logit contributions
 Cle+0.033
 tail+0.033
 prope+0.032
 ears+0.032
 Horse+0.031
Neg logit contributions
rig-0.028
pack-0.027
inner-0.027
washer-0.026
ade-0.024
Token They
Token ID1119
Feature activation+5.25e-01

Pos logit contributions
 Cle+0.008
 prope+0.008
 tail+0.008
 Horse+0.007
 ears+0.007
Neg logit contributions
rig-0.012
inner-0.012
pack-0.012
washer-0.011
igsaw-0.011
Token played
Token ID2826
Feature activation+1.82e+00

Pos logit contributions
 Cle+0.018
 tail+0.017
 Horse+0.016
joy+0.016
 ears+0.016
Neg logit contributions
pack-0.021
rig-0.021
inner-0.020
washer-0.020
ade-0.019
Token games
Token ID1830
Feature activation+4.19e-01

Pos logit contributions
 Cle+0.079
 tail+0.073
 Horse+0.073
 ears+0.070
 prope+0.070
Neg logit contributions
pack-0.060
rig-0.060
inner-0.058
washer-0.053
ade-0.052
Token and
Token ID290
Feature activation+6.19e-01

Pos logit contributions
 Cle+0.012
 tail+0.012
 Horse+0.011
 ears+0.011
 prope+0.011
Neg logit contributions
rig-0.019
pack-0.019
inner-0.019
washer-0.018
prise-0.017
Token had
Token ID550
Feature activation+1.64e+00

Pos logit contributions
 Cle+0.023
 Horse+0.022
joy+0.021
Leave+0.021
 trigger+0.021
Neg logit contributions
pack-0.020
washer-0.020
 else-0.019
inner-0.019
rig-0.019
Token fun
Token ID1257
Feature activation-1.89e+00

Pos logit contributions
 Cle+0.070
 tail+0.067
 Horse+0.065
 ears+0.064
 prope+0.064
Neg logit contributions
rig-0.053
pack-0.052
inner-0.051
washer-0.048
prise-0.045
Token until
Token ID1566
Feature activation+1.70e-01

Pos logit contributions
pack+0.065
rig+0.065
inner+0.062
washer+0.059
ade+0.058
Neg logit contributions
 Cle-0.079
 Horse-0.072
 tail-0.070
 prope-0.069
Leave-0.066
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
 tail+0.006
 Horse+0.006
 Cle+0.006
 prope+0.006
 ears+0.006
Neg logit contributions
pack-0.006
inner-0.006
prise-0.005
 else-0.005
rous-0.005
Token rain
Token ID6290
Feature activation-6.21e-01

Pos logit contributions
 Cle+0.004
 tail+0.004
 Horse+0.004
 prope+0.004
 ears+0.004
Neg logit contributions
inner-0.006
rig-0.006
pack-0.006
washer-0.006
ade-0.006
Token stopped
Token ID5025
Feature activation+1.84e+00

Pos logit contributions
inner+0.026
rig+0.025
pack+0.025
ade+0.024
washer+0.024
Neg logit contributions
 Cle-0.021
 tail-0.020
 Horse-0.020
 ear-0.020
 prope-0.020
Token.
Token ID13
Feature activation+7.90e-01

Pos logit contributions
 Cle+0.068
 goodbye+0.066
 tail+0.065
 Horse+0.063
 ear+0.063
Neg logit contributions
pack-0.065
rig-0.064
inner-0.057
washer-0.057
prise-0.054
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
 Cle+0.017
 tail+0.017
 Horse+0.015
 ears+0.015
 no+0.015
Neg logit contributions
rig-0.039
inner-0.038
pack-0.037
prise-0.036
washer-0.035
Token They
Token ID1119
Feature activation-1.06e-01

Pos logit contributions
 Cle+0.008
 tail+0.008
 Horse+0.007
 ears+0.007
 no+0.006
Neg logit contributions
rig-0.022
pack-0.021
inner-0.021
prise-0.020
washer-0.020
Token would
Token ID561
Feature activation+2.72e+00

Pos logit contributions
pack+0.005
rig+0.005
inner+0.005
washer+0.004
prise+0.004
Neg logit contributions
 Cle-0.003
 tail-0.003
 ears-0.003
 prope-0.003
 Horse-0.003
Token see
Token ID766
Feature activation-1.83e+00

Pos logit contributions
 Cle+0.102
 tail+0.099
 Horse+0.094
 ears+0.093
 prope+0.092
Neg logit contributions
rig-0.103
pack-0.101
inner-0.100
washer-0.094
prise-0.090
Token all
Token ID477
Feature activation-2.83e+00

Pos logit contributions
rig+0.074
pack+0.073
inner+0.070
washer+0.069
off+0.066
Neg logit contributions
 Cle-0.060
 tail-0.059
 ear-0.054
 prope-0.054
 ears-0.053
Token sorts
Token ID10524
Feature activation-5.87e+00

Pos logit contributions
inner+0.120
rig+0.115
pack+0.114
prise+0.113
washer+0.108
Neg logit contributions
 Cle-0.096
 tail-0.095
 Horse-0.092
 Big-0.089
 ears-0.087
Token of
Token ID286
Feature activation-8.11e-01

Pos logit contributions
pack+0.272
rig+0.272
inner+0.264
prise+0.247
washer+0.245
Neg logit contributions
 Cle-0.164
 tail-0.161
 goodbye-0.152
 no-0.152
 ears-0.151
Token animals
Token ID4695
Feature activation+8.59e-01

Pos logit contributions
rig+0.040
pack+0.039
inner+0.039
washer+0.037
prise+0.036
Neg logit contributions
 Cle-0.021
 tail-0.020
 ears-0.019
 Horse-0.019
 prope-0.018
Token like
Token ID588
Feature activation-2.16e+00

Pos logit contributions
 tail+0.017
 Cle+0.017
 Horse+0.015
 no+0.015
 ears+0.015
Neg logit contributions
inner-0.048
rig-0.047
pack-0.046
igsaw-0.044
prise-0.044
Token lions
Token ID31420
Feature activation+1.81e+00

Pos logit contributions
rig+0.100
pack+0.099
inner+0.097
washer+0.095
prise+0.091
Neg logit contributions
 Cle-0.058
 tail-0.056
 prope-0.051
 ear-0.051
 ears-0.051
Token,
Token ID11
Feature activation+8.59e-01

Pos logit contributions
 Cle+0.047
 tail+0.045
 Horse+0.041
 prope+0.041
 ears+0.041
Neg logit contributions
rig-0.089
pack-0.088
inner-0.086
washer-0.083
prise-0.080
Token The
Token ID383
Feature activation+3.36e-01

Pos logit contributions
rig+0.009
pack+0.009
inner+0.009
washer+0.009
off+0.008
Neg logit contributions
 Cle-0.006
 tail-0.006
 prope-0.006
 ear-0.005
 ears-0.005
Token person
Token ID1048
Feature activation-2.48e-01

Pos logit contributions
 Cle+0.011
 tail+0.010
 Horse+0.010
 prope+0.009
 ears+0.009
Neg logit contributions
rig-0.015
pack-0.015
inner-0.015
washer-0.014
prise-0.013
Token kept
Token ID4030
Feature activation+8.75e-01

Pos logit contributions
rig+0.011
pack+0.011
inner+0.011
washer+0.010
prise+0.010
Neg logit contributions
 Cle-0.008
 tail-0.007
 Horse-0.007
 ears-0.007
 prope-0.007
Token trying
Token ID2111
Feature activation-7.91e-01

Pos logit contributions
 Cle+0.027
 tail+0.026
 Horse+0.025
 prope+0.024
 ears+0.024
Neg logit contributions
rig-0.038
pack-0.038
inner-0.036
washer-0.035
prise-0.034
Token all
Token ID477
Feature activation-3.37e+00

Pos logit contributions
rig+0.035
pack+0.034
inner+0.033
washer+0.032
ade+0.031
Neg logit contributions
 Cle-0.025
 tail-0.023
 Horse-0.022
 prope-0.022
 ears-0.021
Token sorts
Token ID10524
Feature activation-5.77e+00

Pos logit contributions
rig+0.185
inner+0.183
pack+0.181
prise+0.179
washer+0.170
Neg logit contributions
 tail-0.066
 no-0.063
 Cle-0.061
 Big-0.058
 ear-0.056
Token of
Token ID286
Feature activation-1.14e+00

Pos logit contributions
rig+0.233
pack+0.231
inner+0.226
washer+0.214
prise+0.207
Neg logit contributions
 Cle-0.200
 tail-0.195
 ears-0.182
 Horse-0.182
 prope-0.180
Token things
Token ID1243
Feature activation-8.49e-01

Pos logit contributions
inner+0.047
pack+0.047
rig+0.047
washer+0.045
prise+0.043
Neg logit contributions
 tail-0.038
 ears-0.037
 Cle-0.036
 ear-0.034
 no-0.034
Token,
Token ID11
Feature activation+1.98e-01

Pos logit contributions
rig+0.043
inner+0.042
pack+0.042
prise+0.041
washer+0.039
Neg logit contributions
 no-0.021
 Cle-0.020
 tail-0.020
 goodbye-0.018
 prope-0.017
Token but
Token ID475
Feature activation+1.16e+00

Pos logit contributions
 Cle+0.005
 tail+0.005
 Horse+0.005
 prope+0.005
 ear+0.004
Neg logit contributions
rig-0.009
pack-0.009
inner-0.009
washer-0.009
ade-0.008
Token the
Token ID262
Feature activation+4.18e-01

Pos logit contributions
 Cle+0.033
 tail+0.032
 Horse+0.030
 prope+0.029
 ears+0.029
Neg logit contributions
rig-0.053
pack-0.052
inner-0.051
washer-0.051
prise-0.048
Token store
Token ID3650
Feature activation-1.80e+00

Pos logit contributions
 Cle+0.034
 tail+0.034
 ears+0.031
 ear+0.031
 no+0.031
Neg logit contributions
rig-0.043
inner-0.040
pack-0.040
prise-0.037
washer-0.037
Token.
Token ID13
Feature activation+2.33e-01

Pos logit contributions
rig+0.083
pack+0.081
inner+0.081
washer+0.076
prise+0.074
Neg logit contributions
 Cle-0.053
 tail-0.051
 ears-0.047
 Horse-0.047
 no-0.046
Token She
Token ID1375
Feature activation-6.03e-02

Pos logit contributions
 prope+0.007
 Cle+0.007
 tail+0.007
 Horse+0.007
 ears+0.006
Neg logit contributions
pack-0.010
rig-0.010
inner-0.010
washer-0.009
ade-0.009
Token saw
Token ID2497
Feature activation-8.93e-01

Pos logit contributions
rig+0.003
inner+0.003
pack+0.003
prise+0.003
washer+0.003
Neg logit contributions
 Cle-0.002
 tail-0.001
 no-0.001
 ears-0.001
 Horse-0.001
Token all
Token ID477
Feature activation-2.58e+00

Pos logit contributions
pack+0.036
rig+0.035
inner+0.035
washer+0.034
ade+0.033
Neg logit contributions
 Cle-0.029
 tail-0.029
 prope-0.027
 Horse-0.027
 ears-0.026
Token sorts
Token ID10524
Feature activation-5.68e+00

Pos logit contributions
inner+0.128
rig+0.128
pack+0.125
prise+0.123
washer+0.117
Neg logit contributions
 Cle-0.066
 tail-0.065
 ear-0.062
 ears-0.060
 no-0.060
Token of
Token ID286
Feature activation-7.11e-01

Pos logit contributions
rig+0.253
pack+0.250
inner+0.245
washer+0.229
prise+0.226
Neg logit contributions
 Cle-0.176
 tail-0.171
 ears-0.161
 no-0.160
 ear-0.159
Token toys
Token ID14958
Feature activation+1.21e-01

Pos logit contributions
rig+0.029
pack+0.029
inner+0.029
washer+0.027
prise+0.026
Neg logit contributions
 Cle-0.024
 tail-0.024
 ears-0.023
 Horse-0.022
 ear-0.022
Token that
Token ID326
Feature activation-2.05e+00

Pos logit contributions
 no+0.002
 Cle+0.002
 tail+0.002
 ears+0.002
 Horse+0.001
Neg logit contributions
rig-0.008
inner-0.007
pack-0.007
prise-0.007
igsaw-0.007
Token she
Token ID673
Feature activation-7.46e-01

Pos logit contributions
pack+0.091
rig+0.091
inner+0.089
washer+0.086
prise+0.082
Neg logit contributions
 Cle-0.061
 tail-0.060
 Horse-0.056
 prope-0.056
 ears-0.055
Token had
Token ID550
Feature activation-2.85e-01

Pos logit contributions
rig+0.038
inner+0.037
pack+0.037
prise+0.035
washer+0.034
Neg logit contributions
 Cle-0.018
 tail-0.017
 no-0.016
 ears-0.016
 Horse-0.016
Token She
Token ID1375
Feature activation-1.23e-02

Pos logit contributions
 Cle+0.010
 tail+0.010
 Horse+0.009
 ears+0.009
 prope+0.009
Neg logit contributions
rig-0.021
pack-0.021
inner-0.020
washer-0.020
prise-0.019
Token would
Token ID561
Feature activation+2.70e+00

Pos logit contributions
rig+0.001
igsaw+0.001
inner+0.001
prise+0.001
pack+0.001
Neg logit contributions
 no-0.000
 tail-0.000
 ear-0.000
 Cle-0.000
 prope-0.000
Token often
Token ID1690
Feature activation+1.27e+00

Pos logit contributions
 no+0.090
 tail+0.086
 ear+0.083
 prope+0.082
 ears+0.079
Neg logit contributions
rig-0.124
inner-0.107
prise-0.105
igsaw-0.103
pack-0.102
Token make
Token ID787
Feature activation+1.04e+00

Pos logit contributions
 tail+0.039
 ear+0.038
 no+0.038
 ears+0.036
 heart+0.036
Neg logit contributions
rig-0.061
inner-0.057
icy-0.052
pack-0.051
prise-0.051
Token all
Token ID477
Feature activation-2.66e+00

Pos logit contributions
 ears+0.029
 tail+0.028
 Cle+0.027
 no+0.027
 horns+0.025
Neg logit contributions
rig-0.049
inner-0.047
pack-0.046
prise-0.044
washer-0.044
Token sorts
Token ID10524
Feature activation-5.59e+00

Pos logit contributions
rig+0.130
inner+0.121
pack+0.118
prise+0.117
washer+0.111
Neg logit contributions
 heart-0.069
 tail-0.069
 no-0.067
 ear-0.065
 ears-0.062
Token of
Token ID286
Feature activation-1.03e+00

Pos logit contributions
rig+0.271
pack+0.270
inner+0.260
prise+0.245
washer+0.245
Neg logit contributions
 tail-0.141
 Cle-0.137
 no-0.135
 ears-0.132
 goodbye-0.131
Token things
Token ID1243
Feature activation-7.79e-01

Pos logit contributions
rig+0.050
pack+0.050
inner+0.049
prise+0.046
washer+0.046
Neg logit contributions
 ears-0.026
 tail-0.025
 Cle-0.023
 heart-0.023
 horns-0.022
Token out
Token ID503
Feature activation-1.63e+00

Pos logit contributions
rig+0.046
inner+0.044
pack+0.043
prise+0.042
off+0.040
Neg logit contributions
 no-0.013
 tail-0.011
 Cle-0.011
 ears-0.011
 Spark-0.009
Token of
Token ID286
Feature activation-1.38e-01

Pos logit contributions
rig+0.076
pack+0.073
inner+0.072
prise+0.066
washer+0.065
Neg logit contributions
 tail-0.047
 Cle-0.046
 no-0.045
 ears-0.045
 ear-0.043
Token paper
Token ID3348
Feature activation-5.66e-01

Pos logit contributions
rig+0.007
inner+0.006
pack+0.006
prise+0.006
washer+0.006
Neg logit contributions
 ears-0.004
 tail-0.004
 Cle-0.004
joy-0.004
 ear-0.004
Token and
Token ID290
Feature activation+1.19e-01

Pos logit contributions
 Cle+0.061
 tail+0.054
 prope+0.054
 Horse+0.053
 ears+0.052
Neg logit contributions
rig-0.056
washer-0.056
pack-0.055
 else-0.054
inner-0.052
Token taught
Token ID7817
Feature activation+1.84e+00

Pos logit contributions
 Cle+0.004
 Horse+0.004
 prope+0.004
 tail+0.004
Leave+0.004
Neg logit contributions
washer-0.004
 else-0.004
rig-0.004
pack-0.004
ade-0.004
Token the
Token ID262
Feature activation-2.25e+00

Pos logit contributions
 Cle+0.058
 tail+0.056
 prope+0.053
 Horse+0.053
 ears+0.051
Neg logit contributions
rig-0.081
pack-0.078
inner-0.076
washer-0.072
off-0.071
Token animals
Token ID4695
Feature activation-9.37e-02

Pos logit contributions
rig+0.105
inner+0.099
pack+0.099
washer+0.096
ade+0.094
Neg logit contributions
 Cle-0.064
 tail-0.059
 prope-0.058
Leave-0.055
 ear-0.054
Token all
Token ID477
Feature activation-3.30e+00

Pos logit contributions
rig+0.004
pack+0.004
inner+0.004
washer+0.004
prise+0.004
Neg logit contributions
 tail-0.003
 Cle-0.003
 no-0.003
 ears-0.003
 goodbye-0.003
Token sorts
Token ID10524
Feature activation-5.65e+00

Pos logit contributions
pack+0.147
inner+0.144
rig+0.143
prise+0.135
washer+0.133
Neg logit contributions
 tail-0.104
 Cle-0.098
 no-0.095
 ears-0.094
 goodbye-0.094
Token of
Token ID286
Feature activation-9.58e-01

Pos logit contributions
rig+0.251
pack+0.250
inner+0.242
washer+0.226
prise+0.225
Neg logit contributions
 tail-0.168
 Cle-0.167
 no-0.160
 goodbye-0.158
 ear-0.155
Token things
Token ID1243
Feature activation-9.78e-01

Pos logit contributions
pack+0.041
inner+0.040
rig+0.040
washer+0.038
prise+0.036
Neg logit contributions
 tail-0.032
 Cle-0.031
 ears-0.030
 ear-0.029
 prope-0.029
Token.
Token ID13
Feature activation+1.95e-01

Pos logit contributions
rig+0.051
pack+0.051
inner+0.051
prise+0.048
washer+0.046
Neg logit contributions
 no-0.021
 tail-0.021
 Cle-0.020
 goodbye-0.020
 ears-0.019
Token They
Token ID1119
Feature activation+2.66e-01

Pos logit contributions
 Cle+0.006
 tail+0.005
 prope+0.005
 Horse+0.005
 ears+0.005
Neg logit contributions
rig-0.009
pack-0.009
inner-0.009
washer-0.008
off-0.008
Token taught
Token ID7817
Feature activation+1.72e+00

Pos logit contributions
 Cle+0.009
 tail+0.008
 Horse+0.008
 ears+0.008
joy+0.008
Neg logit contributions
rig-0.011
pack-0.011
inner-0.011
washer-0.011
ade-0.010