TOP ACTIVATIONS
MAX = 6.172

Can we make a vacation coll age ?" Leo asked .
. There were neck l aces and rings with spark les
pond . It was a tort oise ! The all igator
Jack . Jack had a sword that he loved to play
crown . Ben wore a cape and a hat .
time there was an enormous tort oise who always wished for
These are beautiful neck l aces and brace lets . You
" I need a tw ig to build my nest ."
She wanted to make a coll age out of the beautiful
want to make neck l aces and brace lets with them
. Tim had a lucky er aser . The er aser
shapes . They make a coll age of a farm .
. He had a shiny sword that he loved to show
clown s juggling and ac rob ats doing flips . But
plan was to make a coll age with pictures from a
a little boy wearing a superhero costume . She said ,
. He had a band age on his paw .
He always had a tw ig in his hand so he
S ara loved neck l aces . She nodded and reached
. Lily had a pink er aser that she used to

MIN ACTIVATIONS
MIN = -6.225

and crept back to the dining room . She felt very
and sniff ing all the smells . John jumped into a
him and ran to the dining room . She saw the
tell stories around the camp fire . <|endoftext|> Once upon a
and the lightning struck the hyd rant . Suddenly water was
The bottle lands in the boiling soup and spl ashes everywhere
every bite of the ste aming hot pasta and enjoyed the
m allows over the camp fire . One
it come out of the seaw eed and walk around the
hand and walk to the dining room . They sit on
her mom standing over the stove . " What
He carried it to the dining room and set it on
owner and sniff all the smells in the park . One
let 's go to the dining room and have a snack
. Emily accidentally knocked the stove off the counter ! She
the kind lady behind the counter . As
to see her Mum be aming with pride . Sarah knew
around the hallway , the dining room and the bedroom .
sweet scent of the camp fire . When
to be careful around the stove when her mom my was

INTERVAL 3.073 - 6.172
CONTAINS 0.515%

you can always find a friend to explore the world with
the road . Bobby had never seen one before and he
man e and a big tail . He was very alert
. She had a red bike that she loved to ride
Benny was a very good friend . The end . <|endoftext|>

INTERVAL -0.027 - 3.073
CONTAINS 49.588%

this beautiful thing will still be here when you come back
and went to play on the swings . <|endoftext|> Once upon
smelled bad . " Y uck !" Lily said
on the grass . Soon , Maya cheered up and felt
? â € The troll replied , � � € �

INTERVAL -3.126 - -0.027
CONTAINS 49.368%

. " Can we go , mom ?" Lily
an incredible day , made even better by the mail she
. The life knew it had to find
Roger was so happy . He gave the puppy
and get it back ." L ily and her

INTERVAL -6.225 - -3.126
CONTAINS 0.530%

reach the top of the wall to paint ?" Tim asked
a big cake on the table . It is purple too
something special to offer , like Billy 's powerful shots in
bottle of wine on the table . They did not know
letting him play with the amazing je ep . Lily smiled
TokenCan
Token ID6090
Feature activation-1.79e+00

Pos logit contributions
oot+0.039
aces+0.038
emaker+0.035
 runner+0.035
 racer+0.033
Neg logit contributions
 bowls-0.036
 erupt-0.034
 boiling-0.034
 frying-0.034
 hyd-0.034
Token we
Token ID356
Feature activation-1.31e+00

Pos logit contributions
 bowls+0.050
 erupt+0.048
 Dad+0.048
 hyd+0.047
 frying+0.046
Neg logit contributions
aces-0.077
oot-0.077
emaker-0.071
iest-0.068
 runner-0.068
Token make
Token ID787
Feature activation+3.82e-01

Pos logit contributions
 bowls+0.038
 frying+0.036
 boiling+0.036
 hyd+0.035
 erupt+0.035
Neg logit contributions
oot-0.056
aces-0.055
emaker-0.050
 runner-0.049
ance-0.048
Token a
Token ID257
Feature activation+6.99e-01

Pos logit contributions
oot+0.013
aces+0.012
ance+0.011
orns+0.010
emaker+0.010
Neg logit contributions
 hyd-0.014
 frying-0.014
ksh-0.014
 boiling-0.013
 bowls-0.013
Token vacation
Token ID14600
Feature activation-1.56e-02

Pos logit contributions
oot+0.025
 racer+0.025
 runner+0.025
aces+0.023
affe+0.022
Neg logit contributions
ksh-0.021
 bowls-0.020
 frying-0.020
 hyd-0.020
 boiling-0.019
Token coll
Token ID2927
Feature activation+6.17e+00

Pos logit contributions
 bowls+0.001
 boiling+0.001
 frying+0.001
ksh+0.001
 hyd+0.001
Neg logit contributions
oot-0.000
aces-0.000
iest-0.000
 runner-0.000
 racer-0.000
Tokenage
Token ID496
Feature activation+5.42e+00

Pos logit contributions
oot+0.169
aces+0.167
emaker+0.156
 runner+0.156
ance+0.143
Neg logit contributions
 bowls-0.249
 hyd-0.245
 burgers-0.240
 erupt-0.236
 grill-0.236
Token?"
Token ID1701
Feature activation+5.47e-01

Pos logit contributions
aces+0.204
oot+0.203
emaker+0.187
 runner+0.178
ance+0.171
Neg logit contributions
 bowls-0.181
 erupt-0.176
 hyd-0.174
 frying-0.172
 boiling-0.171
Token Leo
Token ID19632
Feature activation-5.03e-01

Pos logit contributions
oot+0.021
aces+0.021
emaker+0.019
 runner+0.019
ance+0.018
Neg logit contributions
 bowls-0.017
 frying-0.017
 erupt-0.017
 hyd-0.017
 boiling-0.017
Token asked
Token ID1965
Feature activation+8.88e-01

Pos logit contributions
 bowls+0.017
 hyd+0.017
 frying+0.017
 boiling+0.016
 burgers+0.016
Neg logit contributions
oot-0.018
aces-0.018
emaker-0.017
 runner-0.016
py-0.016
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
oot+0.039
aces+0.038
emaker+0.035
 runner+0.034
ance+0.033
Neg logit contributions
 bowls-0.026
 boiling-0.023
 erupt-0.023
 frying-0.023
 Dad-0.023
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
oot+0.123
aces+0.122
emaker+0.115
 runner+0.109
ance+0.106
Neg logit contributions
 bowls-0.099
 frying-0.093
 hyd-0.092
 boiling-0.092
 erupt-0.090
Token There
Token ID1318
Feature activation-1.30e-01

Pos logit contributions
oot+0.005
aces+0.005
emaker+0.005
iest+0.004
 runner+0.004
Neg logit contributions
 bowls-0.004
 frying-0.003
 boiling-0.003
 erupt-0.003
 hyd-0.003
Token were
Token ID547
Feature activation-1.41e+00

Pos logit contributions
ksh+0.005
 frying+0.005
 bowls+0.005
 hyd+0.005
 erupt+0.005
Neg logit contributions
oot-0.004
aces-0.004
emaker-0.004
iest-0.004
ance-0.004
Token neck
Token ID7393
Feature activation+4.39e+00

Pos logit contributions
 bowls+0.044
 frying+0.042
 boiling+0.041
 erupt+0.041
 hyd+0.041
Neg logit contributions
oot-0.057
aces-0.056
emaker-0.052
 runner-0.050
ance-0.048
Tokenl
Token ID75
Feature activation+1.66e+00

Pos logit contributions
oot+0.146
aces+0.142
emaker+0.134
 runner+0.131
mate+0.127
Neg logit contributions
 bowls-0.166
 frying-0.160
 erupt-0.156
 boiling-0.155
 y-0.152
Tokenaces
Token ID2114
Feature activation+6.10e+00

Pos logit contributions
oot+0.016
emaker+0.012
mate+0.012
 runner+0.010
 racer+0.009
Neg logit contributions
 bowls-0.098
 frying-0.095
 erupt-0.093
 pasta-0.093
 boiling-0.092
Token and
Token ID290
Feature activation-3.91e-03

Pos logit contributions
oot+0.244
emaker+0.241
mate+0.239
aces+0.238
 runner+0.229
Neg logit contributions
 bowls-0.169
 erupt-0.158
 frying-0.157
 clean-0.156
 boiling-0.155
Token rings
Token ID13917
Feature activation+2.88e+00

Pos logit contributions
 bowls+0.000
 y+0.000
 delicious+0.000
 pasta+0.000
 un+0.000
Neg logit contributions
oot-0.000
emaker-0.000
ross-0.000
mate-0.000
 runner-0.000
Token with
Token ID351
Feature activation-6.62e-01

Pos logit contributions
oot+0.119
emaker+0.116
aces+0.113
 runner+0.109
ross+0.107
Neg logit contributions
 bowls-0.080
 y-0.076
 erupt-0.075
 delicious-0.075
 frying-0.072
Token spark
Token ID9009
Feature activation-3.95e-01

Pos logit contributions
 bowls+0.021
 y+0.019
 boiling+0.019
 frying+0.018
 burgers+0.018
Neg logit contributions
oot-0.028
aces-0.026
emaker-0.025
 runner-0.024
ross-0.024
Tokenles
Token ID829
Feature activation+8.58e-01

Pos logit contributions
 bowls+0.016
 frying+0.015
 y+0.015
ksh+0.015
 pasta+0.015
Neg logit contributions
oot-0.012
aces-0.011
emaker-0.011
 runner-0.011
mate-0.011
Token pond
Token ID16723
Feature activation-3.25e+00

Pos logit contributions
ksh+0.017
 las+0.016
 apr+0.016
 frying+0.016
 hyd+0.016
Neg logit contributions
aces-0.021
 runner-0.020
orns-0.020
oot-0.020
iest-0.019
Token.
Token ID13
Feature activation-9.79e-02

Pos logit contributions
 bowls+0.117
 frying+0.115
ksh+0.112
 hyd+0.110
 boiling+0.110
Neg logit contributions
aces-0.112
oot-0.111
emaker-0.096
 runner-0.093
iest-0.093
Token It
Token ID632
Feature activation+3.62e-01

Pos logit contributions
 bowls+0.004
 frying+0.004
 hyd+0.004
 boiling+0.004
 erupt+0.004
Neg logit contributions
aces-0.003
oot-0.003
emaker-0.003
 runner-0.002
ance-0.002
Token was
Token ID373
Feature activation-5.63e-02

Pos logit contributions
aces+0.012
oot+0.012
emaker+0.011
py+0.011
iest+0.011
Neg logit contributions
 bowls-0.013
 frying-0.013
 hyd-0.012
 burgers-0.012
ksh-0.012
Token a
Token ID257
Feature activation+3.93e-01

Pos logit contributions
 bowls+0.002
ksh+0.002
 frying+0.002
 hyd+0.002
 erupt+0.002
Neg logit contributions
aces-0.002
oot-0.002
 runner-0.002
emaker-0.002
py-0.002
Token tort
Token ID7619
Feature activation+6.08e+00

Pos logit contributions
 runner+0.014
 racer+0.014
oot+0.013
mate+0.013
aces+0.012
Neg logit contributions
ksh-0.013
 bowls-0.013
 apr-0.012
 erupt-0.011
 hyd-0.011
Tokenoise
Token ID25678
Feature activation+3.03e+00

Pos logit contributions
aces+0.220
oot+0.205
ance+0.181
 runner+0.179
 villains+0.177
Neg logit contributions
 bowls-0.193
 hyd-0.193
 boiling-0.185
 erupt-0.183
 frying-0.183
Token!
Token ID0
Feature activation-5.40e-01

Pos logit contributions
oot+0.113
aces+0.112
emaker+0.100
 runner+0.098
ance+0.094
Neg logit contributions
 bowls-0.104
 frying-0.099
 erupt-0.098
 boiling-0.098
 hyd-0.098
Token The
Token ID383
Feature activation+7.16e-01

Pos logit contributions
 bowls+0.021
 frying+0.020
 boiling+0.020
 hyd+0.020
 erupt+0.020
Neg logit contributions
oot-0.018
aces-0.018
emaker-0.016
 runner-0.015
ance-0.015
Token all
Token ID477
Feature activation+1.89e-01

Pos logit contributions
oot+0.024
aces+0.024
emaker+0.021
 runner+0.020
ance+0.020
Neg logit contributions
 bowls-0.028
 frying-0.027
 erupt-0.026
 boiling-0.026
 hyd-0.026
Tokenigator
Token ID23823
Feature activation+4.60e-02

Pos logit contributions
oot+0.008
aces+0.008
 runner+0.007
ance+0.007
emaker+0.007
Neg logit contributions
 bowls-0.005
 boiling-0.005
 erupt-0.005
 frying-0.005
 hyd-0.005
Token Jack
Token ID3619
Feature activation-3.04e+00

Pos logit contributions
 hyd+0.028
 erupt+0.028
 frying+0.027
ksh+0.027
 dining+0.027
Neg logit contributions
aces-0.021
oot-0.020
iest-0.019
emaker-0.018
orns-0.018
Token.
Token ID13
Feature activation-4.71e-01

Pos logit contributions
 bowls+0.092
 frying+0.087
 boiling+0.087
 erupt+0.087
 hyd+0.086
Neg logit contributions
oot-0.124
aces-0.123
emaker-0.112
 runner-0.108
ance-0.106
Token Jack
Token ID3619
Feature activation-7.88e-01

Pos logit contributions
 bowls+0.015
 Dad+0.014
 erupt+0.014
 frying+0.014
 grill+0.014
Neg logit contributions
oot-0.019
aces-0.018
emaker-0.017
iest-0.016
 runner-0.016
Token had
Token ID550
Feature activation+2.04e+00

Pos logit contributions
 bowls+0.026
 frying+0.024
 erupt+0.024
 boiling+0.024
 hyd+0.024
Neg logit contributions
aces-0.030
oot-0.030
emaker-0.027
 runner-0.026
ance-0.026
Token a
Token ID257
Feature activation+1.05e+00

Pos logit contributions
oot+0.088
aces+0.086
emaker+0.080
 runner+0.077
ance+0.075
Neg logit contributions
 bowls-0.059
 frying-0.055
 boiling-0.055
 erupt-0.055
 hyd-0.054
Token sword
Token ID8429
Feature activation+6.05e+00

Pos logit contributions
 runner+0.039
 racer+0.038
aces+0.037
oot+0.037
mate+0.036
Neg logit contributions
 bowls-0.032
ksh-0.032
 erupt-0.032
 hyd-0.031
 boiling-0.030
Token that
Token ID326
Feature activation-2.43e-01

Pos logit contributions
oot+0.262
aces+0.251
emaker+0.249
ance+0.240
orns+0.236
Neg logit contributions
 bowls-0.150
 hyd-0.149
 erupt-0.149
 grill-0.147
 dish-0.145
Token he
Token ID339
Feature activation-3.23e-04

Pos logit contributions
 bowls+0.010
 frying+0.009
 boiling+0.009
 erupt+0.009
 hyd+0.009
Neg logit contributions
oot-0.008
aces-0.007
emaker-0.007
 runner-0.006
ance-0.006
Token loved
Token ID6151
Feature activation-1.59e+00

Pos logit contributions
 bowls+0.000
 hyd+0.000
 frying+0.000
 erupt+0.000
 y+0.000
Neg logit contributions
oot-0.000
aces-0.000
emaker-0.000
ance-0.000
 runner-0.000
Token to
Token ID284
Feature activation+8.38e-01

Pos logit contributions
 bowls+0.051
 erupt+0.048
 boiling+0.048
 frying+0.047
 burgers+0.047
Neg logit contributions
oot-0.064
aces-0.063
emaker-0.058
 runner-0.055
ance-0.055
Token play
Token ID711
Feature activation+1.80e+00

Pos logit contributions
oot+0.043
ross+0.042
emaker+0.041
aces+0.041
ance+0.040
Neg logit contributions
 stir-0.019
 cook-0.018
 clean-0.017
 un-0.017
 erupt-0.016
Token crown
Token ID12389
Feature activation+4.88e+00

Pos logit contributions
aces+0.039
oot+0.039
 runner+0.036
emaker+0.035
 racer+0.034
Neg logit contributions
 bowls-0.029
 erupt-0.028
 hyd-0.027
 frying-0.027
 boiling-0.027
Token.
Token ID13
Feature activation-3.28e-01

Pos logit contributions
oot+0.203
aces+0.199
emaker+0.189
Loop+0.186
orns+0.185
Neg logit contributions
 bowls-0.128
 hyd-0.128
 pan-0.124
 erupt-0.123
 cook-0.123
Token Ben
Token ID3932
Feature activation-7.49e-02

Pos logit contributions
 bowls+0.011
 frying+0.010
 erupt+0.010
 boiling+0.010
 hyd+0.010
Neg logit contributions
oot-0.013
aces-0.013
emaker-0.012
iest-0.011
 runner-0.011
Token wore
Token ID12408
Feature activation+2.80e+00

Pos logit contributions
 bowls+0.003
 erupt+0.003
 boiling+0.003
 frying+0.003
 hyd+0.003
Neg logit contributions
aces-0.003
oot-0.002
 runner-0.002
ance-0.002
emaker-0.002
Token a
Token ID257
Feature activation+1.06e+00

Pos logit contributions
oot+0.144
emaker+0.135
aces+0.132
ross+0.126
 runner+0.124
Neg logit contributions
 bowls-0.066
 y-0.061
 pasta-0.059
 frying-0.057
 boiling-0.057
Token cape
Token ID36023
Feature activation+6.03e+00

Pos logit contributions
oot+0.048
aces+0.046
emaker+0.044
ance+0.043
ross+0.041
Neg logit contributions
 bowls-0.030
 frying-0.028
 boiling-0.028
 y-0.027
 bowl-0.027
Token and
Token ID290
Feature activation+5.37e-01

Pos logit contributions
emaker+0.293
oot+0.290
ross+0.283
reetings+0.279
orns+0.276
Neg logit contributions
 clean-0.105
 bowls-0.101
 hyd-0.100
 pan-0.099
 dish-0.098
Token a
Token ID257
Feature activation+1.03e+00

Pos logit contributions
oot+0.029
emaker+0.027
aces+0.025
mate+0.025
ross+0.025
Neg logit contributions
 bowls-0.012
 y-0.011
 un-0.011
 pasta-0.011
 stir-0.011
Token hat
Token ID6877
Feature activation+3.22e+00

Pos logit contributions
oot+0.042
aces+0.039
emaker+0.037
ance+0.037
ross+0.034
Neg logit contributions
 bowls-0.035
 bowl-0.033
 frying-0.033
 y-0.033
 pan-0.033
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
oot+0.149
emaker+0.149
ross+0.143
reetings+0.143
orns+0.139
Neg logit contributions
 bowls-0.068
 hyd-0.065
 dish-0.064
 cook-0.064
 bowl-0.063
Token
Token ID198
Feature activation-3.66e-01

Pos logit contributions
 bowls+0.008
 frying+0.007
 boiling+0.007
 erupt+0.007
 hyd+0.007
Neg logit contributions
oot-0.008
aces-0.008
emaker-0.007
 runner-0.007
iest-0.007
Token time
Token ID640
Feature activation+5.91e-01

Pos logit contributions
 hyd+0.024
 bowls+0.023
 boiling+0.023
 frying+0.023
 erupt+0.023
Neg logit contributions
aces-0.013
 runner-0.012
oot-0.012
emaker-0.011
 racer-0.011
Token there
Token ID612
Feature activation+5.88e-01

Pos logit contributions
oot+0.018
aces+0.018
emaker+0.016
 runner+0.015
ance+0.015
Neg logit contributions
 bowls-0.024
 frying-0.023
 erupt-0.023
 boiling-0.023
 hyd-0.023
Token was
Token ID373
Feature activation+3.67e-01

Pos logit contributions
oot+0.020
aces+0.020
emaker+0.019
iest+0.018
 runner+0.018
Neg logit contributions
 bowls-0.021
 frying-0.021
ksh-0.021
 boiling-0.020
 burgers-0.020
Token an
Token ID281
Feature activation+6.25e-01

Pos logit contributions
aces+0.014
oot+0.013
 runner+0.012
emaker+0.012
py+0.011
Neg logit contributions
 bowls-0.012
 hyd-0.012
 frying-0.012
 erupt-0.012
ksh-0.012
Token enormous
Token ID9812
Feature activation-5.24e-01

Pos logit contributions
oot+0.024
aces+0.023
 runner+0.021
py+0.020
emaker+0.020
Neg logit contributions
 bowls-0.021
 frying-0.020
ksh-0.020
 hyd-0.020
 erupt-0.020
Token tort
Token ID7619
Feature activation+6.00e+00

Pos logit contributions
 bowls+0.018
 frying+0.017
 erupt+0.017
 hyd+0.017
 boiling+0.017
Neg logit contributions
oot-0.019
aces-0.018
 runner-0.017
emaker-0.017
 racer-0.016
Tokenoise
Token ID25678
Feature activation+2.36e+00

Pos logit contributions
aces+0.220
oot+0.207
affe+0.185
br+0.183
 villains+0.182
Neg logit contributions
 bowls-0.187
 hyd-0.180
 boiling-0.177
 frying-0.176
 cooking-0.173
Token who
Token ID508
Feature activation-2.51e-01

Pos logit contributions
aces+0.099
oot+0.098
emaker+0.091
ance+0.087
 runner+0.086
Neg logit contributions
 bowls-0.068
 hyd-0.065
 frying-0.065
 boiling-0.064
 grill-0.063
Token always
Token ID1464
Feature activation+2.10e+00

Pos logit contributions
 bowls+0.009
 frying+0.009
 boiling+0.009
 erupt+0.009
 hyd+0.009
Neg logit contributions
oot-0.009
aces-0.009
emaker-0.008
 runner-0.007
ance-0.007
Token wished
Token ID16555
Feature activation+1.37e+00

Pos logit contributions
oot+0.086
aces+0.085
emaker+0.079
 runner+0.074
orns+0.073
Neg logit contributions
 hyd-0.062
 bowls-0.061
 erupt-0.061
 frying-0.060
 boiling-0.059
Token for
Token ID329
Feature activation+3.63e-01

Pos logit contributions
oot+0.053
aces+0.052
emaker+0.051
 runner+0.047
orns+0.046
Neg logit contributions
 bowls-0.044
 boiling-0.043
 burgers-0.042
 erupt-0.042
 pasta-0.042
TokenThese
Token ID4711
Feature activation+5.82e-02

Pos logit contributions
 bowls+0.022
 frying+0.021
 boiling+0.020
 erupt+0.020
 burgers+0.020
Neg logit contributions
oot-0.019
aces-0.019
emaker-0.018
 runner-0.017
mate-0.016
Token are
Token ID389
Feature activation-3.02e+00

Pos logit contributions
aces+0.002
oot+0.002
emaker+0.002
 runner+0.002
ance+0.002
Neg logit contributions
 bowls-0.002
 hyd-0.002
 frying-0.002
 boiling-0.002
 erupt-0.002
Token beautiful
Token ID4950
Feature activation-9.35e-01

Pos logit contributions
 bowls+0.087
 frying+0.084
 hyd+0.083
 boiling+0.082
ksh+0.081
Neg logit contributions
aces-0.127
oot-0.125
emaker-0.111
 runner-0.109
ance-0.107
Token neck
Token ID7393
Feature activation+4.15e+00

Pos logit contributions
 bowls+0.031
 frying+0.028
 boiling+0.028
 hyd+0.028
 grill+0.028
Neg logit contributions
oot-0.038
aces-0.036
emaker-0.034
ance-0.032
 runner-0.032
Tokenl
Token ID75
Feature activation+2.04e+00

Pos logit contributions
oot+0.159
aces+0.154
emaker+0.148
 runner+0.146
mate+0.140
Neg logit contributions
 bowls-0.133
 frying-0.128
 boiling-0.125
 erupt-0.125
 hyd-0.124
Tokenaces
Token ID2114
Feature activation+6.00e+00

Pos logit contributions
oot+0.055
emaker+0.048
mate+0.047
 racer+0.046
 runner+0.046
Neg logit contributions
 bowls-0.082
 erupt-0.082
 hyd-0.078
ksh-0.078
 pasta-0.077
Token and
Token ID290
Feature activation-2.53e-01

Pos logit contributions
oot+0.231
aces+0.221
emaker+0.219
 runner+0.210
mate+0.206
Neg logit contributions
 bowls-0.184
 erupt-0.179
 frying-0.172
 hyd-0.171
 boiling-0.168
Token brace
Token ID22581
Feature activation+5.28e+00

Pos logit contributions
 bowls+0.008
 y+0.008
 stir+0.007
 un+0.007
 erupt+0.007
Neg logit contributions
oot-0.011
emaker-0.010
ross-0.009
 runner-0.009
mate-0.009
Tokenlets
Token ID5289
Feature activation+4.00e+00

Pos logit contributions
emaker+0.181
oot+0.178
 runner+0.176
ross+0.175
iest+0.172
Neg logit contributions
ksh-0.156
 slice-0.150
 bowls-0.145
 appet-0.141
 y-0.140
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
oot+0.168
aces+0.158
emaker+0.158
 runner+0.153
 racer+0.148
Neg logit contributions
 bowls-0.116
 erupt-0.103
 hyd-0.102
 boiling-0.102
 frying-0.101
Token You
Token ID921
Feature activation+5.62e-01

Pos logit contributions
oot+0.007
emaker+0.007
aces+0.007
iest+0.007
ross+0.006
Neg logit contributions
 bowls-0.005
 Dad-0.005
ksh-0.005
 hyd-0.005
 stir-0.005
Token "
Token ID366
Feature activation+2.67e-01

Pos logit contributions
 bowls+0.019
 erupt+0.018
 frying+0.018
 hyd+0.018
 boiling+0.018
Neg logit contributions
oot-0.026
aces-0.026
emaker-0.024
iest-0.023
 runner-0.023
TokenI
Token ID40
Feature activation-3.14e-01

Pos logit contributions
oot+0.011
aces+0.011
emaker+0.010
 runner+0.010
ance+0.009
Neg logit contributions
 bowls-0.008
 hyd-0.008
 frying-0.008
 erupt-0.008
 boiling-0.008
Token need
Token ID761
Feature activation+1.13e+00

Pos logit contributions
 bowls+0.010
 frying+0.009
 boiling+0.009
 erupt+0.009
 burgers+0.009
Neg logit contributions
oot-0.013
aces-0.012
emaker-0.011
 runner-0.011
iest-0.011
Token a
Token ID257
Feature activation+8.64e-01

Pos logit contributions
oot+0.053
aces+0.052
emaker+0.051
 runner+0.049
 racer+0.046
Neg logit contributions
 bowls-0.029
 boiling-0.028
 pasta-0.027
 y-0.027
 burgers-0.026
Token tw
Token ID665
Feature activation+3.03e+00

Pos logit contributions
oot+0.033
aces+0.032
 runner+0.030
emaker+0.029
 racer+0.029
Neg logit contributions
 bowls-0.028
ksh-0.026
 frying-0.026
 boiling-0.026
 hyd-0.026
Tokenig
Token ID328
Feature activation+5.97e+00

Pos logit contributions
oot+0.082
aces+0.080
emaker+0.076
 villains+0.076
ance+0.072
Neg logit contributions
 bowls-0.119
 pan-0.118
 stir-0.116
 frying-0.116
 bowl-0.115
Token to
Token ID284
Feature activation+4.44e-01

Pos logit contributions
oot+0.237
emaker+0.233
 villains+0.230
aces+0.230
 runner+0.228
Neg logit contributions
 clean-0.152
 hyd-0.152
 pot-0.151
 bowls-0.148
 pan-0.147
Token build
Token ID1382
Feature activation+1.08e+00

Pos logit contributions
oot+0.021
aces+0.020
emaker+0.019
 runner+0.019
ross+0.018
Neg logit contributions
 stir-0.011
 bowls-0.011
 clean-0.011
 erupt-0.011
 sink-0.010
Token my
Token ID616
Feature activation+1.33e+00

Pos logit contributions
oot+0.046
aces+0.045
emaker+0.042
 runner+0.041
ance+0.039
Neg logit contributions
 bowls-0.031
 erupt-0.029
 boiling-0.029
 frying-0.029
 hyd-0.029
Token nest
Token ID16343
Feature activation+1.73e+00

Pos logit contributions
oot+0.054
aces+0.053
emaker+0.049
 runner+0.046
ance+0.045
Neg logit contributions
 bowls-0.042
 frying-0.039
 erupt-0.039
 boiling-0.039
 hyd-0.039
Token."
Token ID526
Feature activation-4.69e-01

Pos logit contributions
oot+0.068
aces+0.066
emaker+0.063
 runner+0.060
ance+0.058
Neg logit contributions
 bowls-0.056
 hyd-0.053
 erupt-0.053
 frying-0.052
 boiling-0.051
Token She
Token ID1375
Feature activation+6.80e-01

Pos logit contributions
aces+0.000
oot+0.000
emaker+0.000
 runner+0.000
ance+0.000
Neg logit contributions
 bowls-0.000
 hyd-0.000
 frying-0.000
 erupt-0.000
 boiling-0.000
Token wanted
Token ID2227
Feature activation-2.51e-01

Pos logit contributions
oot+0.028
aces+0.028
emaker+0.025
 runner+0.024
ance+0.024
Neg logit contributions
 bowls-0.020
 frying-0.019
 erupt-0.019
 hyd-0.019
ksh-0.019
Token to
Token ID284
Feature activation-3.37e-01

Pos logit contributions
 hyd+0.010
ksh+0.010
 bowls+0.009
 frying+0.009
 boiling+0.009
Neg logit contributions
oot-0.008
aces-0.008
emaker-0.007
iest-0.007
ance-0.007
Token make
Token ID787
Feature activation+2.02e-01

Pos logit contributions
 bowls+0.009
 erupt+0.009
 frying+0.009
 boiling+0.009
 hyd+0.009
Neg logit contributions
oot-0.015
aces-0.015
emaker-0.014
 runner-0.013
ance-0.013
Token a
Token ID257
Feature activation-6.19e-02

Pos logit contributions
aces+0.006
oot+0.006
ance+0.005
iest+0.005
py+0.005
Neg logit contributions
ksh-0.008
 frying-0.008
 hyd-0.008
 appet-0.007
 boiling-0.007
Token coll
Token ID2927
Feature activation+5.96e+00

Pos logit contributions
ksh+0.002
 bowls+0.002
 frying+0.002
 boiling+0.002
 hyd+0.002
Neg logit contributions
 racer-0.002
 runner-0.002
oot-0.002
mate-0.002
affe-0.002
Tokenage
Token ID496
Feature activation+5.47e+00

Pos logit contributions
aces+0.113
oot+0.113
emaker+0.096
 runner+0.095
ance+0.086
Neg logit contributions
 bowls-0.298
 hyd-0.294
 erupt-0.290
 frying-0.287
 burgers-0.286
Token out
Token ID503
Feature activation-1.11e+00

Pos logit contributions
oot+0.190
aces+0.188
emaker+0.169
 runner+0.162
ance+0.158
Neg logit contributions
 bowls-0.200
 frying-0.191
 boiling-0.190
 erupt-0.190
 hyd-0.189
Token of
Token ID286
Feature activation+5.94e-01

Pos logit contributions
 bowls+0.052
 boiling+0.050
 erupt+0.050
 frying+0.050
 hyd+0.049
Neg logit contributions
oot-0.028
aces-0.028
emaker-0.024
 runner-0.022
ance-0.022
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
aces+0.024
oot+0.024
emaker+0.022
 runner+0.022
iest+0.021
Neg logit contributions
 bowls-0.017
ksh-0.016
 frying-0.016
 hyd-0.016
 erupt-0.016
Token beautiful
Token ID4950
Feature activation-2.87e+00

Pos logit contributions
aces+0.038
oot+0.037
emaker+0.034
 runner+0.034
orns+0.032
Neg logit contributions
 bowls-0.032
 erupt-0.032
 frying-0.031
 boiling-0.031
 hyd-0.031
Token want
Token ID765
Feature activation-1.50e+00

Pos logit contributions
aces+0.005
oot+0.004
 runner+0.004
ance+0.004
emaker+0.004
Neg logit contributions
ksh-0.003
 bowls-0.003
 burgers-0.003
 boiling-0.003
 frying-0.003
Token to
Token ID284
Feature activation+3.06e-01

Pos logit contributions
ksh+0.068
 hyd+0.064
rig+0.063
 frying+0.063
 erupt+0.061
Neg logit contributions
oot-0.035
aces-0.034
ance-0.029
iest-0.028
mate-0.027
Token make
Token ID787
Feature activation+2.30e-01

Pos logit contributions
oot+0.014
aces+0.014
emaker+0.013
 runner+0.012
ance+0.012
Neg logit contributions
 bowls-0.008
 frying-0.008
 boiling-0.008
 hyd-0.007
 erupt-0.007
Token neck
Token ID7393
Feature activation+4.41e+00

Pos logit contributions
oot+0.006
aces+0.006
ance+0.005
er+0.004
 herself+0.004
Neg logit contributions
ksh-0.009
 appet-0.009
 frying-0.009
 hyd-0.009
rig-0.009
Tokenl
Token ID75
Feature activation+2.00e+00

Pos logit contributions
oot+0.127
aces+0.125
emaker+0.112
 runner+0.110
ance+0.103
Neg logit contributions
 bowls-0.187
 erupt-0.180
 frying-0.179
 boiling-0.177
 hyd-0.176
Tokenaces
Token ID2114
Feature activation+5.94e+00

Pos logit contributions
oot+0.012
 runner+0.009
mate+0.008
emaker+0.007
 racer+0.005
Neg logit contributions
 bowls-0.124
 erupt-0.122
ksh-0.119
 y-0.118
 stir-0.118
Token and
Token ID290
Feature activation-1.25e-01

Pos logit contributions
oot+0.235
aces+0.230
emaker+0.229
ance+0.216
 runner+0.216
Neg logit contributions
 bowls-0.171
 erupt-0.166
 clean-0.162
 y-0.157
 hyd-0.155
Token brace
Token ID22581
Feature activation+5.10e+00

Pos logit contributions
 bowls+0.004
 y+0.004
 un+0.004
 stir+0.004
 sp+0.003
Neg logit contributions
oot-0.006
emaker-0.005
ross-0.005
 runner-0.005
mate-0.005
Tokenlets
Token ID5289
Feature activation+3.90e+00

Pos logit contributions
emaker+0.170
oot+0.168
iest+0.161
ross+0.161
 runner+0.161
Neg logit contributions
ksh-0.162
 bowls-0.158
 slice-0.154
 y-0.149
 erupt-0.146
Token with
Token ID351
Feature activation-3.32e-01

Pos logit contributions
oot+0.168
aces+0.161
emaker+0.159
 runner+0.153
ross+0.148
Neg logit contributions
 bowls-0.109
 erupt-0.099
 hyd-0.097
 bowl-0.095
 pasta-0.095
Token them
Token ID606
Feature activation-1.25e+00

Pos logit contributions
 bowls+0.010
 y+0.010
 un+0.009
 erupt+0.009
 delicious+0.009
Neg logit contributions
oot-0.015
emaker-0.013
aces-0.013
ross-0.013
 runner-0.013
Token.
Token ID13
Feature activation+4.51e-01

Pos logit contributions
 bowls+0.028
 frying+0.026
 hyd+0.026
 erupt+0.026
 boiling+0.026
Neg logit contributions
oot-0.036
aces-0.036
emaker-0.032
 runner-0.032
ance-0.031
Token Tim
Token ID5045
Feature activation+6.84e-01

Pos logit contributions
oot+0.019
aces+0.019
emaker+0.017
 runner+0.017
ance+0.016
Neg logit contributions
 bowls-0.013
 erupt-0.013
 boiling-0.013
 frying-0.013
 hyd-0.013
Token had
Token ID550
Feature activation+2.49e+00

Pos logit contributions
aces+0.023
oot+0.022
emaker+0.020
 runner+0.019
py+0.019
Neg logit contributions
 bowls-0.027
 boiling-0.025
 frying-0.025
 burgers-0.025
 erupt-0.025
Token a
Token ID257
Feature activation+1.33e+00

Pos logit contributions
oot+0.123
aces+0.117
emaker+0.112
 runner+0.106
iest+0.105
Neg logit contributions
 bowls-0.059
 frying-0.057
 boiling-0.055
 y-0.054
 erupt-0.054
Token lucky
Token ID9670
Feature activation+1.61e-01

Pos logit contributions
 runner+0.046
oot+0.044
 racer+0.044
aces+0.044
mate+0.040
Neg logit contributions
ksh-0.045
 bowls-0.045
 erupt-0.044
 boiling-0.043
 hyd-0.042
Token er
Token ID1931
Feature activation+5.92e+00

Pos logit contributions
oot+0.006
aces+0.006
emaker+0.005
 runner+0.005
 racer+0.005
Neg logit contributions
 bowls-0.005
 frying-0.005
 boiling-0.005
 erupt-0.005
 hyd-0.005
Tokenaser
Token ID6005
Feature activation+4.98e+00

Pos logit contributions
ross+0.170
reetings+0.161
anced+0.151
aces+0.147
 villains+0.143
Neg logit contributions
 dish-0.209
washer-0.207
 pasta-0.205
 else-0.202
 bowls-0.201
Token.
Token ID13
Feature activation+6.80e-01

Pos logit contributions
oot+0.230
emaker+0.228
reetings+0.227
anced+0.223
aces+0.219
Neg logit contributions
 dish-0.109
 pasta-0.102
 pan-0.099
 frying-0.098
 pot-0.098
Token The
Token ID383
Feature activation+1.31e+00

Pos logit contributions
oot+0.023
aces+0.022
emaker+0.020
 runner+0.019
ance+0.019
Neg logit contributions
 bowls-0.026
 erupt-0.025
 frying-0.025
 boiling-0.025
 hyd-0.024
Token er
Token ID1931
Feature activation+3.72e+00

Pos logit contributions
oot+0.055
aces+0.053
ance+0.048
emaker+0.048
ross+0.048
Neg logit contributions
 dish-0.040
 bowls-0.038
 pasta-0.038
 y-0.037
 bowl-0.037
Tokenaser
Token ID6005
Feature activation+2.95e+00

Pos logit contributions
ross+0.110
oot+0.101
anced+0.099
reetings+0.099
 runner+0.098
Neg logit contributions
washer-0.126
 else-0.125
 pasta-0.125
 dish-0.125
 bowls-0.121
Token shapes
Token ID15268
Feature activation-1.66e-02

Pos logit contributions
 bowls+0.018
 frying+0.017
 boiling+0.017
 hyd+0.017
 erupt+0.017
Neg logit contributions
aces-0.021
oot-0.021
emaker-0.018
 runner-0.018
ance-0.018
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
 bowls+0.001
 frying+0.001
 hyd+0.001
 boiling+0.001
 erupt+0.001
Neg logit contributions
oot-0.001
aces-0.001
emaker-0.001
 runner-0.001
ance-0.001
Token They
Token ID1119
Feature activation-5.58e-02

Pos logit contributions
aces+0.007
oot+0.006
ance+0.005
 runner+0.005
 racer+0.005
Neg logit contributions
 hyd-0.009
 frying-0.008
 erupt-0.008
 boiling-0.008
 bowls-0.008
Token make
Token ID787
Feature activation+6.37e-01

Pos logit contributions
ksh+0.002
 frying+0.002
 burgers+0.002
 bowls+0.002
 hyd+0.002
Neg logit contributions
aces-0.002
oot-0.002
emaker-0.002
 runner-0.002
ance-0.002
Token a
Token ID257
Feature activation+3.14e-01

Pos logit contributions
aces+0.021
oot+0.019
ance+0.017
emaker+0.017
 racer+0.016
Neg logit contributions
 hyd-0.023
 frying-0.023
ksh-0.023
 boiling-0.021
 bowls-0.021
Token coll
Token ID2927
Feature activation+5.90e+00

Pos logit contributions
 racer+0.010
 runner+0.010
oot+0.009
affe+0.009
br+0.009
Neg logit contributions
ksh-0.010
 bowls-0.010
 hyd-0.009
 frying-0.009
 boiling-0.009
Tokenage
Token ID496
Feature activation+5.51e+00

Pos logit contributions
oot+0.155
aces+0.148
 runner+0.137
emaker+0.136
ance+0.128
Neg logit contributions
 bowls-0.253
 hyd-0.247
 erupt-0.245
 frying-0.243
 slice-0.239
Token of
Token ID286
Feature activation+1.68e+00

Pos logit contributions
oot+0.186
aces+0.186
emaker+0.164
 runner+0.157
iest+0.155
Neg logit contributions
 bowls-0.207
 frying-0.199
 boiling-0.196
 hyd-0.194
 erupt-0.192
Token a
Token ID257
Feature activation+3.28e-01

Pos logit contributions
aces+0.069
oot+0.068
emaker+0.062
 runner+0.060
iest+0.059
Neg logit contributions
 bowls-0.047
 frying-0.047
ksh-0.046
 hyd-0.046
 erupt-0.046
Token farm
Token ID5318
Feature activation+4.47e-01

Pos logit contributions
oot+0.011
 runner+0.011
 racer+0.011
aces+0.011
emaker+0.010
Neg logit contributions
ksh-0.010
 bowls-0.010
 hyd-0.010
 erupt-0.010
 frying-0.010
Token.
Token ID13
Feature activation+4.99e-01

Pos logit contributions
oot+0.012
aces+0.012
 racer+0.010
 runner+0.010
mate+0.009
Neg logit contributions
ksh-0.019
 frying-0.018
 boiling-0.018
 bowls-0.018
 las-0.018
Token.
Token ID13
Feature activation-9.16e-02

Pos logit contributions
 bowls+0.026
 hyd+0.025
 frying+0.024
 erupt+0.024
 un+0.024
Neg logit contributions
oot-0.048
aces-0.048
emaker-0.043
 runner-0.043
iest-0.043
Token He
Token ID679
Feature activation+7.71e-01

Pos logit contributions
 bowls+0.003
 erupt+0.003
 grill+0.003
 hyd+0.003
 Dad+0.003
Neg logit contributions
oot-0.004
aces-0.004
emaker-0.003
iest-0.003
 runner-0.003
Token had
Token ID550
Feature activation+2.21e+00

Pos logit contributions
oot+0.031
aces+0.031
emaker+0.029
 runner+0.027
ance+0.027
Neg logit contributions
 bowls-0.024
 erupt-0.023
 hyd-0.023
 frying-0.023
 boiling-0.022
Token a
Token ID257
Feature activation+1.32e+00

Pos logit contributions
oot+0.105
aces+0.096
emaker+0.096
 runner+0.091
mate+0.089
Neg logit contributions
 bowls-0.058
 y-0.055
 frying-0.055
 erupt-0.054
 boiling-0.054
Token shiny
Token ID22441
Feature activation+1.85e+00

Pos logit contributions
aces+0.051
oot+0.051
 runner+0.048
 racer+0.046
emaker+0.046
Neg logit contributions
 bowls-0.041
 boiling-0.038
 erupt-0.038
ksh-0.038
 frying-0.038
Token sword
Token ID8429
Feature activation+5.90e+00

Pos logit contributions
oot+0.069
aces+0.065
emaker+0.063
ance+0.062
ross+0.058
Neg logit contributions
 bowl-0.068
 grill-0.066
 pan-0.066
 bowls-0.066
 dish-0.066
Token that
Token ID326
Feature activation-1.78e-01

Pos logit contributions
emaker+0.274
oot+0.272
reetings+0.267
ance+0.262
anced+0.261
Neg logit contributions
 hyd-0.118
 erupt-0.114
 pot-0.114
 grill-0.114
 dish-0.113
Token he
Token ID339
Feature activation-6.05e-03

Pos logit contributions
 bowls+0.007
 erupt+0.006
 hyd+0.006
 frying+0.006
 boiling+0.006
Neg logit contributions
oot-0.006
aces-0.006
emaker-0.005
 runner-0.005
ance-0.005
Token loved
Token ID6151
Feature activation-1.68e+00

Pos logit contributions
 un+0.000
 y+0.000
 hyd+0.000
 bowls+0.000
 clean+0.000
Neg logit contributions
oot-0.000
aces-0.000
emaker-0.000
ance-0.000
 runner-0.000
Token to
Token ID284
Feature activation+7.57e-01

Pos logit contributions
 bowls+0.049
 erupt+0.046
 boiling+0.045
 pasta+0.045
 hyd+0.044
Neg logit contributions
oot-0.072
aces-0.070
emaker-0.067
 runner-0.063
ance-0.063
Token show
Token ID905
Feature activation+6.23e-01

Pos logit contributions
oot+0.039
ross+0.039
emaker+0.039
aces+0.037
ance+0.037
Neg logit contributions
 stir-0.016
 cook-0.016
 clean-0.016
 un-0.015
 erupt-0.014
Token clown
Token ID25573
Feature activation+8.15e-01

Pos logit contributions
 bowls+0.035
 frying+0.033
 boiling+0.033
 erupt+0.033
 hyd+0.033
Neg logit contributions
oot-0.047
aces-0.047
emaker-0.043
 runner-0.041
ance-0.040
Tokens
Token ID82
Feature activation-9.77e-01

Pos logit contributions
oot+0.028
aces+0.025
 runner+0.025
emaker+0.024
 racer+0.023
Neg logit contributions
 bowls-0.031
 hyd-0.031
 boiling-0.030
 frying-0.030
 apr-0.029
Token juggling
Token ID48097
Feature activation+3.41e-01

Pos logit contributions
 bowls+0.038
 hyd+0.037
 frying+0.037
 boiling+0.036
ksh+0.036
Neg logit contributions
oot-0.031
aces-0.031
 runner-0.027
emaker-0.027
ance-0.026
Token and
Token ID290
Feature activation-5.54e-01

Pos logit contributions
oot+0.013
aces+0.013
emaker+0.012
 runner+0.011
ance+0.011
Neg logit contributions
 bowls-0.011
 frying-0.011
 erupt-0.011
 boiling-0.011
 hyd-0.011
Token ac
Token ID936
Feature activation+3.90e+00

Pos logit contributions
 bowls+0.017
 erupt+0.016
 frying+0.016
 boiling+0.016
 burgers+0.015
Neg logit contributions
oot-0.023
aces-0.023
emaker-0.021
ance-0.020
 runner-0.020
Tokenrob
Token ID22609
Feature activation+5.89e+00

Pos logit contributions
oot+0.088
aces+0.086
 runner+0.079
emaker+0.076
 racer+0.070
Neg logit contributions
 bowls-0.177
 frying-0.171
 hyd-0.170
 boiling-0.169
 burgers-0.169
Tokenats
Token ID1381
Feature activation+8.65e-01

Pos logit contributions
oot+0.209
aces+0.198
emaker+0.189
 runner+0.186
mate+0.178
Neg logit contributions
 bowls-0.205
 frying-0.188
 burgers-0.188
 boiling-0.185
 apr-0.185
Token doing
Token ID1804
Feature activation-6.63e-01

Pos logit contributions
oot+0.034
aces+0.034
emaker+0.031
 runner+0.030
ance+0.029
Neg logit contributions
 bowls-0.027
 erupt-0.026
 boiling-0.026
 frying-0.026
 burgers-0.025
Token flips
Token ID45971
Feature activation-1.05e+00

Pos logit contributions
 bowls+0.022
 hyd+0.022
 frying+0.021
 boiling+0.021
ksh+0.021
Neg logit contributions
aces-0.025
oot-0.024
 runner-0.022
emaker-0.022
 racer-0.021
Token.
Token ID13
Feature activation+1.38e-02

Pos logit contributions
 bowls+0.034
 frying+0.032
 erupt+0.032
 boiling+0.032
 hyd+0.032
Neg logit contributions
oot-0.041
aces-0.040
emaker-0.037
 runner-0.035
ance-0.035
Token But
Token ID887
Feature activation+1.66e+00

Pos logit contributions
oot+0.001
aces+0.001
emaker+0.000
 runner+0.000
ance+0.000
Neg logit contributions
 bowls-0.000
 frying-0.000
 boiling-0.000
 erupt-0.000
 hyd-0.000
Token plan
Token ID1410
Feature activation+7.05e-01

Pos logit contributions
oot+0.038
aces+0.036
emaker+0.032
orns+0.031
py+0.031
Neg logit contributions
 bowls-0.028
 bowl-0.027
 grill-0.027
 dish-0.027
 pasta-0.026
Token was
Token ID373
Feature activation+3.87e-01

Pos logit contributions
oot+0.030
aces+0.030
emaker+0.027
 runner+0.026
orns+0.026
Neg logit contributions
 bowls-0.019
 erupt-0.019
 hyd-0.018
 boiling-0.018
 frying-0.018
Token to
Token ID284
Feature activation+1.76e-01

Pos logit contributions
oot+0.016
aces+0.016
emaker+0.014
 runner+0.014
ance+0.013
Neg logit contributions
 bowls-0.012
 frying-0.011
 hyd-0.011
 boiling-0.011
 erupt-0.011
Token make
Token ID787
Feature activation+4.83e-01

Pos logit contributions
oot+0.007
aces+0.007
 runner+0.006
emaker+0.006
mate+0.006
Neg logit contributions
ksh-0.006
 bowls-0.005
 frying-0.005
 boiling-0.005
 hyd-0.005
Token a
Token ID257
Feature activation+1.61e-01

Pos logit contributions
aces+0.016
oot+0.015
ance+0.015
 runner+0.014
 racer+0.014
Neg logit contributions
 hyd-0.018
 frying-0.017
ksh-0.017
 erupt-0.016
 boiling-0.016
Token coll
Token ID2927
Feature activation+5.89e+00

Pos logit contributions
 racer+0.005
 runner+0.005
mate+0.004
 superhero+0.004
 villain+0.004
Neg logit contributions
ksh-0.006
 hyd-0.005
 bowls-0.005
 boiling-0.005
 frying-0.005
Tokenage
Token ID496
Feature activation+5.45e+00

Pos logit contributions
aces+0.125
oot+0.124
emaker+0.104
 runner+0.104
ance+0.100
Neg logit contributions
 hyd-0.276
 bowls-0.275
 erupt-0.270
 clean-0.266
 frying-0.265
Token with
Token ID351
Feature activation+5.53e-02

Pos logit contributions
oot+0.199
aces+0.198
emaker+0.179
 runner+0.171
ance+0.167
Neg logit contributions
 bowls-0.188
 erupt-0.181
 hyd-0.180
 frying-0.180
 boiling-0.180
Token pictures
Token ID5986
Feature activation+1.82e+00

Pos logit contributions
aces+0.002
oot+0.002
emaker+0.002
iest+0.002
ance+0.002
Neg logit contributions
 bowls-0.002
 erupt-0.002
 frying-0.002
 hyd-0.002
ksh-0.002
Token from
Token ID422
Feature activation+4.00e-01

Pos logit contributions
oot+0.056
aces+0.054
emaker+0.050
 runner+0.047
ance+0.045
Neg logit contributions
 bowls-0.073
 erupt-0.070
 boiling-0.070
 frying-0.070
 hyd-0.069
Token a
Token ID257
Feature activation-6.91e-01

Pos logit contributions
aces+0.016
oot+0.015
emaker+0.014
 runner+0.014
ance+0.013
Neg logit contributions
 bowls-0.012
 frying-0.012
 erupt-0.012
 hyd-0.012
 boiling-0.012
Token a
Token ID257
Feature activation+5.93e-02

Pos logit contributions
 bowls+0.052
 boiling+0.049
 frying+0.049
 erupt+0.049
 hyd+0.048
Neg logit contributions
oot-0.073
aces-0.072
emaker-0.065
 runner-0.064
ance-0.062
Token little
Token ID1310
Feature activation-1.85e-02

Pos logit contributions
 runner+0.002
oot+0.002
 racer+0.002
emaker+0.002
mate+0.002
Neg logit contributions
ksh-0.002
 bowls-0.002
 hyd-0.002
 erupt-0.002
 apr-0.002
Token boy
Token ID2933
Feature activation+1.28e+00

Pos logit contributions
 bowls+0.001
ksh+0.001
 erupt+0.001
 frying+0.001
 apr+0.001
Neg logit contributions
oot-0.001
 runner-0.001
emaker-0.001
aces-0.001
 racer-0.001
Token wearing
Token ID5762
Feature activation+1.40e+00

Pos logit contributions
oot+0.045
aces+0.042
emaker+0.039
 runner+0.038
 racer+0.036
Neg logit contributions
 bowls-0.047
ksh-0.046
 frying-0.044
 apr-0.044
 burgers-0.043
Token a
Token ID257
Feature activation+7.98e-01

Pos logit contributions
oot+0.070
aces+0.067
emaker+0.064
ance+0.061
 runner+0.061
Neg logit contributions
 bowls-0.031
 y-0.029
 frying-0.029
 boiling-0.029
 pasta-0.028
Token superhero
Token ID17343
Feature activation+5.83e+00

Pos logit contributions
oot+0.033
aces+0.033
emaker+0.030
 runner+0.029
ance+0.028
Neg logit contributions
 bowls-0.024
 frying-0.023
 boiling-0.023
 erupt-0.023
 hyd-0.023
Token costume
Token ID16569
Feature activation+3.87e+00

Pos logit contributions
oot+0.255
ross+0.235
emaker+0.233
ance+0.232
aces+0.229
Neg logit contributions
 bowls-0.157
 hyd-0.156
 pan-0.153
 bowl-0.152
 pot-0.152
Token.
Token ID13
Feature activation+6.12e-01

Pos logit contributions
oot+0.167
emaker+0.167
aces+0.155
ance+0.153
 runner+0.153
Neg logit contributions
 bowls-0.096
 y-0.092
 hyd-0.091
 bowl-0.090
 pasta-0.090
Token She
Token ID1375
Feature activation+1.13e+00

Pos logit contributions
oot+0.020
aces+0.019
emaker+0.017
 runner+0.016
ance+0.016
Neg logit contributions
 bowls-0.024
 frying-0.023
 boiling-0.023
 erupt-0.023
 hyd-0.023
Token said
Token ID531
Feature activation+3.42e-01

Pos logit contributions
oot+0.051
aces+0.050
emaker+0.047
iest+0.045
 runner+0.045
Neg logit contributions
 bowls-0.030
 frying-0.029
 boiling-0.028
 erupt-0.028
 hyd-0.028
Token,
Token ID11
Feature activation+9.45e-02

Pos logit contributions
aces+0.013
oot+0.012
emaker+0.012
orns+0.011
 runner+0.011
Neg logit contributions
 bowls-0.011
 Dad-0.011
 y-0.011
 frying-0.011
 pasta-0.011
Token.
Token ID13
Feature activation+2.02e-01

Pos logit contributions
 bowls+0.014
 boiling+0.013
 hyd+0.013
 erupt+0.013
 burgers+0.012
Neg logit contributions
oot-0.022
aces-0.022
emaker-0.021
 runner-0.020
 racer-0.020
Token He
Token ID679
Feature activation+8.09e-01

Pos logit contributions
oot+0.007
aces+0.007
emaker+0.006
 runner+0.006
ance+0.006
Neg logit contributions
 bowls-0.007
 frying-0.007
 hyd-0.007
 boiling-0.007
 erupt-0.007
Token had
Token ID550
Feature activation+1.95e+00

Pos logit contributions
oot+0.030
aces+0.029
emaker+0.026
 runner+0.026
 racer+0.025
Neg logit contributions
 bowls-0.028
 hyd-0.026
 frying-0.026
 boiling-0.026
 erupt-0.026
Token a
Token ID257
Feature activation+8.52e-01

Pos logit contributions
oot+0.080
aces+0.080
emaker+0.072
 runner+0.070
ance+0.069
Neg logit contributions
 bowls-0.059
 frying-0.056
 hyd-0.056
 boiling-0.055
 erupt-0.055
Token band
Token ID4097
Feature activation+5.04e+00

Pos logit contributions
oot+0.034
aces+0.033
 runner+0.032
 racer+0.030
emaker+0.030
Neg logit contributions
 bowls-0.026
ksh-0.024
 erupt-0.024
 hyd-0.024
 boiling-0.024
Tokenage
Token ID496
Feature activation+5.82e+00

Pos logit contributions
aces+0.163
oot+0.157
emaker+0.149
ance+0.142
 runner+0.141
Neg logit contributions
 hyd-0.185
 frying-0.180
 erupt-0.177
 bowls-0.176
 boiling-0.175
Token on
Token ID319
Feature activation+2.87e+00

Pos logit contributions
oot+0.217
aces+0.211
emaker+0.198
 runner+0.190
ance+0.183
Neg logit contributions
 bowls-0.189
 boiling-0.188
 hyd-0.187
 frying-0.185
 erupt-0.185
Token his
Token ID465
Feature activation+1.28e+00

Pos logit contributions
oot+0.126
aces+0.124
emaker+0.116
ance+0.112
iest+0.110
Neg logit contributions
 bowls-0.080
 boiling-0.078
 grill-0.078
 erupt-0.077
 burgers-0.074
Token paw
Token ID41827
Feature activation+2.05e+00

Pos logit contributions
aces+0.045
oot+0.045
emaker+0.039
 runner+0.038
ance+0.037
Neg logit contributions
 bowls-0.047
 frying-0.045
 boiling-0.045
 erupt-0.045
 hyd-0.044
Token.
Token ID13
Feature activation-7.57e-02

Pos logit contributions
oot+0.080
aces+0.079
emaker+0.073
 runner+0.070
ance+0.069
Neg logit contributions
 bowls-0.065
 frying-0.062
 hyd-0.062
 boiling-0.062
 erupt-0.061
Token
Token ID198
Feature activation-3.53e-01

Pos logit contributions
 bowls+0.003
 frying+0.003
 hyd+0.003
 boiling+0.003
 erupt+0.003
Neg logit contributions
oot-0.002
aces-0.002
emaker-0.002
 runner-0.002
ance-0.002
Token He
Token ID679
Feature activation+9.62e-01

Pos logit contributions
aces+0.016
oot+0.015
emaker+0.013
 runner+0.012
 racer+0.012
Neg logit contributions
 bowls-0.030
 frying-0.030
 boiling-0.030
 hyd-0.029
 erupt-0.029
Token always
Token ID1464
Feature activation+2.14e+00

Pos logit contributions
oot+0.040
aces+0.039
emaker+0.035
 runner+0.034
ance+0.034
Neg logit contributions
 bowls-0.030
 frying-0.028
 boiling-0.028
 erupt-0.028
 hyd-0.028
Token had
Token ID550
Feature activation+1.68e+00

Pos logit contributions
oot+0.090
aces+0.088
emaker+0.081
 runner+0.079
ance+0.076
Neg logit contributions
 bowls-0.064
 frying-0.061
 hyd-0.061
 erupt-0.060
 boiling-0.060
Token a
Token ID257
Feature activation+4.93e-01

Pos logit contributions
aces+0.068
oot+0.066
emaker+0.060
 runner+0.058
ance+0.058
Neg logit contributions
 bowls-0.051
 hyd-0.050
 erupt-0.050
 frying-0.050
 boiling-0.049
Token tw
Token ID665
Feature activation+3.17e+00

Pos logit contributions
aces+0.016
 runner+0.016
oot+0.016
 racer+0.016
mate+0.015
Neg logit contributions
ksh-0.017
 erupt-0.017
 bowls-0.017
 boiling-0.016
 hyd-0.016
Tokenig
Token ID328
Feature activation+5.81e+00

Pos logit contributions
oot+0.111
aces+0.107
emaker+0.103
 runner+0.099
ance+0.099
Neg logit contributions
 bowls-0.107
 frying-0.106
 pan-0.101
 hyd-0.100
 boiling-0.100
Token in
Token ID287
Feature activation+6.01e-01

Pos logit contributions
aces+0.195
oot+0.190
emaker+0.176
orns+0.175
ance+0.174
Neg logit contributions
 bowls-0.196
 frying-0.194
 cooking-0.194
 hyd-0.192
 cook-0.191
Token his
Token ID465
Feature activation+1.47e+00

Pos logit contributions
oot+0.023
aces+0.022
emaker+0.020
 runner+0.020
ance+0.019
Neg logit contributions
 bowls-0.021
 frying-0.020
 boiling-0.020
 erupt-0.019
 hyd-0.019
Token hand
Token ID1021
Feature activation+3.15e-01

Pos logit contributions
aces+0.054
 runner+0.046
 racer+0.045
oot+0.045
emaker+0.042
Neg logit contributions
ksh-0.052
 erupt-0.051
 boiling-0.048
 burgers-0.048
 boil-0.046
Token so
Token ID523
Feature activation-1.67e+00

Pos logit contributions
oot+0.012
aces+0.012
emaker+0.011
 runner+0.011
py+0.011
Neg logit contributions
 bowls-0.010
 frying-0.010
 hyd-0.009
 burgers-0.009
 grill-0.009
Token he
Token ID339
Feature activation-7.10e-01

Pos logit contributions
 Dad+0.053
 bowls+0.050
 y+0.050
 hot+0.049
 pasta+0.049
Neg logit contributions
aces-0.072
oot-0.070
orns-0.063
emaker-0.063
reetings-0.063
TokenS
Token ID50
Feature activation-1.35e+00

Pos logit contributions
 bowls+0.018
 frying+0.017
 hyd+0.016
 erupt+0.016
 boiling+0.016
Neg logit contributions
aces-0.020
oot-0.020
emaker-0.018
iest-0.017
ance-0.017
Tokenara
Token ID3301
Feature activation-8.87e-01

Pos logit contributions
 bowls+0.046
 frying+0.044
 hyd+0.044
 erupt+0.044
 boiling+0.044
Neg logit contributions
oot-0.051
aces-0.050
emaker-0.046
 runner-0.044
ance-0.043
Token loved
Token ID6151
Feature activation-1.57e+00

Pos logit contributions
 boiling+0.035
 burgers+0.035
 bowls+0.035
 hyd+0.034
 frying+0.034
Neg logit contributions
aces-0.029
oot-0.028
emaker-0.024
 runner-0.022
affe-0.022
Token neck
Token ID7393
Feature activation+4.06e+00

Pos logit contributions
 bowls+0.051
 frying+0.048
 boiling+0.048
 erupt+0.048
 hyd+0.048
Neg logit contributions
oot-0.061
aces-0.061
emaker-0.055
 runner-0.053
ance-0.052
Tokenl
Token ID75
Feature activation+1.39e+00

Pos logit contributions
oot+0.135
aces+0.130
 runner+0.122
emaker+0.122
mate+0.116
Neg logit contributions
 bowls-0.151
 frying-0.145
 y-0.144
 erupt-0.143
 boiling-0.143
Tokenaces
Token ID2114
Feature activation+5.81e+00

Pos logit contributions
oot+0.022
aces+0.018
emaker+0.018
 runner+0.017
mate+0.016
Neg logit contributions
 bowls-0.075
 erupt-0.072
 frying-0.071
 boiling-0.071
 hyd-0.071
Token.
Token ID13
Feature activation-7.14e-02

Pos logit contributions
oot+0.240
aces+0.235
emaker+0.228
 runner+0.221
mate+0.219
Neg logit contributions
 bowls-0.161
 erupt-0.152
 y-0.150
 frying-0.149
 hyd-0.148
Token She
Token ID1375
Feature activation+7.65e-01

Pos logit contributions
 bowls+0.003
 frying+0.003
 Dad+0.003
 grill+0.003
 erupt+0.003
Neg logit contributions
oot-0.002
aces-0.002
emaker-0.002
iest-0.002
 runner-0.002
Token nodded
Token ID14464
Feature activation+2.13e+00

Pos logit contributions
oot+0.033
aces+0.032
emaker+0.031
 runner+0.029
iest+0.029
Neg logit contributions
 bowls-0.022
 frying-0.020
 boiling-0.020
 hyd-0.019
 y-0.019
Token and
Token ID290
Feature activation-9.67e-02

Pos logit contributions
oot+0.094
aces+0.092
emaker+0.088
 runner+0.083
ance+0.083
Neg logit contributions
 bowls-0.061
 boiling-0.057
 Dad-0.057
 hyd-0.056
 frying-0.055
Token reached
Token ID4251
Feature activation-9.03e-01

Pos logit contributions
 bowls+0.003
 frying+0.003
 erupt+0.003
 boiling+0.003
 hyd+0.003
Neg logit contributions
oot-0.004
aces-0.004
emaker-0.004
 runner-0.004
ance-0.004
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
oot+0.066
aces+0.064
emaker+0.061
 runner+0.059
ance+0.058
Neg logit contributions
 bowls-0.042
 erupt-0.039
 hyd-0.038
 boiling-0.038
 frying-0.037
Token Lily
Token ID20037
Feature activation+8.37e-01

Pos logit contributions
 bowls+0.004
 frying+0.003
 erupt+0.003
 boiling+0.003
 hyd+0.003
Neg logit contributions
oot-0.005
aces-0.005
emaker-0.004
 runner-0.004
ance-0.004
Token had
Token ID550
Feature activation+1.91e+00

Pos logit contributions
oot+0.031
aces+0.031
emaker+0.027
 runner+0.027
ance+0.026
Neg logit contributions
 bowls-0.029
 frying-0.028
 boiling-0.027
 erupt-0.027
 hyd-0.027
Token a
Token ID257
Feature activation+1.11e+00

Pos logit contributions
oot+0.086
aces+0.084
emaker+0.079
 runner+0.076
ance+0.074
Neg logit contributions
 bowls-0.052
 frying-0.049
 boiling-0.048
 erupt-0.048
 hyd-0.048
Token pink
Token ID11398
Feature activation+2.63e+00

Pos logit contributions
aces+0.041
oot+0.041
 runner+0.038
emaker+0.037
 racer+0.037
Neg logit contributions
 bowls-0.036
 erupt-0.035
 hyd-0.034
 boiling-0.034
ksh-0.034
Token er
Token ID1931
Feature activation+5.76e+00

Pos logit contributions
oot+0.125
aces+0.122
emaker+0.117
ross+0.115
ance+0.113
Neg logit contributions
 bowl-0.072
 bowls-0.071
 dish-0.070
 grill-0.070
 pan-0.069
Tokenaser
Token ID6005
Feature activation+5.07e+00

Pos logit contributions
ross+0.181
reetings+0.168
 villains+0.155
anced+0.153
 onward+0.152
Neg logit contributions
 pasta-0.192
 dish-0.187
 bowls-0.186
 pan-0.182
 pot-0.182
Token that
Token ID326
Feature activation-4.22e-01

Pos logit contributions
oot+0.239
emaker+0.238
reetings+0.237
anced+0.237
ance+0.229
Neg logit contributions
 pan-0.106
 dish-0.105
 pot-0.104
 bowl-0.103
 pasta-0.101
Token she
Token ID673
Feature activation+1.23e-01

Pos logit contributions
 bowls+0.017
 frying+0.016
 erupt+0.016
 boiling+0.016
 hyd+0.016
Neg logit contributions
oot-0.013
aces-0.013
emaker-0.012
 runner-0.011
ance-0.011
Token used
Token ID973
Feature activation+1.32e+00

Pos logit contributions
oot+0.005
aces+0.005
emaker+0.005
ance+0.004
 runner+0.004
Neg logit contributions
 bowls-0.004
 frying-0.004
 y-0.004
 stir-0.003
 hyd-0.003
Token to
Token ID284
Feature activation-3.78e-02

Pos logit contributions
emaker+0.061
oot+0.060
 runner+0.058
ross+0.057
aces+0.056
Neg logit contributions
 bowls-0.029
 y-0.028
 clean-0.028
 pasta-0.027
 delicious-0.026
Token and
Token ID290
Feature activation+1.23e-01

Pos logit contributions
oot+0.026
aces+0.026
 runner+0.022
emaker+0.022
ance+0.021
Neg logit contributions
 bowls-0.030
 frying-0.029
 erupt-0.029
 boiling-0.028
 burgers-0.028
Token crept
Token ID47092
Feature activation-4.75e-01

Pos logit contributions
oot+0.005
aces+0.005
emaker+0.004
ance+0.004
 runner+0.004
Neg logit contributions
 bowls-0.004
 erupt-0.004
 frying-0.004
 boiling-0.004
 hyd-0.004
Token back
Token ID736
Feature activation-5.27e-01

Pos logit contributions
 bowls+0.015
 erupt+0.015
 frying+0.014
 hyd+0.014
 boiling+0.014
Neg logit contributions
oot-0.019
aces-0.018
 runner-0.016
emaker-0.016
ance-0.016
Token to
Token ID284
Feature activation-1.14e+00

Pos logit contributions
 bowls+0.017
 frying+0.016
 boiling+0.016
 erupt+0.016
 hyd+0.016
Neg logit contributions
oot-0.021
aces-0.021
emaker-0.019
 runner-0.018
ance-0.018
Token the
Token ID262
Feature activation-2.61e-01

Pos logit contributions
ksh+0.050
 bowls+0.046
 frying+0.045
 hyd+0.045
 burgers+0.044
Neg logit contributions
oot-0.030
aces-0.027
mate-0.027
ance-0.027
emaker-0.026
Token dining
Token ID17423
Feature activation-6.23e+00

Pos logit contributions
ksh+0.007
rig+0.006
 erupt+0.006
 appet+0.005
 reel+0.005
Neg logit contributions
iest-0.010
 days-0.009
mate-0.009
 racer-0.009
 runner-0.009
Token room
Token ID2119
Feature activation-2.88e+00

Pos logit contributions
ksh+0.182
 erupt+0.167
 reel+0.150
 burgers+0.150
 barbecue+0.149
Neg logit contributions
aces-0.242
iest-0.228
er-0.224
 days-0.220
oot-0.216
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
 bowls+0.102
 frying+0.099
 erupt+0.098
ksh+0.098
 hyd+0.098
Neg logit contributions
oot-0.101
aces-0.100
emaker-0.086
 runner-0.086
iest-0.083
Token She
Token ID1375
Feature activation+5.89e-01

Pos logit contributions
 bowls+0.015
 hyd+0.015
 boiling+0.015
 frying+0.015
 erupt+0.015
Neg logit contributions
aces-0.011
oot-0.011
emaker-0.009
 runner-0.009
ance-0.009
Token felt
Token ID2936
Feature activation+1.77e+00

Pos logit contributions
aces+0.020
oot+0.020
 runner+0.017
emaker+0.017
ance+0.017
Neg logit contributions
ksh-0.020
 erupt-0.020
 bowls-0.019
 burgers-0.019
 hyd-0.019
Token very
Token ID845
Feature activation-8.83e-01

Pos logit contributions
aces+0.065
oot+0.061
iest+0.059
ance+0.057
emaker+0.053
Neg logit contributions
ksh-0.060
 bowls-0.058
 grill-0.054
 erupt-0.054
 burgers-0.052
Token and
Token ID290
Feature activation-8.92e-01

Pos logit contributions
oot+0.007
aces+0.007
emaker+0.007
 runner+0.006
ance+0.006
Neg logit contributions
 bowls-0.006
 erupt-0.005
 hyd-0.005
 frying-0.005
 boiling-0.005
Token sniff
Token ID26300
Feature activation-1.02e+00

Pos logit contributions
 bowls+0.031
 burgers+0.030
 hamb+0.030
 y+0.029
 grill+0.029
Neg logit contributions
oot-0.036
aces-0.035
emaker-0.030
iest-0.029
ance-0.029
Tokening
Token ID278
Feature activation-1.05e+00

Pos logit contributions
 bowls+0.044
 frying+0.042
 boiling+0.042
 hyd+0.042
 erupt+0.042
Neg logit contributions
oot-0.029
aces-0.029
emaker-0.025
 runner-0.024
ance-0.023
Token all
Token ID477
Feature activation-9.32e-01

Pos logit contributions
 bowls+0.037
 frying+0.036
 erupt+0.035
 boiling+0.035
 hyd+0.035
Neg logit contributions
aces-0.038
oot-0.038
emaker-0.033
 runner-0.033
ance-0.032
Token the
Token ID262
Feature activation+3.90e-01

Pos logit contributions
 bowls+0.031
 frying+0.030
 erupt+0.030
 hyd+0.030
 boiling+0.030
Neg logit contributions
oot-0.035
aces-0.035
emaker-0.032
 runner-0.030
iest-0.030
Token smells
Token ID25760
Feature activation-6.14e+00

Pos logit contributions
aces+0.013
oot+0.013
emaker+0.012
 runner+0.012
iest+0.011
Neg logit contributions
 bowls-0.014
 frying-0.014
 hyd-0.014
 boiling-0.014
 erupt-0.014
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
 bowls+0.245
 hyd+0.238
 erupt+0.235
 frying+0.234
ksh+0.234
Neg logit contributions
aces-0.180
oot-0.174
iest-0.168
 runner-0.152
emaker-0.151
Token John
Token ID1757
Feature activation-1.08e+00

Pos logit contributions
 bowls+0.006
 boiling+0.006
 frying+0.006
 hyd+0.006
 erupt+0.006
Neg logit contributions
oot-0.006
aces-0.006
emaker-0.005
 runner-0.005
ance-0.005
Token jumped
Token ID11687
Feature activation-8.75e-01

Pos logit contributions
 bowls+0.037
 boiling+0.035
 erupt+0.035
 hyd+0.035
 frying+0.034
Neg logit contributions
aces-0.040
oot-0.040
emaker-0.035
 runner-0.035
ance-0.033
Token into
Token ID656
Feature activation-4.69e-01

Pos logit contributions
 bowls+0.028
 frying+0.027
 boiling+0.026
 erupt+0.026
 hyd+0.026
Neg logit contributions
oot-0.035
aces-0.034
emaker-0.031
 runner-0.030
ance-0.029
Token a
Token ID257
Feature activation-6.58e-01

Pos logit contributions
 hyd+0.017
 frying+0.017
 erupt+0.017
ksh+0.017
 bowls+0.016
Neg logit contributions
aces-0.015
oot-0.014
 runner-0.013
emaker-0.013
mate-0.012
Token him
Token ID683
Feature activation-5.16e-01

Pos logit contributions
 hyd+0.023
ksh+0.023
 frying+0.022
 bowls+0.022
 erupt+0.021
Neg logit contributions
oot-0.019
aces-0.018
emaker-0.017
mate-0.015
py-0.015
Token and
Token ID290
Feature activation-2.43e-01

Pos logit contributions
 bowls+0.025
 apr+0.024
ksh+0.024
 las+0.024
 frying+0.024
Neg logit contributions
oot-0.013
aces-0.011
py-0.009
un-0.009
emaker-0.008
Token ran
Token ID4966
Feature activation-5.09e-02

Pos logit contributions
ksh+0.011
 bowls+0.010
 hyd+0.010
 grill+0.010
 erupt+0.010
Neg logit contributions
oot-0.006
aces-0.006
emaker-0.006
py-0.005
un-0.005
Token to
Token ID284
Feature activation-8.65e-01

Pos logit contributions
 bowls+0.002
 frying+0.002
 boiling+0.002
ksh+0.002
 hyd+0.002
Neg logit contributions
oot-0.002
aces-0.001
 runner-0.001
mate-0.001
emaker-0.001
Token the
Token ID262
Feature activation-1.89e-01

Pos logit contributions
ksh+0.040
 frying+0.036
 bowls+0.035
 hyd+0.035
 burgers+0.035
Neg logit contributions
oot-0.023
mate-0.021
emaker-0.020
aces-0.018
ance-0.018
Token dining
Token ID17423
Feature activation-6.07e+00

Pos logit contributions
ksh+0.006
rig+0.006
 erupt+0.005
 hamb+0.005
 appet+0.005
Neg logit contributions
aces-0.006
 villains-0.006
mate-0.006
er-0.005
 racer-0.005
Token room
Token ID2119
Feature activation-2.38e+00

Pos logit contributions
ksh+0.199
 erupt+0.175
rig+0.164
 barbecue+0.161
 burgers+0.158
Neg logit contributions
aces-0.217
er-0.206
iest-0.202
 days-0.195
oot-0.193
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
ksh+0.092
 bowls+0.090
 frying+0.090
 las+0.089
 hyd+0.088
Neg logit contributions
oot-0.075
aces-0.074
emaker-0.063
 runner-0.061
mate-0.058
Token She
Token ID1375
Feature activation+7.82e-01

Pos logit contributions
ksh+0.012
 erupt+0.012
 bowls+0.012
 burgers+0.012
 hyd+0.012
Neg logit contributions
oot-0.003
aces-0.003
 Kit-0.002
ance-0.002
 Bree-0.002
Token saw
Token ID2497
Feature activation-1.53e+00

Pos logit contributions
oot+0.027
aces+0.025
emaker+0.024
Tweet+0.023
un+0.023
Neg logit contributions
ksh-0.027
 erupt-0.026
 bowls-0.025
 hyd-0.025
 burgers-0.025
Token the
Token ID262
Feature activation+5.50e-01

Pos logit contributions
 hyd+0.054
ksh+0.054
 erupt+0.051
 frying+0.050
 bowls+0.049
Neg logit contributions
aces-0.054
oot-0.054
emaker-0.052
ance-0.048
iest-0.046
Token tell
Token ID1560
Feature activation-5.20e-01

Pos logit contributions
 bowls+0.018
 frying+0.017
 boiling+0.017
 hyd+0.017
 erupt+0.017
Neg logit contributions
oot-0.024
aces-0.024
emaker-0.022
 runner-0.021
ance-0.021
Token stories
Token ID3923
Feature activation-3.62e-01

Pos logit contributions
 bowls+0.016
 frying+0.016
 hyd+0.015
ksh+0.015
 boiling+0.015
Neg logit contributions
oot-0.020
aces-0.020
emaker-0.018
ance-0.018
 runner-0.018
Token around
Token ID1088
Feature activation-3.07e-01

Pos logit contributions
 bowls+0.012
 erupt+0.012
 frying+0.012
 boiling+0.011
 hyd+0.011
Neg logit contributions
oot-0.013
aces-0.013
emaker-0.012
 runner-0.012
ance-0.011
Token the
Token ID262
Feature activation-7.69e-01

Pos logit contributions
 bowls+0.010
 frying+0.009
ksh+0.009
 erupt+0.009
 hyd+0.009
Neg logit contributions
oot-0.012
aces-0.012
emaker-0.011
iest-0.010
 runner-0.010
Token camp
Token ID1413
Feature activation-2.91e+00

Pos logit contributions
 bowls+0.022
 frying+0.022
 erupt+0.022
ksh+0.022
 hyd+0.021
Neg logit contributions
aces-0.030
oot-0.028
 runner-0.028
iest-0.027
 racer-0.027
Tokenfire
Token ID6495
Feature activation-6.00e+00

Pos logit contributions
 bowls+0.089
 frying+0.085
 boiling+0.083
ksh+0.082
 erupt+0.081
Neg logit contributions
aces-0.116
oot-0.115
iest-0.104
 runner-0.103
emaker-0.102
Token.
Token ID13
Feature activation-8.88e-02

Pos logit contributions
 bowls+0.229
 frying+0.225
ksh+0.221
 apr+0.214
 boiling+0.214
Neg logit contributions
aces-0.184
oot-0.183
iest-0.169
emaker-0.158
 runner-0.158
Token<|endoftext|>
Token ID50256
Feature activation-7.64e-01

Pos logit contributions
 bowls+0.003
 frying+0.003
 apr+0.003
 batter+0.003
 boiling+0.003
Neg logit contributions
oot-0.003
aces-0.003
ance-0.002
anced-0.002
emaker-0.002
TokenOnce
Token ID7454
Feature activation-3.09e-01

Pos logit contributions
 bowls+0.021
 boiling+0.020
 frying+0.020
 erupt+0.019
 hyd+0.019
Neg logit contributions
oot-0.034
aces-0.033
emaker-0.031
 runner-0.030
ance-0.029
Token upon
Token ID2402
Feature activation-7.19e-01

Pos logit contributions
 bowls+0.011
 erupt+0.011
 boiling+0.011
 frying+0.011
 hyd+0.010
Neg logit contributions
aces-0.011
oot-0.011
emaker-0.009
 runner-0.009
ance-0.009
Token a
Token ID257
Feature activation-9.77e-01

Pos logit contributions
 bowls+0.023
 frying+0.023
 hyd+0.022
 erupt+0.022
 boiling+0.022
Neg logit contributions
aces-0.027
oot-0.027
emaker-0.024
 runner-0.024
iest-0.023
Token and
Token ID290
Feature activation-6.01e-01

Pos logit contributions
 frying+0.014
ksh+0.013
 bowls+0.013
 hyd+0.013
 las+0.012
Neg logit contributions
aces-0.012
oot-0.011
emaker-0.010
mate-0.010
 runner-0.010
Token the
Token ID262
Feature activation+9.12e-01

Pos logit contributions
 bowls+0.019
 frying+0.018
 boiling+0.018
 hyd+0.018
 erupt+0.017
Neg logit contributions
oot-0.024
aces-0.024
emaker-0.022
 runner-0.021
ance-0.021
Token lightning
Token ID14357
Feature activation-8.20e-01

Pos logit contributions
aces+0.037
oot+0.036
emaker+0.034
 runner+0.034
iest+0.034
Neg logit contributions
 bowls-0.024
 frying-0.024
ksh-0.024
 las-0.023
 erupt-0.023
Token struck
Token ID7425
Feature activation-1.41e+00

Pos logit contributions
 bowls+0.029
 frying+0.027
 boiling+0.027
 hyd+0.027
 erupt+0.027
Neg logit contributions
oot-0.030
aces-0.030
emaker-0.027
 runner-0.026
iest-0.025
Token the
Token ID262
Feature activation-8.68e-01

Pos logit contributions
 bowls+0.048
 frying+0.048
 hyd+0.045
 boiling+0.045
 grill+0.045
Neg logit contributions
aces-0.050
oot-0.049
emaker-0.044
ance-0.043
 runner-0.043
Token hyd
Token ID7409
Feature activation-5.98e+00

Pos logit contributions
ksh+0.026
 bowls+0.026
 frying+0.025
 las+0.025
 hamb+0.024
Neg logit contributions
aces-0.031
 runner-0.029
oot-0.029
 racer-0.028
emaker-0.028
Tokenrant
Token ID5250
Feature activation-4.42e+00

Pos logit contributions
 bowls+0.202
 frying+0.186
 pasta+0.180
 las+0.180
 bowl+0.179
Neg logit contributions
aces-0.221
oot-0.220
py-0.198
emaker-0.192
iest-0.189
Token.
Token ID13
Feature activation-2.16e-01

Pos logit contributions
 bowls+0.150
 frying+0.150
 las+0.147
ksh+0.146
 boiling+0.144
Neg logit contributions
aces-0.149
oot-0.142
iest-0.131
emaker-0.127
 runner-0.124
Token Suddenly
Token ID24975
Feature activation+5.55e-01

Pos logit contributions
 bowls+0.008
 frying+0.008
 boiling+0.008
 hyd+0.008
 erupt+0.007
Neg logit contributions
oot-0.007
aces-0.007
emaker-0.007
 runner-0.006
ance-0.006
Token water
Token ID1660
Feature activation-1.13e+00

Pos logit contributions
oot+0.023
aces+0.023
emaker+0.021
 runner+0.020
ross+0.019
Neg logit contributions
 bowls-0.018
 erupt-0.016
 y-0.016
 Dad-0.016
 boiling-0.016
Token was
Token ID373
Feature activation-2.64e-01

Pos logit contributions
 bowls+0.037
 frying+0.035
 boiling+0.035
 erupt+0.035
 hyd+0.035
Neg logit contributions
oot-0.044
aces-0.043
emaker-0.039
 runner-0.038
ance-0.037
Token The
Token ID383
Feature activation+4.45e-01

Pos logit contributions
 bowls+0.007
 frying+0.007
 hyd+0.007
 burgers+0.007
 boiling+0.007
Neg logit contributions
aces-0.006
oot-0.006
emaker-0.005
 runner-0.005
ance-0.005
Token bottle
Token ID9294
Feature activation-1.14e+00

Pos logit contributions
aces+0.019
oot+0.018
 runner+0.017
emaker+0.017
iest+0.017
Neg logit contributions
 erupt-0.011
ksh-0.011
 bowls-0.011
 frying-0.011
 hyd-0.010
Token lands
Token ID8604
Feature activation+1.38e-01

Pos logit contributions
 bowls+0.039
 erupt+0.037
 boiling+0.037
 frying+0.036
 hyd+0.036
Neg logit contributions
oot-0.043
aces-0.042
emaker-0.038
 runner-0.037
ance-0.036
Token in
Token ID287
Feature activation-2.18e-01

Pos logit contributions
oot+0.004
aces+0.004
emaker+0.004
 runner+0.004
ance+0.003
Neg logit contributions
 bowls-0.006
 boiling-0.006
 erupt-0.005
 hyd-0.005
 frying-0.005
Token the
Token ID262
Feature activation+2.24e-01

Pos logit contributions
 frying+0.008
ksh+0.007
 hyd+0.007
 bowls+0.007
 erupt+0.007
Neg logit contributions
aces-0.007
oot-0.007
emaker-0.007
mate-0.007
 runner-0.006
Token boiling
Token ID24372
Feature activation-5.95e+00

Pos logit contributions
aces+0.009
oot+0.009
iest+0.009
 runner+0.009
emaker+0.009
Neg logit contributions
ksh-0.005
 erupt-0.005
rig-0.005
 bowls-0.005
 hamb-0.005
Token soup
Token ID17141
Feature activation-2.17e+00

Pos logit contributions
ksh+0.160
 frying+0.160
 bowls+0.159
 erupt+0.156
 hamb+0.149
Neg logit contributions
aces-0.247
oot-0.236
iest-0.226
emaker-0.221
orns-0.212
Token and
Token ID290
Feature activation-1.06e+00

Pos logit contributions
ksh+0.085
 bowls+0.081
 frying+0.081
 las+0.081
 apr+0.080
Neg logit contributions
aces-0.067
oot-0.059
iest-0.054
emaker-0.052
ance-0.050
Token spl
Token ID4328
Feature activation-2.80e+00

Pos logit contributions
ksh+0.033
 frying+0.031
 bowls+0.031
rig+0.030
 hyd+0.030
Neg logit contributions
aces-0.040
oot-0.036
ance-0.034
emaker-0.034
orns-0.033
Tokenashes
Token ID7465
Feature activation-1.88e+00

Pos logit contributions
 bowls+0.102
 dining+0.097
 las+0.095
 erupt+0.095
 stove+0.095
Neg logit contributions
aces-0.101
oot-0.097
agged-0.083
ance-0.082
orns-0.082
Token everywhere
Token ID8347
Feature activation-5.29e-01

Pos logit contributions
 bowls+0.067
 frying+0.067
ksh+0.065
 hyd+0.065
 erupt+0.065
Neg logit contributions
aces-0.065
oot-0.063
emaker-0.057
 runner-0.054
ance-0.054
Token every
Token ID790
Feature activation+2.16e+00

Pos logit contributions
 bowls+0.001
 frying+0.001
 boiling+0.001
 erupt+0.001
 hyd+0.001
Neg logit contributions
oot-0.001
aces-0.001
emaker-0.001
 runner-0.001
ance-0.001
Token bite
Token ID13197
Feature activation-7.51e-01

Pos logit contributions
oot+0.075
aces+0.075
emaker+0.069
 runner+0.068
iest+0.066
Neg logit contributions
 bowls-0.076
 hyd-0.073
 erupt-0.073
 frying-0.073
ksh-0.072
Token of
Token ID286
Feature activation-7.27e-01

Pos logit contributions
 bowls+0.029
 frying+0.028
 boiling+0.028
 erupt+0.028
 hyd+0.028
Neg logit contributions
oot-0.024
aces-0.024
emaker-0.021
 runner-0.021
ance-0.020
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
ksh+0.026
 hyd+0.026
 bowls+0.026
 frying+0.026
 erupt+0.026
Neg logit contributions
aces-0.024
oot-0.024
emaker-0.022
 runner-0.020
ance-0.020
Token ste
Token ID2876
Feature activation-2.35e+00

Pos logit contributions
iest+0.001
aces+0.001
 runner+0.001
emaker+0.001
 days+0.001
Neg logit contributions
 erupt-0.000
 hyd-0.000
ksh-0.000
 extingu-0.000
 frying-0.000
Tokenaming
Token ID3723
Feature activation-5.94e+00

Pos logit contributions
 erupt+0.089
 bowls+0.088
 frying+0.086
ksh+0.086
 grill+0.085
Neg logit contributions
aces-0.078
oot-0.077
emaker-0.069
iest-0.069
ance-0.066
Token hot
Token ID3024
Feature activation-4.41e+00

Pos logit contributions
 erupt+0.146
 hyd+0.135
ksh+0.133
 boiling+0.122
 bowls+0.120
Neg logit contributions
aces-0.273
iest-0.260
oot-0.248
emaker-0.241
 runner-0.238
Token pasta
Token ID26296
Feature activation-3.58e+00

Pos logit contributions
 erupt+0.122
ksh+0.112
 hyd+0.110
 bowls+0.106
rig+0.105
Neg logit contributions
aces-0.189
iest-0.183
oot-0.174
emaker-0.170
 runner-0.165
Token and
Token ID290
Feature activation-1.01e+00

Pos logit contributions
 bowls+0.138
 erupt+0.136
ksh+0.135
 hyd+0.135
 frying+0.135
Neg logit contributions
aces-0.114
oot-0.107
iest-0.096
emaker-0.094
 runner-0.092
Token enjoyed
Token ID8359
Feature activation-6.55e-01

Pos logit contributions
 bowls+0.032
 erupt+0.030
 frying+0.030
 hyd+0.030
 boiling+0.030
Neg logit contributions
oot-0.040
aces-0.040
emaker-0.036
 runner-0.035
ance-0.034
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
 bowls+0.022
 frying+0.021
 erupt+0.021
 hyd+0.021
 boiling+0.021
Neg logit contributions
oot-0.024
aces-0.024
emaker-0.022
 runner-0.021
ance-0.021
Tokenm
Token ID76
Feature activation-2.35e+00

Pos logit contributions
 erupt+0.048
 bowls+0.048
 frying+0.047
 hyd+0.046
 boiling+0.046
Neg logit contributions
oot-0.066
aces-0.066
emaker-0.060
iest-0.058
ance-0.057
Tokenallows
Token ID47205
Feature activation-2.83e+00

Pos logit contributions
 bowls+0.061
 las+0.060
 erupt+0.060
ksh+0.059
 bowl+0.057
Neg logit contributions
aces-0.102
oot-0.096
iest-0.089
ance-0.086
py-0.086
Token over
Token ID625
Feature activation-8.12e-01

Pos logit contributions
 bowls+0.101
 frying+0.098
 boiling+0.096
 hyd+0.095
 erupt+0.095
Neg logit contributions
oot-0.101
aces-0.101
emaker-0.087
 runner-0.085
ance-0.085
Token the
Token ID262
Feature activation-8.19e-01

Pos logit contributions
 frying+0.025
 bowls+0.025
 erupt+0.025
ksh+0.024
 hyd+0.024
Neg logit contributions
aces-0.030
oot-0.030
 runner-0.027
emaker-0.027
ance-0.026
Token camp
Token ID1413
Feature activation-3.01e+00

Pos logit contributions
 bowls+0.029
 frying+0.028
 erupt+0.028
 boiling+0.027
 hyd+0.027
Neg logit contributions
aces-0.026
oot-0.025
 runner-0.024
 racer-0.022
iest-0.022
Tokenfire
Token ID6495
Feature activation-5.94e+00

Pos logit contributions
 bowls+0.099
 frying+0.097
 boiling+0.096
 erupt+0.093
 las+0.092
Neg logit contributions
aces-0.113
oot-0.111
 runner-0.097
emaker-0.095
iest-0.095
Token.
Token ID13
Feature activation-2.03e-01

Pos logit contributions
 frying+0.238
 bowls+0.234
 las+0.230
 boiling+0.230
ksh+0.228
Neg logit contributions
aces-0.164
oot-0.153
iest-0.137
 runner-0.131
ance-0.126
Token
Token ID220
Feature activation+1.58e+00

Pos logit contributions
 bowls+0.007
 frying+0.007
 boiling+0.007
 hyd+0.007
 erupt+0.007
Neg logit contributions
oot-0.007
aces-0.007
emaker-0.007
 runner-0.006
iest-0.006
Token
Token ID198
Feature activation-4.44e-01

Pos logit contributions
oot+0.066
aces+0.065
emaker+0.059
 runner+0.057
ance+0.056
Neg logit contributions
 bowls-0.047
 frying-0.045
 boiling-0.045
 hyd-0.045
 erupt-0.045
Token
Token ID198
Feature activation-1.71e-01

Pos logit contributions
 bowls+0.011
 erupt+0.010
 frying+0.010
 boiling+0.010
 hyd+0.009
Neg logit contributions
aces-0.021
oot-0.021
emaker-0.020
 runner-0.019
ance-0.019
TokenOne
Token ID3198
Feature activation+1.56e+00

Pos logit contributions
 bowls+0.006
 frying+0.006
 boiling+0.006
 erupt+0.006
 hyd+0.006
Neg logit contributions
aces-0.006
oot-0.006
emaker-0.005
ance-0.005
iest-0.005
Token it
Token ID340
Feature activation+2.05e-01

Pos logit contributions
 frying+0.056
ksh+0.056
 hyd+0.055
 bowls+0.055
 erupt+0.053
Neg logit contributions
aces-0.057
oot-0.057
emaker-0.053
ance-0.051
 runner-0.049
Token come
Token ID1282
Feature activation-2.29e+00

Pos logit contributions
aces+0.007
oot+0.007
emaker+0.006
 runner+0.006
py+0.006
Neg logit contributions
 bowls-0.008
 frying-0.007
ksh-0.007
 hyd-0.007
 apr-0.007
Token out
Token ID503
Feature activation-2.54e+00

Pos logit contributions
 bowls+0.064
 frying+0.062
 boiling+0.059
 burgers+0.058
 hyd+0.058
Neg logit contributions
oot-0.101
aces-0.097
emaker-0.089
 runner-0.088
ance-0.085
Token of
Token ID286
Feature activation-1.07e+00

Pos logit contributions
 bowls+0.122
 frying+0.120
 hyd+0.118
ksh+0.117
 burgers+0.117
Neg logit contributions
oot-0.058
aces-0.055
emaker-0.048
 runner-0.045
iest-0.043
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
ksh+0.038
 frying+0.037
 bowls+0.035
 erupt+0.035
 las+0.034
Neg logit contributions
oot-0.036
aces-0.035
emaker-0.032
mate-0.031
 runner-0.031
Token seaw
Token ID32085
Feature activation-5.91e+00

Pos logit contributions
 runner+0.000
oot+0.000
 racer+0.000
iest+0.000
aces+0.000
Neg logit contributions
ksh-0.000
 apr-0.000
 frying-0.000
 erupt-0.000
 las-0.000
Tokeneed
Token ID2308
Feature activation-2.64e+00

Pos logit contributions
 bowls+0.196
 erupt+0.188
 boiling+0.187
 frying+0.187
 hyd+0.185
Neg logit contributions
oot-0.226
aces-0.223
emaker-0.198
 runner-0.194
ance-0.188
Token and
Token ID290
Feature activation-6.26e-01

Pos logit contributions
 frying+0.100
ksh+0.099
 bowls+0.097
 las+0.096
 erupt+0.096
Neg logit contributions
aces-0.084
oot-0.082
emaker-0.071
 runner-0.071
iest-0.069
Token walk
Token ID2513
Feature activation+5.10e-01

Pos logit contributions
 bowls+0.018
ksh+0.018
 frying+0.018
 hyd+0.017
 boiling+0.017
Neg logit contributions
aces-0.025
oot-0.025
emaker-0.022
 runner-0.022
ance-0.021
Token around
Token ID1088
Feature activation+1.26e-02

Pos logit contributions
oot+0.020
aces+0.019
emaker+0.017
 runner+0.017
iest+0.017
Neg logit contributions
 bowls-0.017
 frying-0.016
 boiling-0.016
 erupt-0.016
 hyd-0.016
Token the
Token ID262
Feature activation-4.52e-01

Pos logit contributions
aces+0.000
oot+0.000
 runner+0.000
mate+0.000
emaker+0.000
Neg logit contributions
 frying-0.000
ksh-0.000
 bowls-0.000
 burgers-0.000
 erupt-0.000
Token hand
Token ID1021
Feature activation+5.83e-02

Pos logit contributions
 erupt+0.061
ksh+0.058
 boiling+0.056
 frying+0.055
 las+0.055
Neg logit contributions
aces-0.051
oot-0.040
emaker-0.039
mate-0.039
 runner-0.037
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
aces+0.002
oot+0.002
ance+0.001
emaker+0.001
 runner+0.001
Neg logit contributions
 erupt-0.002
 bowls-0.002
 las-0.002
 frying-0.002
 boiling-0.002
Token walk
Token ID2513
Feature activation+6.60e-01

Pos logit contributions
ksh+0.037
 erupt+0.033
 boiling+0.032
 frying+0.032
rig+0.032
Neg logit contributions
aces-0.036
oot-0.032
 runner-0.032
 lear-0.031
ance-0.031
Token to
Token ID284
Feature activation-7.90e-01

Pos logit contributions
oot+0.025
aces+0.025
emaker+0.023
 runner+0.022
ance+0.022
Neg logit contributions
 bowls-0.022
 frying-0.021
 boiling-0.021
 erupt-0.021
 hyd-0.021
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
ksh+0.042
 appet+0.038
rig+0.038
 hyd+0.037
 frying+0.036
Neg logit contributions
mate-0.009
 herself-0.009
 runner-0.009
 recess-0.008
oot-0.008
Token dining
Token ID17423
Feature activation-5.91e+00

Pos logit contributions
aces+0.005
 runner+0.005
 racer+0.005
mate+0.005
iest+0.005
Neg logit contributions
 erupt-0.003
ksh-0.003
 hyd-0.003
rig-0.003
 reel-0.003
Token room
Token ID2119
Feature activation-2.30e+00

Pos logit contributions
ksh+0.160
 erupt+0.154
 boiling+0.141
 barbecue+0.137
 hyd+0.136
Neg logit contributions
aces-0.245
iest-0.220
oot-0.217
er-0.216
 days-0.208
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
 bowls+0.081
 frying+0.081
 erupt+0.080
ksh+0.080
 boiling+0.080
Neg logit contributions
aces-0.079
oot-0.078
emaker-0.066
 runner-0.066
ance-0.064
Token They
Token ID1119
Feature activation-3.34e-01

Pos logit contributions
 boiling+0.011
 erupt+0.011
 hyd+0.011
 bowls+0.011
 frying+0.011
Neg logit contributions
aces-0.009
oot-0.008
 runner-0.007
ance-0.007
 racer-0.007
Token sit
Token ID1650
Feature activation+3.09e-01

Pos logit contributions
ksh+0.012
 boiling+0.011
 burgers+0.011
 hyd+0.011
 las+0.011
Neg logit contributions
aces-0.011
 runner-0.010
oot-0.010
ance-0.009
 lear-0.009
Token on
Token ID319
Feature activation+2.40e+00

Pos logit contributions
oot+0.009
aces+0.009
emaker+0.008
 runner+0.007
ance+0.007
Neg logit contributions
 bowls-0.013
 frying-0.013
 erupt-0.013
 boiling-0.013
 hyd-0.013
Token her
Token ID607
Feature activation+7.71e-01

Pos logit contributions
ksh+0.067
 hyd+0.065
 bowls+0.064
 erupt+0.064
 frying+0.063
Neg logit contributions
aces-0.078
oot-0.076
iest-0.068
emaker-0.068
ance-0.068
Token mom
Token ID1995
Feature activation-4.00e-01

Pos logit contributions
aces+0.028
oot+0.027
 runner+0.025
 racer+0.024
emaker+0.024
Neg logit contributions
ksh-0.025
 bowls-0.024
 frying-0.024
 las-0.024
 boiling-0.023
Token standing
Token ID5055
Feature activation-1.75e+00

Pos logit contributions
ksh+0.014
 apr+0.014
 las+0.014
 hyd+0.014
 bowls+0.014
Neg logit contributions
oot-0.012
aces-0.012
emaker-0.011
stretched-0.011
py-0.010
Token over
Token ID625
Feature activation-1.60e+00

Pos logit contributions
ksh+0.064
 erupt+0.063
 bowls+0.062
 hamb+0.062
 burgers+0.061
Neg logit contributions
aces-0.057
oot-0.054
 runner-0.049
emaker-0.048
mate-0.046
Token the
Token ID262
Feature activation-8.60e-01

Pos logit contributions
ksh+0.058
 bowls+0.058
 frying+0.057
 erupt+0.057
 burgers+0.056
Neg logit contributions
aces-0.049
oot-0.049
 runner-0.045
mate-0.044
emaker-0.043
Token stove
Token ID27635
Feature activation-5.89e+00

Pos logit contributions
ksh+0.021
rig+0.020
 erupt+0.020
 reel+0.019
 empt+0.018
Neg logit contributions
aces-0.030
mate-0.029
iest-0.029
 runner-0.029
 days-0.028
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
ksh+0.230
 bowls+0.226
 las+0.223
 frying+0.221
 apr+0.221
Neg logit contributions
aces-0.170
oot-0.162
emaker-0.140
iest-0.138
 runner-0.136
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 bowls+0.001
 hyd+0.001
 erupt+0.001
ksh+0.001
 boiling+0.001
Neg logit contributions
oot-0.000
aces-0.000
 runner-0.000
ance-0.000
emaker-0.000
Token
Token ID198
Feature activation-2.40e-02

Pos logit contributions
 bowls+0.008
 hyd+0.007
 boiling+0.007
 frying+0.007
 erupt+0.007
Neg logit contributions
oot-0.010
aces-0.010
emaker-0.009
 runner-0.009
ance-0.008
Token"
Token ID1
Feature activation+1.66e+00

Pos logit contributions
 bowls+0.001
 erupt+0.001
 boiling+0.001
 hyd+0.001
 frying+0.001
Neg logit contributions
oot-0.001
aces-0.001
emaker-0.001
 runner-0.001
ance-0.000
TokenWhat
Token ID2061
Feature activation-1.13e+00

Pos logit contributions
emaker+0.050
oot+0.049
aces+0.049
Tweet+0.048
 runner+0.048
Neg logit contributions
 erupt-0.060
 bowls-0.060
 hyd-0.057
 frying-0.057
 grill-0.056
Token He
Token ID679
Feature activation+4.27e-01

Pos logit contributions
 bowls+0.025
 hyd+0.025
 erupt+0.025
 frying+0.025
 boiling+0.025
Neg logit contributions
aces-0.015
oot-0.014
emaker-0.012
 runner-0.011
ance-0.011
Token carried
Token ID5281
Feature activation+1.25e+00

Pos logit contributions
aces+0.014
oot+0.013
 racer+0.012
emaker+0.012
Tweet+0.011
Neg logit contributions
ksh-0.014
 erupt-0.013
 dining-0.013
 frying-0.013
 hyd-0.013
Token it
Token ID340
Feature activation+4.40e-01

Pos logit contributions
oot+0.049
aces+0.048
emaker+0.044
 runner+0.042
ance+0.041
Neg logit contributions
 bowls-0.041
 frying-0.039
 boiling-0.038
 erupt-0.038
 hyd-0.038
Token to
Token ID284
Feature activation-7.39e-01

Pos logit contributions
oot+0.017
aces+0.016
emaker+0.015
 runner+0.014
ance+0.014
Neg logit contributions
 bowls-0.015
 frying-0.014
 boiling-0.014
ksh-0.014
 hyd-0.014
Token the
Token ID262
Feature activation+4.13e-02

Pos logit contributions
ksh+0.033
 frying+0.031
 hyd+0.030
 bowls+0.030
rig+0.029
Neg logit contributions
oot-0.018
aces-0.017
mate-0.017
emaker-0.016
 racer-0.015
Token dining
Token ID17423
Feature activation-5.89e+00

Pos logit contributions
mate+0.001
 racer+0.001
 days+0.001
iest+0.001
 runner+0.001
Neg logit contributions
ksh-0.001
rig-0.001
 erupt-0.001
 gasp-0.001
 appet-0.001
Token room
Token ID2119
Feature activation-2.16e+00

Pos logit contributions
ksh+0.176
 erupt+0.160
 mad+0.148
rig+0.145
 reel+0.145
Neg logit contributions
aces-0.224
iest-0.207
er-0.205
 days-0.205
ross-0.198
Token and
Token ID290
Feature activation-6.04e-01

Pos logit contributions
 bowls+0.080
 frying+0.078
 erupt+0.077
ksh+0.077
 boiling+0.077
Neg logit contributions
aces-0.072
oot-0.071
emaker-0.062
 runner-0.061
iest-0.059
Token set
Token ID900
Feature activation+2.37e-01

Pos logit contributions
ksh+0.020
rig+0.019
 erupt+0.018
 bowls+0.018
 frying+0.017
Neg logit contributions
aces-0.020
oot-0.019
ance-0.017
emaker-0.017
mate-0.017
Token it
Token ID340
Feature activation-2.04e-01

Pos logit contributions
oot+0.008
aces+0.008
emaker+0.007
ance+0.007
mate+0.006
Neg logit contributions
 bowls-0.009
ksh-0.009
 frying-0.009
 hyd-0.009
 boiling-0.008
Token on
Token ID319
Feature activation+1.39e+00

Pos logit contributions
 frying+0.007
ksh+0.007
 bowls+0.007
 burgers+0.007
 las+0.007
Neg logit contributions
aces-0.007
oot-0.006
mate-0.006
iest-0.006
emaker-0.005
Token owner
Token ID4870
Feature activation+9.72e-01

Pos logit contributions
aces+0.087
oot+0.087
emaker+0.079
 runner+0.077
ance+0.075
Neg logit contributions
 bowls-0.064
 erupt-0.061
 frying-0.060
 hyd-0.060
 boiling-0.060
Token and
Token ID290
Feature activation-8.20e-01

Pos logit contributions
oot+0.041
aces+0.040
emaker+0.038
 runner+0.036
iest+0.035
Neg logit contributions
 bowls-0.028
 erupt-0.026
 burgers-0.026
 frying-0.026
 hyd-0.026
Token sniff
Token ID26300
Feature activation-5.65e-01

Pos logit contributions
 bowls+0.024
 frying+0.023
 erupt+0.023
 boiling+0.022
 hyd+0.022
Neg logit contributions
oot-0.035
aces-0.034
emaker-0.031
 runner-0.030
ance-0.030
Token all
Token ID477
Feature activation-6.26e-01

Pos logit contributions
 bowls+0.022
 boiling+0.021
 hyd+0.021
 burgers+0.021
 frying+0.021
Neg logit contributions
oot-0.018
aces-0.017
emaker-0.015
 runner-0.015
 racer-0.015
Token the
Token ID262
Feature activation+9.93e-01

Pos logit contributions
 bowls+0.020
 frying+0.019
 boiling+0.019
 erupt+0.019
 hyd+0.018
Neg logit contributions
oot-0.025
aces-0.025
emaker-0.023
 runner-0.022
ance-0.021
Token smells
Token ID25760
Feature activation-5.88e+00

Pos logit contributions
aces+0.037
oot+0.037
emaker+0.033
 runner+0.032
iest+0.031
Neg logit contributions
 bowls-0.033
 frying-0.032
 erupt-0.032
 hyd-0.032
 boiling-0.032
Token in
Token ID287
Feature activation-5.58e-02

Pos logit contributions
ksh+0.221
 bowls+0.219
 erupt+0.215
 hyd+0.212
 apr+0.208
Neg logit contributions
aces-0.180
iest-0.176
oot-0.168
emaker-0.150
ance-0.145
Token the
Token ID262
Feature activation+6.16e-01

Pos logit contributions
 bowls+0.002
ksh+0.002
 frying+0.002
 erupt+0.002
 hyd+0.002
Neg logit contributions
aces-0.002
oot-0.002
emaker-0.002
 runner-0.002
iest-0.002
Token park
Token ID3952
Feature activation-1.59e+00

Pos logit contributions
aces+0.026
oot+0.025
iest+0.023
 runner+0.023
emaker+0.023
Neg logit contributions
 erupt-0.016
ksh-0.016
 bowls-0.016
 hyd-0.015
 frying-0.015
Token.
Token ID13
Feature activation+3.53e-02

Pos logit contributions
 bowls+0.054
 frying+0.052
 boiling+0.051
 erupt+0.051
 hyd+0.051
Neg logit contributions
oot-0.058
aces-0.058
emaker-0.051
 runner-0.050
iest-0.049
Token One
Token ID1881
Feature activation+1.81e+00

Pos logit contributions
oot+0.001
aces+0.001
emaker+0.001
 runner+0.001
ance+0.001
Neg logit contributions
 bowls-0.001
 frying-0.001
 boiling-0.001
 erupt-0.001
 hyd-0.001
Token let
Token ID1309
Feature activation+7.21e-01

Pos logit contributions
 bowls+0.014
 boiling+0.014
ksh+0.014
 frying+0.014
 erupt+0.014
Neg logit contributions
aces-0.011
oot-0.011
emaker-0.011
 runner-0.010
mate-0.010
Token's
Token ID338
Feature activation-1.90e+00

Pos logit contributions
oot+0.029
emaker+0.029
ance+0.028
aces+0.028
elle+0.026
Neg logit contributions
 hyd-0.021
 erupt-0.020
 boiling-0.019
 bowls-0.019
 frying-0.019
Token go
Token ID467
Feature activation-1.73e+00

Pos logit contributions
ksh+0.065
 bowls+0.062
 boiling+0.060
 burgers+0.059
 las+0.059
Neg logit contributions
aces-0.064
oot-0.063
 runner-0.060
emaker-0.059
mate-0.058
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
 bowls+0.054
 frying+0.050
 hyd+0.050
 boiling+0.049
 erupt+0.049
Neg logit contributions
aces-0.072
oot-0.070
emaker-0.066
 runner-0.063
ross-0.061
Token the
Token ID262
Feature activation+3.39e-01

Pos logit contributions
ksh+0.042
 hyd+0.040
 frying+0.039
 bowls+0.039
 erupt+0.037
Neg logit contributions
oot-0.033
aces-0.029
emaker-0.028
 runner-0.028
ance-0.028
Token dining
Token ID17423
Feature activation-5.81e+00

Pos logit contributions
 racer+0.013
 runner+0.013
aces+0.013
mate+0.013
oot+0.012
Neg logit contributions
ksh-0.009
 erupt-0.008
 hyd-0.008
rig-0.008
 bowls-0.007
Token room
Token ID2119
Feature activation-2.16e+00

Pos logit contributions
ksh+0.140
 erupt+0.139
 boiling+0.132
 hyd+0.125
 frying+0.124
Neg logit contributions
aces-0.257
oot-0.233
iest-0.228
 runner-0.225
emaker-0.223
Token and
Token ID290
Feature activation-4.13e-01

Pos logit contributions
 bowls+0.079
 frying+0.077
 boiling+0.076
 erupt+0.076
 hyd+0.075
Neg logit contributions
aces-0.073
oot-0.073
emaker-0.064
 runner-0.062
ance-0.061
Token have
Token ID423
Feature activation+3.22e-01

Pos logit contributions
ksh+0.015
 bowls+0.013
 boiling+0.013
 las+0.013
 frying+0.013
Neg logit contributions
aces-0.012
oot-0.012
 runner-0.011
emaker-0.011
ance-0.011
Token a
Token ID257
Feature activation+2.54e-01

Pos logit contributions
aces+0.008
oot+0.007
orns+0.007
 days+0.007
ance+0.007
Neg logit contributions
rig-0.013
 hyd-0.013
 erupt-0.013
 frying-0.013
ksh-0.013
Token snack
Token ID26906
Feature activation+9.32e-01

Pos logit contributions
 racer+0.007
br+0.007
 runner+0.007
 seeker+0.007
 cape+0.007
Neg logit contributions
ksh-0.009
 hyd-0.008
ishment-0.008
 erupt-0.008
 boiling-0.008
Token.
Token ID13
Feature activation-2.88e-02

Pos logit contributions
 bowls+0.028
 frying+0.027
 boiling+0.027
 hyd+0.027
 erupt+0.027
Neg logit contributions
oot-0.035
aces-0.035
emaker-0.032
 runner-0.031
ance-0.030
Token Emily
Token ID17608
Feature activation+1.86e-01

Pos logit contributions
 bowls+0.001
 boiling+0.001
 frying+0.001
 Dad+0.001
 erupt+0.001
Neg logit contributions
oot-0.001
aces-0.001
emaker-0.001
iest-0.001
 runner-0.001
Token accidentally
Token ID14716
Feature activation+1.96e+00

Pos logit contributions
aces+0.007
oot+0.007
emaker+0.006
 runner+0.006
ance+0.006
Neg logit contributions
 bowls-0.006
 hyd-0.006
 boiling-0.006
 erupt-0.006
 burgers-0.006
Token knocked
Token ID13642
Feature activation-1.50e+00

Pos logit contributions
oot+0.077
aces+0.076
emaker+0.070
ance+0.066
 runner+0.066
Neg logit contributions
 bowls-0.063
ksh-0.059
 frying-0.059
 erupt-0.058
 hyd-0.058
Token the
Token ID262
Feature activation-1.18e+00

Pos logit contributions
 bowls+0.047
 boiling+0.045
 frying+0.043
 erupt+0.043
 Dad+0.042
Neg logit contributions
oot-0.061
aces-0.060
 runner-0.054
emaker-0.053
 racer-0.052
Token stove
Token ID27635
Feature activation-5.79e+00

Pos logit contributions
ksh+0.030
rig+0.028
itionally+0.024
prise+0.023
 erupt+0.022
Neg logit contributions
iest-0.052
 days-0.045
aces-0.045
working-0.043
est-0.042
Token off
Token ID572
Feature activation+8.61e-01

Pos logit contributions
 bowls+0.214
ksh+0.210
 frying+0.209
 apr+0.205
 hamb+0.203
Neg logit contributions
oot-0.184
aces-0.182
emaker-0.165
iest-0.159
mate-0.158
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
oot+0.038
aces+0.037
emaker+0.034
 runner+0.033
ance+0.032
Neg logit contributions
 bowls-0.025
 boiling-0.024
 frying-0.023
 erupt-0.023
 hyd-0.023
Token counter
Token ID3753
Feature activation-5.24e+00

Pos logit contributions
ksh+0.021
rig+0.020
prise+0.018
 erupt+0.017
 reel+0.017
Neg logit contributions
iest-0.045
aces-0.045
 days-0.044
working-0.042
 runner-0.041
Token!
Token ID0
Feature activation-9.08e-01

Pos logit contributions
ksh+0.213
 apr+0.204
 bowls+0.202
 frying+0.200
 las+0.200
Neg logit contributions
aces-0.153
oot-0.149
emaker-0.122
mate-0.116
ance-0.116
Token She
Token ID1375
Feature activation+6.56e-01

Pos logit contributions
 bowls+0.034
 frying+0.033
 boiling+0.032
 erupt+0.032
 hyd+0.032
Neg logit contributions
oot-0.031
aces-0.030
emaker-0.028
 runner-0.026
iest-0.026
Token the
Token ID262
Feature activation-5.61e-01

Pos logit contributions
 bowls+0.043
 boiling+0.041
 erupt+0.041
 Dad+0.040
 hyd+0.039
Neg logit contributions
aces-0.065
oot-0.064
emaker-0.057
 runner-0.057
iest-0.056
Token kind
Token ID1611
Feature activation-2.86e+00

Pos logit contributions
 bowls+0.021
 frying+0.021
 boiling+0.020
ksh+0.020
 hyd+0.020
Neg logit contributions
oot-0.018
aces-0.018
emaker-0.016
 runner-0.016
 racer-0.015
Token lady
Token ID10846
Feature activation-1.71e+00

Pos logit contributions
 bowls+0.092
 erupt+0.087
 grill+0.087
 hyd+0.086
 bowl+0.086
Neg logit contributions
aces-0.112
oot-0.105
emaker-0.097
 runner-0.095
ance-0.094
Token behind
Token ID2157
Feature activation-1.47e+00

Pos logit contributions
 bowls+0.055
 frying+0.052
 erupt+0.051
 boiling+0.051
 hyd+0.051
Neg logit contributions
oot-0.068
aces-0.067
emaker-0.061
 runner-0.059
ance-0.058
Token the
Token ID262
Feature activation-1.82e+00

Pos logit contributions
 bowls+0.046
 boiling+0.043
 frying+0.043
 erupt+0.042
 hyd+0.042
Neg logit contributions
oot-0.060
aces-0.060
emaker-0.055
 runner-0.053
ance-0.051
Token counter
Token ID3753
Feature activation-5.79e+00

Pos logit contributions
ksh+0.070
 bowls+0.067
 hyd+0.065
 frying+0.064
 boiling+0.064
Neg logit contributions
oot-0.058
aces-0.054
emaker-0.050
 runner-0.049
 racer-0.048
Token.
Token ID13
Feature activation-2.50e-01

Pos logit contributions
 bowls+0.210
ksh+0.207
 frying+0.207
 boiling+0.205
 erupt+0.203
Neg logit contributions
aces-0.196
oot-0.194
emaker-0.163
ance-0.158
 runner-0.155
Token
Token ID220
Feature activation+1.57e+00

Pos logit contributions
 bowls+0.008
 frying+0.008
 boiling+0.008
 erupt+0.008
 hyd+0.007
Neg logit contributions
oot-0.010
aces-0.010
emaker-0.009
 runner-0.009
ance-0.008
Token
Token ID198
Feature activation-5.13e-01

Pos logit contributions
oot+0.070
aces+0.069
emaker+0.064
 runner+0.063
iest+0.061
Neg logit contributions
 bowls-0.042
 frying-0.039
 erupt-0.039
 boiling-0.039
 hyd-0.038
Token
Token ID198
Feature activation-2.61e-01

Pos logit contributions
 bowls+0.013
 frying+0.012
 erupt+0.012
 boiling+0.012
 hyd+0.011
Neg logit contributions
aces-0.024
oot-0.024
emaker-0.022
 runner-0.021
ance-0.021
TokenAs
Token ID1722
Feature activation-3.26e-01

Pos logit contributions
 bowls+0.009
 frying+0.008
 boiling+0.008
 hyd+0.008
 erupt+0.008
Neg logit contributions
aces-0.010
oot-0.010
emaker-0.009
ance-0.009
iest-0.008
Token to
Token ID284
Feature activation-5.30e-01

Pos logit contributions
oot+0.062
aces+0.061
emaker+0.059
py+0.055
orns+0.054
Neg logit contributions
 bowls-0.037
 boiling-0.036
 hyd-0.034
 frying-0.034
 y-0.034
Token see
Token ID766
Feature activation-2.72e+00

Pos logit contributions
 bowls+0.016
 frying+0.015
 hyd+0.015
 boiling+0.015
 erupt+0.015
Neg logit contributions
oot-0.022
aces-0.022
emaker-0.020
 runner-0.019
ance-0.019
Token her
Token ID607
Feature activation+2.17e-01

Pos logit contributions
 bowls+0.078
 boiling+0.073
 frying+0.072
 erupt+0.072
 hyd+0.071
Neg logit contributions
oot-0.117
aces-0.115
emaker-0.107
 runner-0.103
 racer-0.099
Token Mum
Token ID38367
Feature activation-2.78e+00

Pos logit contributions
aces+0.008
oot+0.008
 runner+0.007
emaker+0.007
iest+0.007
Neg logit contributions
 bowls-0.007
ksh-0.007
 hyd-0.007
 boiling-0.007
 frying-0.007
Token be
Token ID307
Feature activation-6.10e-02

Pos logit contributions
 bowls+0.100
 hyd+0.098
 burgers+0.095
 las+0.095
 erupt+0.095
Neg logit contributions
oot-0.095
aces-0.094
emaker-0.082
 runner-0.080
ance-0.078
Tokenaming
Token ID3723
Feature activation-5.74e+00

Pos logit contributions
 bowls+0.002
ksh+0.002
 grill+0.002
 las+0.002
 burgers+0.002
Neg logit contributions
aces-0.002
oot-0.002
emaker-0.002
 runner-0.002
ross-0.002
Token with
Token ID351
Feature activation-1.39e+00

Pos logit contributions
 bowls+0.197
 erupt+0.189
 frying+0.187
 boiling+0.187
 hyd+0.185
Neg logit contributions
oot-0.208
aces-0.207
emaker-0.185
 runner-0.183
iest-0.175
Token pride
Token ID11293
Feature activation+7.46e-01

Pos logit contributions
ksh+0.046
 hyd+0.045
 frying+0.045
 bowls+0.044
 erupt+0.044
Neg logit contributions
aces-0.052
oot-0.049
stretched-0.045
ance-0.044
 runner-0.044
Token.
Token ID13
Feature activation-1.13e-01

Pos logit contributions
oot+0.030
aces+0.030
emaker+0.028
 runner+0.026
ance+0.026
Neg logit contributions
 bowls-0.023
 frying-0.022
 boiling-0.022
 hyd-0.022
 erupt-0.021
Token Sarah
Token ID10490
Feature activation+6.19e-01

Pos logit contributions
 bowls+0.004
 frying+0.003
 hyd+0.003
 boiling+0.003
 erupt+0.003
Neg logit contributions
oot-0.005
aces-0.004
emaker-0.004
 runner-0.004
ance-0.004
Token knew
Token ID2993
Feature activation+1.15e+00

Pos logit contributions
oot+0.024
aces+0.023
emaker+0.021
ance+0.020
 runner+0.020
Neg logit contributions
 bowls-0.020
 boiling-0.020
 erupt-0.019
 hyd-0.019
 frying-0.019
Token around
Token ID1088
Feature activation-3.41e-02

Pos logit contributions
oot+0.061
aces+0.061
emaker+0.058
iest+0.055
orns+0.054
Neg logit contributions
 bowls-0.041
 erupt-0.041
 hyd-0.039
 un-0.039
 grill-0.038
Token the
Token ID262
Feature activation-7.62e-01

Pos logit contributions
ksh+0.001
 frying+0.001
 bowls+0.001
 hyd+0.001
 burgers+0.001
Neg logit contributions
aces-0.001
oot-0.001
 runner-0.001
emaker-0.001
mate-0.001
Token hallway
Token ID23959
Feature activation-3.23e+00

Pos logit contributions
 erupt+0.024
ksh+0.023
rig+0.023
 reel+0.023
 hamb+0.022
Neg logit contributions
aces-0.024
 runner-0.022
 racer-0.022
 days-0.021
 villains-0.021
Token,
Token ID11
Feature activation+8.30e-02

Pos logit contributions
 bowls+0.110
 frying+0.105
 boiling+0.104
 erupt+0.103
 hyd+0.103
Neg logit contributions
oot-0.121
aces-0.120
emaker-0.108
 runner-0.104
ance-0.102
Token the
Token ID262
Feature activation+4.29e-01

Pos logit contributions
oot+0.003
aces+0.003
 runner+0.003
emaker+0.002
 racer+0.002
Neg logit contributions
 bowls-0.003
 frying-0.003
ksh-0.003
 erupt-0.003
 las-0.003
Token dining
Token ID17423
Feature activation-5.73e+00

Pos logit contributions
aces+0.018
 runner+0.017
oot+0.016
 racer+0.016
emaker+0.016
Neg logit contributions
 erupt-0.011
ksh-0.011
 bowls-0.011
 hyd-0.011
 frying-0.010
Token room
Token ID2119
Feature activation-2.27e+00

Pos logit contributions
ksh+0.155
 erupt+0.150
 boiling+0.139
rig+0.137
 burgers+0.134
Neg logit contributions
aces-0.242
iest-0.219
ross-0.210
 runner-0.208
 days-0.208
Token and
Token ID290
Feature activation-6.33e-01

Pos logit contributions
 bowls+0.071
 frying+0.068
 boiling+0.067
 erupt+0.067
 hyd+0.067
Neg logit contributions
oot-0.090
aces-0.090
emaker-0.081
 runner-0.079
iest-0.077
Token the
Token ID262
Feature activation+6.95e-01

Pos logit contributions
 bowls+0.020
 frying+0.019
 boiling+0.019
 erupt+0.019
 hyd+0.019
Neg logit contributions
oot-0.025
aces-0.025
emaker-0.023
 runner-0.022
ance-0.021
Token bedroom
Token ID14043
Feature activation-1.46e+00

Pos logit contributions
aces+0.029
 runner+0.027
 racer+0.026
oot+0.026
emaker+0.026
Neg logit contributions
 erupt-0.018
ksh-0.017
 hyd-0.017
 bowls-0.016
 frying-0.016
Token.
Token ID13
Feature activation-4.49e-01

Pos logit contributions
 bowls+0.047
 frying+0.046
 boiling+0.045
 erupt+0.045
 hyd+0.045
Neg logit contributions
aces-0.056
oot-0.055
emaker-0.049
 runner-0.048
iest-0.048
Token sweet
Token ID6029
Feature activation-4.64e+00

Pos logit contributions
aces+0.013
oot+0.013
 runner+0.012
emaker+0.012
iest+0.012
Neg logit contributions
 bowls-0.012
 frying-0.012
 erupt-0.012
 boiling-0.012
 hyd-0.012
Token scent
Token ID21212
Feature activation-2.23e+00

Pos logit contributions
 bowls+0.206
 frying+0.201
 hyd+0.199
 boiling+0.198
 erupt+0.198
Neg logit contributions
aces-0.118
oot-0.118
emaker-0.103
iest-0.103
 runner-0.098
Token of
Token ID286
Feature activation-1.16e+00

Pos logit contributions
 bowls+0.089
 frying+0.086
 hyd+0.085
 boiling+0.085
 erupt+0.084
Neg logit contributions
aces-0.069
oot-0.069
emaker-0.061
iest-0.058
 runner-0.058
Token the
Token ID262
Feature activation-9.32e-02

Pos logit contributions
 bowls+0.037
 frying+0.036
ksh+0.035
 hyd+0.034
 erupt+0.034
Neg logit contributions
aces-0.045
oot-0.044
emaker-0.040
 runner-0.039
ance-0.039
Token camp
Token ID1413
Feature activation-2.66e+00

Pos logit contributions
 bowls+0.003
 frying+0.003
 erupt+0.003
 boiling+0.003
 hyd+0.003
Neg logit contributions
aces-0.003
oot-0.003
 runner-0.003
iest-0.003
emaker-0.003
Tokenfire
Token ID6495
Feature activation-5.71e+00

Pos logit contributions
 bowls+0.079
 frying+0.076
 boiling+0.074
ksh+0.073
 erupt+0.072
Neg logit contributions
aces-0.109
oot-0.107
emaker-0.097
iest-0.096
 runner-0.095
Token.
Token ID13
Feature activation-3.25e-01

Pos logit contributions
 bowls+0.222
ksh+0.218
 frying+0.218
 apr+0.214
 las+0.212
Neg logit contributions
aces-0.168
oot-0.159
iest-0.152
emaker-0.143
 runner-0.139
Token
Token ID220
Feature activation+1.36e+00

Pos logit contributions
 bowls+0.011
 boiling+0.010
 frying+0.010
 hyd+0.010
 erupt+0.010
Neg logit contributions
oot-0.012
aces-0.012
emaker-0.011
ance-0.011
 runner-0.010
Token
Token ID198
Feature activation-6.30e-01

Pos logit contributions
oot+0.055
aces+0.055
emaker+0.049
ance+0.047
 runner+0.047
Neg logit contributions
 bowls-0.043
 frying-0.041
 boiling-0.041
 hyd-0.040
 erupt-0.040
Token
Token ID198
Feature activation-3.64e-01

Pos logit contributions
 bowls+0.019
 frying+0.018
 hyd+0.018
 boiling+0.018
 erupt+0.018
Neg logit contributions
oot-0.026
aces-0.026
emaker-0.023
 runner-0.023
ance-0.022
TokenWhen
Token ID2215
Feature activation-1.06e+00

Pos logit contributions
 bowls+0.013
 frying+0.013
 boiling+0.013
 erupt+0.013
 hyd+0.013
Neg logit contributions
oot-0.013
aces-0.013
emaker-0.011
 runner-0.011
ance-0.011
Token to
Token ID284
Feature activation-9.64e-01

Pos logit contributions
aces+0.026
oot+0.024
 runner+0.024
emaker+0.024
affe+0.023
Neg logit contributions
 boiling-0.014
 Dad-0.014
 y-0.014
 delicious-0.014
 cooking-0.014
Token be
Token ID307
Feature activation+9.20e-01

Pos logit contributions
 bowls+0.031
 frying+0.029
 boiling+0.029
 erupt+0.029
 hyd+0.028
Neg logit contributions
oot-0.038
aces-0.038
emaker-0.035
 runner-0.033
ance-0.033
Token careful
Token ID8161
Feature activation+6.03e-01

Pos logit contributions
oot+0.040
aces+0.040
emaker+0.037
 runner+0.036
ance+0.035
Neg logit contributions
 bowls-0.025
 frying-0.024
 erupt-0.024
 boiling-0.024
 hyd-0.023
Token around
Token ID1088
Feature activation-1.20e-01

Pos logit contributions
oot+0.024
aces+0.024
emaker+0.022
 runner+0.021
ance+0.021
Neg logit contributions
 bowls-0.018
 hyd-0.018
 boiling-0.018
 erupt-0.018
 frying-0.018
Token the
Token ID262
Feature activation-4.33e-01

Pos logit contributions
ksh+0.004
 erupt+0.004
 bowls+0.004
 frying+0.004
 hamb+0.004
Neg logit contributions
aces-0.004
oot-0.004
emaker-0.004
iest-0.004
py-0.003
Token stove
Token ID27635
Feature activation-5.71e+00

Pos logit contributions
rig+0.012
ksh+0.011
engu+0.011
 erupt+0.010
prise+0.009
Neg logit contributions
 days-0.016
aces-0.016
working-0.016
iest-0.015
 runner-0.015
Token when
Token ID618
Feature activation-1.17e+00

Pos logit contributions
 bowls+0.212
 frying+0.206
 boiling+0.202
 erupt+0.201
 hyd+0.199
Neg logit contributions
aces-0.191
oot-0.190
emaker-0.169
 runner-0.161
iest-0.159
Token her
Token ID607
Feature activation-3.43e-01

Pos logit contributions
 bowls+0.047
 boiling+0.045
 frying+0.045
 erupt+0.044
 hyd+0.044
Neg logit contributions
oot-0.038
aces-0.037
emaker-0.033
 runner-0.031
ance-0.030
Token mom
Token ID1995
Feature activation-1.68e+00

Pos logit contributions
ksh+0.012
 erupt+0.012
 boiling+0.011
 las+0.011
 bowls+0.011
Neg logit contributions
aces-0.011
oot-0.010
 runner-0.010
emaker-0.010
 racer-0.009
Tokenmy
Token ID1820
Feature activation-1.76e+00

Pos logit contributions
 bowls+0.057
 frying+0.054
 boiling+0.054
 erupt+0.054
 hyd+0.054
Neg logit contributions
oot-0.063
aces-0.062
emaker-0.057
 runner-0.054
ance-0.053
Token was
Token ID373
Feature activation-1.08e+00

Pos logit contributions
 bowls+0.059
 erupt+0.056
 boiling+0.055
 frying+0.055
ksh+0.055
Neg logit contributions
oot-0.066
aces-0.065
emaker-0.059
ance-0.056
 runner-0.056
Token you
Token ID345
Feature activation-1.64e-01

Pos logit contributions
oot+0.055
aces+0.054
emaker+0.050
 runner+0.048
ance+0.047
Neg logit contributions
 bowls-0.039
 erupt-0.037
 boiling-0.037
 hyd-0.037
 frying-0.037
Token can
Token ID460
Feature activation+1.33e-01

Pos logit contributions
 bowls+0.005
 erupt+0.005
 hyd+0.005
 frying+0.005
 boiling+0.005
Neg logit contributions
oot-0.007
aces-0.007
emaker-0.006
 runner-0.006
iest-0.006
Token always
Token ID1464
Feature activation+1.95e+00

Pos logit contributions
aces+0.005
oot+0.005
emaker+0.005
 runner+0.004
iest+0.004
Neg logit contributions
 bowls-0.004
 erupt-0.004
 hyd-0.004
 frying-0.004
 boiling-0.004
Token find
Token ID1064
Feature activation+5.41e-01

Pos logit contributions
oot+0.088
aces+0.088
emaker+0.083
 runner+0.077
iest+0.076
Neg logit contributions
 bowls-0.049
 erupt-0.049
 hyd-0.048
 frying-0.047
 grill-0.046
Token a
Token ID257
Feature activation-6.93e-01

Pos logit contributions
oot+0.023
aces+0.023
emaker+0.021
 runner+0.021
 racer+0.020
Neg logit contributions
 bowls-0.016
 boiling-0.015
 hyd-0.015
 erupt-0.014
 frying-0.014
Token friend
Token ID1545
Feature activation+3.60e+00

Pos logit contributions
 bowls+0.026
 boiling+0.025
ksh+0.025
 frying+0.025
 erupt+0.024
Neg logit contributions
oot-0.023
aces-0.022
 runner-0.021
emaker-0.020
 racer-0.020
Token to
Token ID284
Feature activation-2.46e-01

Pos logit contributions
oot+0.153
aces+0.148
emaker+0.138
 runner+0.130
ance+0.128
Neg logit contributions
 bowls-0.102
 hyd-0.098
 erupt-0.096
 frying-0.096
 grill-0.094
Token explore
Token ID7301
Feature activation+1.01e+00

Pos logit contributions
 erupt+0.006
 bowls+0.006
 clean+0.006
 un+0.006
 hyd+0.006
Neg logit contributions
aces-0.011
oot-0.011
emaker-0.010
 runner-0.010
iest-0.010
Token the
Token ID262
Feature activation+3.34e-01

Pos logit contributions
oot+0.043
aces+0.042
emaker+0.040
 runner+0.037
ance+0.036
Neg logit contributions
 bowls-0.030
 boiling-0.029
 hyd-0.028
 erupt-0.028
 frying-0.027
Token world
Token ID995
Feature activation-1.62e+00

Pos logit contributions
aces+0.010
oot+0.010
 runner+0.010
iest+0.009
orns+0.009
Neg logit contributions
 bowls-0.013
 frying-0.013
ksh-0.012
 boiling-0.012
 hyd-0.012
Token with
Token ID351
Feature activation-5.78e-01

Pos logit contributions
 bowls+0.052
 erupt+0.049
 frying+0.048
 hyd+0.048
 boiling+0.048
Neg logit contributions
oot-0.063
aces-0.062
emaker-0.058
 runner-0.055
ance-0.054
Token the
Token ID262
Feature activation+3.01e-01

Pos logit contributions
oot+0.030
aces+0.030
 runner+0.027
emaker+0.027
mate+0.026
Neg logit contributions
 bowls-0.029
 frying-0.029
ksh-0.027
 hyd-0.027
 boiling-0.027
Token road
Token ID2975
Feature activation-1.43e+00

Pos logit contributions
oot+0.009
aces+0.009
 runner+0.008
emaker+0.008
ance+0.008
Neg logit contributions
 bowls-0.012
 frying-0.012
 boiling-0.011
 hyd-0.011
 erupt-0.011
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
 bowls+0.040
 erupt+0.040
 hyd+0.038
 boiling+0.038
 frying+0.037
Neg logit contributions
oot-0.062
aces-0.061
emaker-0.058
 runner-0.055
ance-0.054
Token Bobby
Token ID17155
Feature activation-6.71e-01

Pos logit contributions
oot+0.006
aces+0.006
emaker+0.005
 runner+0.005
ance+0.005
Neg logit contributions
 bowls-0.010
 frying-0.009
 erupt-0.009
 boiling-0.009
 hyd-0.009
Token had
Token ID550
Feature activation+1.49e+00

Pos logit contributions
 bowls+0.025
 boiling+0.023
 frying+0.023
 erupt+0.023
ksh+0.023
Neg logit contributions
oot-0.024
aces-0.023
emaker-0.020
 runner-0.020
ance-0.019
Token never
Token ID1239
Feature activation+3.15e+00

Pos logit contributions
oot+0.062
emaker+0.060
aces+0.059
iest+0.055
 runner+0.055
Neg logit contributions
 un-0.044
 erupt-0.043
 bowls-0.043
 y-0.043
 clean-0.042
Token seen
Token ID1775
Feature activation-8.09e-02

Pos logit contributions
oot+0.138
aces+0.135
emaker+0.126
 runner+0.121
mate+0.120
Neg logit contributions
 bowls-0.086
 erupt-0.083
 frying-0.081
 hyd-0.080
 boiling-0.080
Token one
Token ID530
Feature activation+2.51e+00

Pos logit contributions
 bowls+0.002
 y+0.002
 pasta+0.002
 erupt+0.002
 burgers+0.002
Neg logit contributions
oot-0.004
aces-0.004
emaker-0.004
 runner-0.003
ross-0.003
Token before
Token ID878
Feature activation+4.40e-01

Pos logit contributions
oot+0.083
aces+0.083
emaker+0.073
ance+0.069
 runner+0.069
Neg logit contributions
 bowls-0.095
 erupt-0.092
 frying-0.092
 boiling-0.091
 hyd-0.090
Token and
Token ID290
Feature activation-3.32e-01

Pos logit contributions
oot+0.017
aces+0.017
emaker+0.016
 runner+0.015
ance+0.015
Neg logit contributions
 bowls-0.014
 boiling-0.013
 erupt-0.013
 frying-0.013
 hyd-0.013
Token he
Token ID339
Feature activation-6.55e-01

Pos logit contributions
 bowls+0.012
 frying+0.011
 erupt+0.011
 hyd+0.011
 boiling+0.011
Neg logit contributions
oot-0.012
aces-0.012
emaker-0.011
 runner-0.010
iest-0.010
Token man
Token ID582
Feature activation+2.36e+00

Pos logit contributions
oot+0.041
emaker+0.038
ance+0.037
aces+0.037
iest+0.034
Neg logit contributions
 grill-0.050
 bowls-0.049
 bowl-0.048
 erupt-0.048
 y-0.048
Tokene
Token ID68
Feature activation+1.35e+00

Pos logit contributions
oot+0.083
aces+0.082
emaker+0.073
 runner+0.070
ance+0.068
Neg logit contributions
 bowls-0.086
 frying-0.082
 boiling-0.082
 erupt-0.082
 hyd-0.081
Token and
Token ID290
Feature activation+7.77e-01

Pos logit contributions
oot+0.056
aces+0.055
emaker+0.054
 runner+0.051
iest+0.051
Neg logit contributions
 bowls-0.037
 grill-0.036
 hyd-0.036
 frying-0.036
 erupt-0.035
Token a
Token ID257
Feature activation+8.12e-01

Pos logit contributions
oot+0.044
emaker+0.041
aces+0.039
ance+0.038
 runner+0.037
Neg logit contributions
 y-0.019
 delicious-0.016
 hamb-0.016
 hot-0.015
 pasta-0.015
Token big
Token ID1263
Feature activation-7.75e-01

Pos logit contributions
oot+0.032
aces+0.031
emaker+0.028
 runner+0.027
ance+0.027
Neg logit contributions
 bowls-0.027
 frying-0.025
 boiling-0.025
 erupt-0.025
 hyd-0.025
Token tail
Token ID7894
Feature activation+3.16e+00

Pos logit contributions
 bowls+0.029
 frying+0.028
 boiling+0.028
 erupt+0.027
 hyd+0.027
Neg logit contributions
oot-0.026
aces-0.026
emaker-0.023
 runner-0.022
ance-0.022
Token.
Token ID13
Feature activation+4.64e-01

Pos logit contributions
oot+0.155
emaker+0.149
aces+0.147
ance+0.140
reetings+0.140
Neg logit contributions
 boiling-0.066
 bowls-0.066
 hyd-0.065
 dish-0.064
 erupt-0.064
Token He
Token ID679
Feature activation+9.35e-01

Pos logit contributions
oot+0.016
aces+0.016
emaker+0.014
 runner+0.013
ance+0.013
Neg logit contributions
 bowls-0.018
 frying-0.017
 erupt-0.017
 boiling-0.017
 hyd-0.016
Token was
Token ID373
Feature activation+5.80e-01

Pos logit contributions
oot+0.040
aces+0.038
emaker+0.037
ance+0.035
 runner+0.034
Neg logit contributions
 bowls-0.027
 hyd-0.026
 erupt-0.026
 y-0.026
 frying-0.026
Token very
Token ID845
Feature activation-9.30e-01

Pos logit contributions
oot+0.028
aces+0.028
emaker+0.026
 runner+0.025
ance+0.025
Neg logit contributions
 bowls-0.013
 frying-0.012
 boiling-0.012
 erupt-0.012
 hyd-0.012
Token alert
Token ID7995
Feature activation+1.76e-01

Pos logit contributions
 bowls+0.025
 frying+0.023
ksh+0.023
 boiling+0.023
 hyd+0.023
Neg logit contributions
oot-0.041
aces-0.040
 runner-0.037
emaker-0.037
iest-0.036
Token.
Token ID13
Feature activation+3.46e-01

Pos logit contributions
 bowls+0.024
 frying+0.023
 erupt+0.023
 boiling+0.023
 burgers+0.023
Neg logit contributions
oot-0.027
aces-0.026
emaker-0.024
 runner-0.023
ance-0.022
Token She
Token ID1375
Feature activation+9.88e-01

Pos logit contributions
oot+0.014
aces+0.013
emaker+0.012
iest+0.012
ance+0.012
Neg logit contributions
 bowls-0.012
 clean-0.011
 frying-0.011
 bowl-0.011
 boiling-0.011
Token had
Token ID550
Feature activation+2.16e+00

Pos logit contributions
oot+0.040
aces+0.040
emaker+0.037
 runner+0.035
ance+0.035
Neg logit contributions
 bowls-0.030
 frying-0.029
 hyd-0.029
 boiling-0.029
 erupt-0.029
Token a
Token ID257
Feature activation+1.08e+00

Pos logit contributions
oot+0.099
aces+0.097
emaker+0.091
 runner+0.087
ance+0.086
Neg logit contributions
 bowls-0.056
 frying-0.053
 boiling-0.052
 hyd-0.052
 erupt-0.051
Token red
Token ID2266
Feature activation+2.57e+00

Pos logit contributions
 runner+0.037
oot+0.037
aces+0.036
 racer+0.035
mate+0.033
Neg logit contributions
 erupt-0.036
 bowls-0.036
ksh-0.035
 boiling-0.034
 hyd-0.034
Token bike
Token ID7161
Feature activation+4.13e+00

Pos logit contributions
aces+0.113
oot+0.110
emaker+0.105
ance+0.100
ross+0.099
Neg logit contributions
 bowls-0.075
 grill-0.074
 bowl-0.074
 dish-0.072
 stove-0.071
Token that
Token ID326
Feature activation-5.51e-01

Pos logit contributions
aces+0.206
emaker+0.198
reetings+0.198
anced+0.197
ance+0.194
Neg logit contributions
 clean-0.086
 dish-0.079
 y-0.077
 hot-0.077
 frying-0.077
Token she
Token ID673
Feature activation+1.77e-01

Pos logit contributions
 clean+0.019
 Dad+0.018
 y+0.018
 un+0.018
 tidy+0.017
Neg logit contributions
oot-0.021
aces-0.020
emaker-0.019
agging-0.018
py-0.018
Token loved
Token ID6151
Feature activation-1.56e+00

Pos logit contributions
oot+0.009
emaker+0.009
aces+0.008
ross+0.008
ance+0.008
Neg logit contributions
 un-0.004
 clean-0.004
 y-0.004
 tidy-0.003
 else-0.003
Token to
Token ID284
Feature activation+3.93e-01

Pos logit contributions
 bowls+0.035
 y+0.035
 Dad+0.034
 dish+0.033
 un+0.033
Neg logit contributions
oot-0.072
aces-0.072
emaker-0.071
iest-0.068
ross-0.067
Token ride
Token ID6594
Feature activation+1.76e+00

Pos logit contributions
ross+0.021
oot+0.020
reetings+0.020
emaker+0.020
py+0.020
Neg logit contributions
 clean-0.008
 un-0.008
 stir-0.007
 cook-0.007
 cool-0.007
Token Benny
Token ID44275
Feature activation+6.60e-01

Pos logit contributions
oot+0.005
aces+0.005
emaker+0.004
 runner+0.004
ance+0.004
Neg logit contributions
 bowls-0.004
 frying-0.004
 boiling-0.004
 erupt-0.004
 hyd-0.004
Token was
Token ID373
Feature activation+3.49e-01

Pos logit contributions
oot+0.024
aces+0.023
emaker+0.021
 runner+0.020
ance+0.020
Neg logit contributions
 bowls-0.023
 frying-0.022
 boiling-0.022
 erupt-0.022
 hyd-0.022
Token a
Token ID257
Feature activation+6.04e-01

Pos logit contributions
oot+0.018
aces+0.018
emaker+0.017
 runner+0.016
ance+0.016
Neg logit contributions
 bowls-0.007
 frying-0.006
 boiling-0.006
 erupt-0.006
 hyd-0.006
Token very
Token ID845
Feature activation-8.62e-01

Pos logit contributions
 runner+0.022
 racer+0.022
oot+0.021
mate+0.020
emaker+0.019
Neg logit contributions
 bowls-0.020
ksh-0.019
 boiling-0.019
 burgers-0.019
 erupt-0.019
Token good
Token ID922
Feature activation+5.77e-01

Pos logit contributions
 bowls+0.020
 frying+0.018
 boiling+0.018
 erupt+0.018
 hyd+0.018
Neg logit contributions
oot-0.042
aces-0.041
emaker-0.038
 runner-0.038
iest-0.037
Token friend
Token ID1545
Feature activation+4.05e+00

Pos logit contributions
aces+0.022
oot+0.021
emaker+0.019
ance+0.018
iest+0.018
Neg logit contributions
 bowls-0.020
 frying-0.019
 hyd-0.019
 erupt-0.019
 boiling-0.019
Token.
Token ID13
Feature activation+4.14e-01

Pos logit contributions
aces+0.170
oot+0.168
emaker+0.154
ance+0.148
iest+0.147
Neg logit contributions
 bowls-0.115
 hyd-0.113
 frying-0.110
 erupt-0.109
 boiling-0.109
Token The
Token ID383
Feature activation+1.01e+00

Pos logit contributions
oot+0.017
aces+0.017
emaker+0.016
 runner+0.015
ance+0.015
Neg logit contributions
 bowls-0.012
 frying-0.012
 boiling-0.011
 erupt-0.011
 hyd-0.011
Token end
Token ID886
Feature activation-1.87e-01

Pos logit contributions
oot+0.035
aces+0.035
emaker+0.030
 runner+0.029
ance+0.029
Neg logit contributions
 bowls-0.038
 boiling-0.036
 frying-0.036
 erupt-0.036
 hyd-0.036
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
 bowls+0.008
 frying+0.008
 boiling+0.007
 burgers+0.007
 hamb+0.007
Neg logit contributions
oot-0.006
aces-0.005
emaker-0.005
mate-0.005
iest-0.005
Token<|endoftext|>
Token ID50256
Feature activation-2.37e-01

Pos logit contributions
oot+0.009
aces+0.008
emaker+0.008
ance+0.007
 runner+0.007
Neg logit contributions
 bowls-0.007
 frying-0.007
 erupt-0.007
 hyd-0.007
 boiling-0.007
Token this
Token ID428
Feature activation+3.08e-01

Pos logit contributions
 bowls+0.025
 frying+0.024
 boiling+0.023
 hyd+0.023
 erupt+0.023
Neg logit contributions
oot-0.033
aces-0.032
emaker-0.029
 runner-0.028
ance-0.027
Token beautiful
Token ID4950
Feature activation-2.15e+00

Pos logit contributions
aces+0.012
oot+0.012
emaker+0.011
 runner+0.010
iest+0.010
Neg logit contributions
 bowls-0.010
 frying-0.009
ksh-0.009
 hyd-0.009
 erupt-0.009
Token thing
Token ID1517
Feature activation+8.47e-01

Pos logit contributions
 bowls+0.067
 frying+0.063
 boiling+0.063
 hyd+0.062
 erupt+0.062
Neg logit contributions
oot-0.089
aces-0.087
emaker-0.080
 runner-0.075
ance-0.075
Token will
Token ID481
Feature activation+3.72e-01

Pos logit contributions
oot+0.031
aces+0.031
emaker+0.028
 runner+0.027
ance+0.027
Neg logit contributions
 bowls-0.029
 frying-0.028
 boiling-0.027
 hyd-0.027
 erupt-0.027
Token still
Token ID991
Feature activation+4.21e-01

Pos logit contributions
oot+0.016
aces+0.016
emaker+0.015
 runner+0.014
ance+0.014
Neg logit contributions
 bowls-0.010
 erupt-0.010
 hyd-0.010
 boiling-0.010
 frying-0.010
Token be
Token ID307
Feature activation+1.12e+00

Pos logit contributions
oot+0.018
aces+0.017
emaker+0.016
 runner+0.015
ance+0.015
Neg logit contributions
 bowls-0.013
 frying-0.012
 boiling-0.012
 hyd-0.012
 erupt-0.012
Token here
Token ID994
Feature activation-1.08e+00

Pos logit contributions
oot+0.048
aces+0.048
emaker+0.043
iest+0.042
 runner+0.042
Neg logit contributions
 bowls-0.032
 frying-0.031
 boiling-0.030
 grill-0.029
 hyd-0.029
Token when
Token ID618
Feature activation-3.90e-01

Pos logit contributions
 bowls+0.037
 frying+0.035
 boiling+0.035
 erupt+0.035
 hyd+0.034
Neg logit contributions
oot-0.040
aces-0.040
emaker-0.036
 runner-0.035
ance-0.034
Token you
Token ID345
Feature activation-8.62e-01

Pos logit contributions
 bowls+0.012
 boiling+0.011
 erupt+0.011
 frying+0.011
 hyd+0.011
Neg logit contributions
oot-0.016
aces-0.016
emaker-0.015
 runner-0.014
ance-0.014
Token come
Token ID1282
Feature activation-2.00e+00

Pos logit contributions
 bowls+0.027
 frying+0.026
 boiling+0.026
 burgers+0.025
ksh+0.025
Neg logit contributions
aces-0.034
oot-0.034
emaker-0.031
ance-0.030
 runner-0.030
Token back
Token ID736
Feature activation-6.80e-01

Pos logit contributions
 erupt+0.054
 hyd+0.054
 bowls+0.053
 frying+0.051
 boiling+0.050
Neg logit contributions
aces-0.088
oot-0.087
emaker-0.082
 runner-0.077
iest-0.076
Token and
Token ID290
Feature activation-5.02e-01

Pos logit contributions
oot+0.030
aces+0.028
Tweet+0.027
emaker+0.027
 runner+0.026
Neg logit contributions
 bowls-0.020
 hyd-0.020
 boiling-0.019
 dish-0.019
 frying-0.019
Token went
Token ID1816
Feature activation-3.53e-01

Pos logit contributions
 bowls+0.014
 hyd+0.014
 erupt+0.013
 y+0.013
 frying+0.013
Neg logit contributions
oot-0.021
aces-0.021
emaker-0.020
 runner-0.019
orns-0.019
Token to
Token ID284
Feature activation-1.10e+00

Pos logit contributions
 clean+0.009
 bowls+0.009
 frying+0.009
 sink+0.009
 un+0.009
Neg logit contributions
aces-0.016
emaker-0.015
oot-0.015
iest-0.014
affe-0.014
Token play
Token ID711
Feature activation+1.18e+00

Pos logit contributions
 bowls+0.039
 frying+0.038
 hyd+0.038
ksh+0.038
 boiling+0.037
Neg logit contributions
oot-0.039
aces-0.038
emaker-0.035
 runner-0.034
ance-0.033
Token on
Token ID319
Feature activation+2.05e+00

Pos logit contributions
oot+0.044
aces+0.044
emaker+0.039
 runner+0.038
ance+0.037
Neg logit contributions
 bowls-0.040
 frying-0.039
 erupt-0.038
 boiling-0.038
 hyd-0.038
Token the
Token ID262
Feature activation+4.63e-01

Pos logit contributions
oot+0.083
aces+0.083
emaker+0.075
 runner+0.073
ance+0.071
Neg logit contributions
 bowls-0.064
 frying-0.060
 boiling-0.060
 erupt-0.060
 hyd-0.060
Token swings
Token ID26728
Feature activation-6.41e-01

Pos logit contributions
oot+0.016
aces+0.016
 runner+0.015
 racer+0.015
emaker+0.014
Neg logit contributions
 bowls-0.016
ksh-0.015
 hyd-0.015
 frying-0.015
 boiling-0.015
Token.
Token ID13
Feature activation-3.38e-01

Pos logit contributions
 bowls+0.018
 erupt+0.017
 hyd+0.017
 boiling+0.017
 grill+0.017
Neg logit contributions
oot-0.027
aces-0.026
emaker-0.024
ance-0.023
py-0.023
Token<|endoftext|>
Token ID50256
Feature activation-3.59e-01

Pos logit contributions
 bowls+0.011
 frying+0.010
 boiling+0.010
 erupt+0.010
 hyd+0.010
Neg logit contributions
oot-0.014
aces-0.013
emaker-0.012
 runner-0.012
ance-0.012
TokenOnce
Token ID7454
Feature activation-4.89e-02

Pos logit contributions
 bowls+0.010
 frying+0.009
 boiling+0.009
 erupt+0.009
 hyd+0.009
Neg logit contributions
oot-0.016
aces-0.015
emaker-0.014
 runner-0.014
ance-0.013
Token upon
Token ID2402
Feature activation-6.59e-01

Pos logit contributions
 bowls+0.002
 Dad+0.001
 boiling+0.001
 bowl+0.001
 erupt+0.001
Neg logit contributions
aces-0.002
oot-0.002
ance-0.002
emaker-0.002
 runner-0.002
Token smelled
Token ID37609
Feature activation-4.40e+00

Pos logit contributions
 bowls+0.005
 frying+0.004
 hyd+0.004
ksh+0.004
 erupt+0.004
Neg logit contributions
aces-0.007
oot-0.006
emaker-0.006
 runner-0.006
iest-0.006
Token bad
Token ID2089
Feature activation-4.41e-01

Pos logit contributions
ksh+0.149
 bowls+0.141
 apr+0.137
 hyd+0.137
 frying+0.133
Neg logit contributions
aces-0.151
iest-0.149
oot-0.139
 runner-0.128
mate-0.128
Token.
Token ID13
Feature activation+1.70e-02

Pos logit contributions
 bowls+0.016
 frying+0.015
 hyd+0.015
 erupt+0.015
 boiling+0.015
Neg logit contributions
aces-0.016
oot-0.015
emaker-0.013
 runner-0.013
iest-0.013
Token
Token ID198
Feature activation-4.68e-01

Pos logit contributions
oot+0.001
aces+0.001
emaker+0.001
 runner+0.001
iest+0.001
Neg logit contributions
 bowls-0.001
 frying-0.001
 boiling-0.001
 erupt-0.001
 hyd-0.001
Token
Token ID198
Feature activation-2.43e-01

Pos logit contributions
 bowls+0.013
 frying+0.012
 boiling+0.012
 erupt+0.012
 hyd+0.012
Neg logit contributions
aces-0.021
oot-0.021
emaker-0.019
 runner-0.019
ance-0.018
Token"
Token ID1
Feature activation+1.62e+00

Pos logit contributions
 bowls+0.008
 frying+0.008
 boiling+0.008
 hyd+0.008
 clean+0.008
Neg logit contributions
oot-0.009
aces-0.009
emaker-0.008
ance-0.008
py-0.008
TokenY
Token ID56
Feature activation-1.10e+00

Pos logit contributions
aces+0.048
emaker+0.048
 runner+0.047
Tweet+0.047
oot+0.047
Neg logit contributions
 bowls-0.061
 erupt-0.059
 frying-0.058
 burgers-0.057
 hyd-0.057
Tokenuck
Token ID1347
Feature activation+7.58e-01

Pos logit contributions
 bowls+0.045
 hyd+0.044
 erupt+0.043
 boiling+0.043
 frying+0.043
Neg logit contributions
oot-0.036
aces-0.034
ance-0.030
emaker-0.029
iest-0.028
Token!"
Token ID2474
Feature activation-4.91e-02

Pos logit contributions
oot+0.025
aces+0.024
emaker+0.022
 runner+0.021
iest+0.020
Neg logit contributions
 bowls-0.029
 frying-0.028
 hyd-0.028
 erupt-0.028
 boiling-0.028
Token Lily
Token ID20037
Feature activation+4.56e-01

Pos logit contributions
 bowls+0.002
 frying+0.002
 boiling+0.002
 erupt+0.002
 hyd+0.002
Neg logit contributions
oot-0.002
aces-0.002
emaker-0.002
 runner-0.002
ance-0.002
Token said
Token ID531
Feature activation+1.27e+00

Pos logit contributions
aces+0.019
oot+0.018
emaker+0.016
 runner+0.016
ance+0.015
Neg logit contributions
 bowls-0.014
 boiling-0.013
 hyd-0.013
 erupt-0.013
 frying-0.013
Token on
Token ID319
Feature activation+1.38e+00

Pos logit contributions
aces+0.030
oot+0.029
emaker+0.028
py+0.026
affe+0.025
Neg logit contributions
 bowls-0.021
 boiling-0.020
 hyd-0.020
 Dad-0.019
 erupt-0.019
Token the
Token ID262
Feature activation-8.85e-02

Pos logit contributions
oot+0.054
aces+0.053
 runner+0.048
ance+0.047
emaker+0.047
Neg logit contributions
 bowls-0.043
 erupt-0.042
 frying-0.041
 hyd-0.041
 boiling-0.040
Token grass
Token ID8701
Feature activation-2.15e+00

Pos logit contributions
 bowls+0.003
 frying+0.003
 erupt+0.003
 boiling+0.003
 hyd+0.003
Neg logit contributions
oot-0.003
aces-0.003
emaker-0.003
 runner-0.003
ance-0.003
Token.
Token ID13
Feature activation-3.24e-01

Pos logit contributions
 bowls+0.066
 hyd+0.062
 boiling+0.061
 frying+0.061
 erupt+0.061
Neg logit contributions
oot-0.087
aces-0.087
emaker-0.081
 runner-0.076
ance-0.074
Token Soon
Token ID15894
Feature activation-3.43e-01

Pos logit contributions
 bowls+0.011
 erupt+0.011
 hyd+0.011
 boiling+0.011
 frying+0.011
Neg logit contributions
aces-0.011
oot-0.011
 runner-0.010
ance-0.010
emaker-0.010
Token,
Token ID11
Feature activation+2.48e-01

Pos logit contributions
 bowls+0.012
 frying+0.011
 boiling+0.011
 hyd+0.011
 erupt+0.011
Neg logit contributions
oot-0.013
aces-0.013
emaker-0.012
 runner-0.011
py-0.011
Token Maya
Token ID26041
Feature activation-1.11e+00

Pos logit contributions
oot+0.010
aces+0.010
 runner+0.009
emaker+0.009
ance+0.009
Neg logit contributions
 bowls-0.008
 erupt-0.008
 frying-0.007
 hyd-0.007
 boiling-0.007
Token cheered
Token ID34767
Feature activation-1.97e+00

Pos logit contributions
 bowls+0.038
 erupt+0.037
 boiling+0.036
 hyd+0.036
 burgers+0.035
Neg logit contributions
aces-0.040
oot-0.040
emaker-0.035
 runner-0.035
ance-0.034
Token up
Token ID510
Feature activation-1.72e-01

Pos logit contributions
 bowls+0.071
 frying+0.068
 erupt+0.067
 boiling+0.067
 hyd+0.067
Neg logit contributions
oot-0.070
aces-0.069
emaker-0.062
 runner-0.060
ance-0.059
Token and
Token ID290
Feature activation-1.15e+00

Pos logit contributions
 bowls+0.005
 boiling+0.005
 hyd+0.005
 frying+0.005
 erupt+0.005
Neg logit contributions
aces-0.007
oot-0.007
emaker-0.007
orns-0.006
ance-0.006
Token felt
Token ID2936
Feature activation+9.76e-01

Pos logit contributions
 bowls+0.035
 erupt+0.033
 frying+0.033
 boiling+0.033
 hyd+0.033
Neg logit contributions
oot-0.047
aces-0.046
emaker-0.042
 runner-0.041
ance-0.040
Token?
Token ID30
Feature activation+1.01e+00

Pos logit contributions
aces+0.035
oot+0.035
emaker+0.032
 runner+0.030
ance+0.029
Neg logit contributions
 bowls-0.026
 boiling-0.025
 erupt-0.025
 frying-0.025
 hyd-0.025
Tokenâ
Token ID22940
Feature activation-3.48e-01

Pos logit contributions
oot+0.040
aces+0.040
emaker+0.036
 runner+0.035
iest+0.034
Neg logit contributions
 bowls-0.032
 frying-0.030
 hyd-0.030
 boiling-0.030
 erupt-0.030
Token€
Token ID26391
Feature activation+1.25e+00

Pos logit contributions
 bowls+0.013
 frying+0.012
 boiling+0.012
 burgers+0.012
 erupt+0.012
Neg logit contributions
oot-0.013
aces-0.012
emaker-0.011
ance-0.011
 runner-0.010
Token The
Token ID383
Feature activation+8.37e-01

Pos logit contributions
aces+0.045
oot+0.045
emaker+0.039
 runner+0.039
 racer+0.038
Neg logit contributions
 bowls-0.044
 boiling-0.043
 frying-0.041
 burgers-0.040
ksh-0.040
Token troll
Token ID13278
Feature activation-1.04e+00

Pos logit contributions
oot+0.031
aces+0.031
emaker+0.028
 runner+0.027
ance+0.026
Neg logit contributions
 bowls-0.029
 erupt-0.028
 hyd-0.028
 frying-0.028
 boiling-0.028
Token replied
Token ID8712
Feature activation+6.38e-01

Pos logit contributions
 bowls+0.028
 frying+0.026
 boiling+0.025
 hyd+0.025
 erupt+0.025
Neg logit contributions
oot-0.046
aces-0.046
emaker-0.042
 runner-0.041
iest-0.040
Token,
Token ID11
Feature activation+3.50e-01

Pos logit contributions
oot+0.021
aces+0.021
emaker+0.019
 runner+0.018
ance+0.017
Neg logit contributions
 bowls-0.024
 frying-0.024
 hyd-0.023
 boiling-0.023
 erupt-0.023
Token �
Token ID6184
Feature activation+2.18e-01

Pos logit contributions
oot+0.012
aces+0.012
emaker+0.010
 runner+0.010
ance+0.010
Neg logit contributions
 bowls-0.013
 frying-0.013
 erupt-0.012
 boiling-0.012
 hyd-0.012
Token�
Token ID95
Feature activation-1.57e-01

Pos logit contributions
oot+0.006
aces+0.005
ance+0.004
 runner+0.004
ross+0.004
Neg logit contributions
 bowls-0.011
 boiling-0.010
 burgers-0.010
 frying-0.010
 towels-0.010
Token€
Token ID26391
Feature activation+1.06e+00

Pos logit contributions
 bowls+0.006
 boiling+0.006
 frying+0.006
 burgers+0.006
 erupt+0.005
Neg logit contributions
aces-0.005
oot-0.005
ance-0.005
emaker-0.004
ross-0.004
Token�
Token ID129
Feature activation-1.89e-01

Pos logit contributions
oot+0.039
aces+0.039
emaker+0.035
 runner+0.034
ance+0.033
Neg logit contributions
 bowls-0.037
 boiling-0.036
 frying-0.035
 erupt-0.034
 hyd-0.034
Token.
Token ID13
Feature activation+3.41e-01

Pos logit contributions
 bowls+0.023
 erupt+0.021
 hyd+0.021
 boiling+0.021
 frying+0.021
Neg logit contributions
oot-0.031
aces-0.030
emaker-0.028
 runner-0.027
ance-0.026
Token
Token ID198
Feature activation-3.29e-01

Pos logit contributions
oot+0.010
aces+0.010
 runner+0.009
 Kit+0.008
 Bounce+0.008
Neg logit contributions
 erupt-0.014
 hyd-0.013
 boiling-0.013
 bowls-0.013
 frying-0.013
Token
Token ID198
Feature activation-9.08e-02

Pos logit contributions
 bowls+0.011
 hyd+0.011
 frying+0.011
 erupt+0.011
 boiling+0.011
Neg logit contributions
oot-0.012
aces-0.012
emaker-0.011
 runner-0.010
mate-0.010
Token"
Token ID1
Feature activation+1.64e+00

Pos logit contributions
 bowls+0.004
 erupt+0.004
 hyd+0.004
 frying+0.004
 boiling+0.004
Neg logit contributions
oot-0.002
aces-0.002
 runner-0.002
emaker-0.002
 racer-0.002
TokenCan
Token ID6090
Feature activation-1.99e+00

Pos logit contributions
 runner+0.045
 racer+0.044
mate+0.044
oot+0.044
aces+0.043
Neg logit contributions
 bowls-0.065
 erupt-0.064
 boiling-0.062
 frying-0.061
 pasta-0.060
Token we
Token ID356
Feature activation-1.41e+00

Pos logit contributions
 bowls+0.055
 frying+0.052
 erupt+0.051
 boiling+0.051
 hyd+0.051
Neg logit contributions
oot-0.088
aces-0.087
emaker-0.080
 runner-0.077
ance-0.076
Token go
Token ID467
Feature activation-1.11e+00

Pos logit contributions
 bowls+0.046
ksh+0.045
 boiling+0.044
 frying+0.043
 dining+0.043
Neg logit contributions
oot-0.053
aces-0.050
 runner-0.048
emaker-0.047
 racer-0.047
Token,
Token ID11
Feature activation+4.87e-01

Pos logit contributions
 bowls+0.030
 erupt+0.030
 hyd+0.029
 frying+0.029
 boiling+0.029
Neg logit contributions
aces-0.050
oot-0.048
emaker-0.046
ross-0.043
 runner-0.043
Token mom
Token ID1995
Feature activation+7.46e-01

Pos logit contributions
oot+0.017
aces+0.017
 runner+0.017
 racer+0.017
mate+0.016
Neg logit contributions
 frying-0.014
ksh-0.014
 bowls-0.014
 erupt-0.013
 boiling-0.013
Token?"
Token ID1701
Feature activation+9.12e-01

Pos logit contributions
oot+0.023
aces+0.022
emaker+0.020
 runner+0.019
iest+0.018
Neg logit contributions
 bowls-0.031
 boiling-0.030
 frying-0.029
 hyd-0.029
ksh-0.029
Token Lily
Token ID20037
Feature activation+2.53e-01

Pos logit contributions
oot+0.030
aces+0.030
emaker+0.027
 runner+0.027
 racer+0.025
Neg logit contributions
 bowls-0.033
 erupt-0.033
 hyd-0.033
 frying-0.032
 boiling-0.032
Token an
Token ID281
Feature activation+7.56e-01

Pos logit contributions
 bowls+0.015
 hyd+0.015
 erupt+0.014
 frying+0.014
 boiling+0.014
Neg logit contributions
aces-0.023
oot-0.023
emaker-0.021
 runner-0.020
iest-0.020
Token incredible
Token ID8082
Feature activation-3.52e-01

Pos logit contributions
oot+0.031
aces+0.030
 runner+0.026
iest+0.026
emaker+0.026
Neg logit contributions
 bowls-0.025
 frying-0.023
 hyd-0.022
 boiling-0.022
 erupt-0.022
Token day
Token ID1110
Feature activation+1.37e+00

Pos logit contributions
 bowls+0.012
 frying+0.011
ksh+0.011
 erupt+0.011
 boiling+0.011
Neg logit contributions
oot-0.013
aces-0.012
 runner-0.012
emaker-0.011
iest-0.011
Token,
Token ID11
Feature activation+1.12e+00

Pos logit contributions
oot+0.052
aces+0.051
emaker+0.047
 runner+0.045
ance+0.044
Neg logit contributions
 bowls-0.046
 frying-0.044
 boiling-0.044
 hyd-0.044
 erupt-0.043
Token made
Token ID925
Feature activation+4.16e-01

Pos logit contributions
oot+0.042
aces+0.042
emaker+0.038
 runner+0.036
ance+0.035
Neg logit contributions
 bowls-0.038
 frying-0.036
 boiling-0.036
 erupt-0.036
 hyd-0.036
Token even
Token ID772
Feature activation-9.02e-01

Pos logit contributions
oot+0.016
aces+0.015
emaker+0.014
ance+0.013
 runner+0.013
Neg logit contributions
 bowls-0.014
 frying-0.014
 hyd-0.013
 erupt-0.013
 boiling-0.013
Token better
Token ID1365
Feature activation+5.82e-01

Pos logit contributions
 bowls+0.028
 hyd+0.027
 frying+0.027
 erupt+0.027
 boiling+0.027
Neg logit contributions
aces-0.035
oot-0.034
emaker-0.032
 runner-0.031
iest-0.030
Token by
Token ID416
Feature activation+7.19e-01

Pos logit contributions
oot+0.020
aces+0.020
emaker+0.018
 runner+0.017
ance+0.017
Neg logit contributions
 bowls-0.022
 frying-0.021
 boiling-0.020
 erupt-0.020
 hyd-0.020
Token the
Token ID262
Feature activation-4.16e-01

Pos logit contributions
aces+0.030
oot+0.030
emaker+0.028
 runner+0.027
iest+0.026
Neg logit contributions
 bowls-0.022
 boiling-0.021
 erupt-0.021
 hyd-0.020
 cooking-0.020
Token mail
Token ID6920
Feature activation-1.89e+00

Pos logit contributions
 bowls+0.014
 frying+0.013
 erupt+0.013
 boiling+0.013
ksh+0.013
Neg logit contributions
oot-0.015
aces-0.015
 runner-0.014
 racer-0.013
emaker-0.013
Token she
Token ID673
Feature activation-1.60e+00

Pos logit contributions
 bowls+0.056
 hyd+0.055
 erupt+0.054
 frying+0.054
 boiling+0.053
Neg logit contributions
oot-0.076
aces-0.076
emaker-0.069
 runner-0.066
orns-0.066
Token.
Token ID13
Feature activation-2.50e-01

Pos logit contributions
 bowls+0.048
 frying+0.045
 erupt+0.045
 boiling+0.045
 hyd+0.045
Neg logit contributions
oot-0.059
aces-0.058
emaker-0.053
 runner-0.051
ance-0.050
Token
Token ID220
Feature activation+1.41e+00

Pos logit contributions
 bowls+0.009
 frying+0.008
 boiling+0.008
 erupt+0.008
 hyd+0.008
Neg logit contributions
oot-0.009
aces-0.009
emaker-0.008
 runner-0.008
ance-0.008
Token
Token ID198
Feature activation-6.33e-01

Pos logit contributions
oot+0.057
aces+0.057
emaker+0.051
ance+0.049
 runner+0.049
Neg logit contributions
 bowls-0.043
 frying-0.041
 boiling-0.041
 hyd-0.041
 erupt-0.040
Token
Token ID198
Feature activation-3.50e-01

Pos logit contributions
 bowls+0.018
 frying+0.017
 boiling+0.017
 erupt+0.017
 hyd+0.017
Neg logit contributions
oot-0.027
aces-0.027
emaker-0.025
 runner-0.024
ance-0.023
TokenThe
Token ID464
Feature activation+6.09e-01

Pos logit contributions
 bowls+0.013
 frying+0.012
 boiling+0.012
 erupt+0.012
 hyd+0.012
Neg logit contributions
oot-0.013
aces-0.012
emaker-0.011
 runner-0.011
ance-0.010
Token life
Token ID1204
Feature activation-3.42e-02

Pos logit contributions
oot+0.023
aces+0.022
emaker+0.020
 runner+0.020
ance+0.019
Neg logit contributions
 bowls-0.021
 frying-0.020
 boiling-0.020
 erupt-0.020
 hyd-0.020
Token knew
Token ID2993
Feature activation+6.29e-01

Pos logit contributions
 bowls+0.001
 hyd+0.001
 boiling+0.001
 erupt+0.001
 frying+0.001
Neg logit contributions
aces-0.001
oot-0.001
emaker-0.001
 runner-0.001
ance-0.001
Token it
Token ID340
Feature activation-4.63e-01

Pos logit contributions
aces+0.030
emaker+0.027
oot+0.027
 runner+0.026
orns+0.026
Neg logit contributions
 hyd-0.015
 erupt-0.015
 boiling-0.015
 y-0.015
 delicious-0.014
Token had
Token ID550
Feature activation+4.05e-01

Pos logit contributions
 bowls+0.014
 erupt+0.013
 frying+0.013
 boiling+0.013
 hyd+0.013
Neg logit contributions
oot-0.019
aces-0.019
emaker-0.017
 runner-0.017
ance-0.016
Token to
Token ID284
Feature activation-4.88e-02

Pos logit contributions
oot+0.016
aces+0.016
emaker+0.014
 runner+0.014
ance+0.013
Neg logit contributions
 bowls-0.013
 frying-0.013
 boiling-0.012
 hyd-0.012
 erupt-0.012
Token find
Token ID1064
Feature activation+9.86e-02

Pos logit contributions
 bowls+0.001
 erupt+0.001
 hyd+0.001
 boiling+0.001
 frying+0.001
Neg logit contributions
aces-0.002
oot-0.002
emaker-0.002
 runner-0.002
ance-0.002
Token
Token ID198
Feature activation-3.58e-01

Pos logit contributions
 bowls+0.004
 frying+0.004
 erupt+0.004
 hyd+0.004
 boiling+0.004
Neg logit contributions
oot-0.004
aces-0.004
emaker-0.004
 runner-0.004
ance-0.004
Token
Token ID198
Feature activation-1.98e-01

Pos logit contributions
 bowls+0.011
 frying+0.010
 hyd+0.010
 boiling+0.010
 erupt+0.010
Neg logit contributions
oot-0.015
aces-0.015
emaker-0.014
 runner-0.013
ance-0.013
TokenRoger
Token ID43719
Feature activation+1.84e-01

Pos logit contributions
 bowls+0.007
 frying+0.007
 boiling+0.007
 erupt+0.007
 hyd+0.007
Neg logit contributions
oot-0.007
aces-0.007
emaker-0.006
 runner-0.006
ance-0.006
Token was
Token ID373
Feature activation+4.44e-01

Pos logit contributions
oot+0.007
aces+0.007
emaker+0.006
ance+0.006
 runner+0.006
Neg logit contributions
 bowls-0.007
 boiling-0.006
 frying-0.006
 erupt-0.006
 burgers-0.006
Token so
Token ID523
Feature activation-8.30e-01

Pos logit contributions
aces+0.018
oot+0.018
 runner+0.016
py+0.015
 racer+0.015
Neg logit contributions
 bowls-0.014
ksh-0.013
 las-0.013
 apr-0.013
 hyd-0.013
Token happy
Token ID3772
Feature activation-7.96e-01

Pos logit contributions
ksh+0.029
 bowls+0.028
 apr+0.028
 stove+0.027
 grill+0.026
Neg logit contributions
oot-0.031
aces-0.030
 runner-0.028
iest-0.028
stretched-0.027
Token.
Token ID13
Feature activation+4.92e-02

Pos logit contributions
 bowls+0.028
 frying+0.027
 boiling+0.026
 erupt+0.026
 hyd+0.026
Neg logit contributions
oot-0.029
aces-0.029
emaker-0.026
 runner-0.025
ance-0.024
Token He
Token ID679
Feature activation+7.71e-01

Pos logit contributions
oot+0.002
aces+0.002
emaker+0.001
iest+0.001
 runner+0.001
Neg logit contributions
 bowls-0.002
 frying-0.002
 erupt-0.002
 grill-0.002
 boiling-0.002
Token gave
Token ID2921
Feature activation+7.18e-01

Pos logit contributions
oot+0.029
aces+0.029
emaker+0.026
 runner+0.025
ance+0.024
Neg logit contributions
 bowls-0.026
 frying-0.025
 boiling-0.025
 erupt-0.024
 hyd-0.024
Token the
Token ID262
Feature activation+1.41e-01

Pos logit contributions
oot+0.033
aces+0.033
emaker+0.030
 runner+0.030
 racer+0.029
Neg logit contributions
 bowls-0.018
 boiling-0.017
 hyd-0.017
 burgers-0.017
 frying-0.017
Token puppy
Token ID26188
Feature activation+2.31e-01

Pos logit contributions
oot+0.005
aces+0.005
emaker+0.005
 runner+0.005
ance+0.004
Neg logit contributions
 bowls-0.005
 frying-0.005
 erupt-0.005
 boiling-0.005
 hyd-0.005
Token and
Token ID290
Feature activation-2.42e-01

Pos logit contributions
 bowls+0.027
 hyd+0.026
 erupt+0.026
 clean+0.025
 cook+0.025
Neg logit contributions
aces-0.050
oot-0.047
emaker-0.046
ross-0.044
 runner-0.043
Token get
Token ID651
Feature activation-8.16e-01

Pos logit contributions
 bowls+0.007
 boiling+0.007
 frying+0.007
ksh+0.007
 hyd+0.007
Neg logit contributions
oot-0.010
aces-0.009
emaker-0.009
 runner-0.009
 racer-0.008
Token it
Token ID340
Feature activation+1.31e+00

Pos logit contributions
 bowls+0.030
 frying+0.029
 erupt+0.029
ksh+0.028
 boiling+0.028
Neg logit contributions
oot-0.028
aces-0.027
emaker-0.024
ance-0.024
 runner-0.023
Token back
Token ID736
Feature activation+1.71e-01

Pos logit contributions
oot+0.053
aces+0.052
emaker+0.049
 runner+0.047
ance+0.045
Neg logit contributions
 bowls-0.040
 erupt-0.038
 hyd-0.038
 frying-0.037
 boiling-0.037
Token."
Token ID526
Feature activation-4.27e-01

Pos logit contributions
aces+0.007
oot+0.007
emaker+0.006
 runner+0.006
mate+0.006
Neg logit contributions
 bowls-0.005
 hyd-0.005
 erupt-0.005
 frying-0.005
 boiling-0.005
Token
Token ID198
Feature activation-4.87e-01

Pos logit contributions
 bowls+0.012
 frying+0.011
 erupt+0.011
 boiling+0.011
 hyd+0.011
Neg logit contributions
oot-0.019
aces-0.019
emaker-0.017
 runner-0.016
ance-0.016
Token
Token ID198
Feature activation-2.56e-01

Pos logit contributions
 bowls+0.013
 boiling+0.012
 frying+0.012
 erupt+0.012
 hyd+0.012
Neg logit contributions
aces-0.022
oot-0.022
emaker-0.020
 runner-0.020
ance-0.019
TokenL
Token ID43
Feature activation-1.09e-01

Pos logit contributions
 bowls+0.008
 hyd+0.008
 frying+0.008
 boiling+0.008
 erupt+0.008
Neg logit contributions
aces-0.010
oot-0.010
emaker-0.009
ance-0.009
 runner-0.008
Tokenily
Token ID813
Feature activation-3.93e-02

Pos logit contributions
 bowls+0.004
 pasta+0.004
 las+0.004
 boiling+0.004
 stir+0.004
Neg logit contributions
oot-0.003
aces-0.003
 runner-0.003
 racer-0.003
stretched-0.003
Token and
Token ID290
Feature activation-4.71e-02

Pos logit contributions
 bowls+0.001
 boiling+0.001
 erupt+0.001
 frying+0.001
 hyd+0.001
Neg logit contributions
aces-0.001
oot-0.001
ance-0.001
emaker-0.001
 runner-0.001
Token her
Token ID607
Feature activation+1.78e+00

Pos logit contributions
 bowls+0.001
 frying+0.001
 boiling+0.001
 erupt+0.001
 hyd+0.001
Neg logit contributions
oot-0.002
aces-0.002
emaker-0.002
iest-0.002
 runner-0.002
Token reach
Token ID3151
Feature activation-1.48e+00

Pos logit contributions
 bowls+0.027
 frying+0.025
 hyd+0.025
 boiling+0.025
ksh+0.025
Neg logit contributions
oot-0.039
aces-0.038
emaker-0.035
 runner-0.034
ance-0.033
Token the
Token ID262
Feature activation-5.12e-01

Pos logit contributions
 bowls+0.045
 frying+0.043
 hyd+0.043
 erupt+0.042
 boiling+0.042
Neg logit contributions
oot-0.060
aces-0.060
emaker-0.054
 runner-0.052
ance-0.051
Token top
Token ID1353
Feature activation-8.20e-01

Pos logit contributions
 bowls+0.020
 frying+0.019
 hyd+0.019
 boiling+0.019
 erupt+0.019
Neg logit contributions
aces-0.017
oot-0.017
emaker-0.015
 runner-0.014
ance-0.014
Token of
Token ID286
Feature activation-1.19e+00

Pos logit contributions
 bowls+0.029
 erupt+0.028
 frying+0.028
 boiling+0.027
 hyd+0.027
Neg logit contributions
oot-0.030
aces-0.029
emaker-0.026
 runner-0.025
ance-0.025
Token the
Token ID262
Feature activation-1.38e-01

Pos logit contributions
 bowls+0.037
 frying+0.036
ksh+0.036
 hyd+0.036
 erupt+0.035
Neg logit contributions
aces-0.046
oot-0.046
emaker-0.042
 runner-0.041
ance-0.040
Token wall
Token ID3355
Feature activation-3.14e+00

Pos logit contributions
 bowls+0.005
 hyd+0.005
 frying+0.005
 boiling+0.005
ksh+0.005
Neg logit contributions
aces-0.005
oot-0.005
emaker-0.004
 runner-0.004
iest-0.004
Token to
Token ID284
Feature activation-1.50e+00

Pos logit contributions
 bowls+0.112
 frying+0.106
 erupt+0.106
 boiling+0.106
 hyd+0.105
Neg logit contributions
oot-0.113
aces-0.111
emaker-0.101
 runner-0.097
ance-0.094
Token paint
Token ID7521
Feature activation-4.63e-01

Pos logit contributions
 bowls+0.040
 frying+0.038
ksh+0.037
 hyd+0.037
 boiling+0.037
Neg logit contributions
oot-0.067
aces-0.066
emaker-0.061
 runner-0.059
ance-0.058
Token?"
Token ID1701
Feature activation+7.78e-02

Pos logit contributions
 bowls+0.016
 frying+0.015
 erupt+0.015
 boiling+0.015
 hyd+0.015
Neg logit contributions
oot-0.017
aces-0.017
emaker-0.015
 runner-0.015
ance-0.014
Token Tim
Token ID5045
Feature activation-8.60e-01

Pos logit contributions
oot+0.003
aces+0.003
emaker+0.003
 runner+0.003
ance+0.002
Neg logit contributions
 bowls-0.003
 frying-0.003
 boiling-0.002
 hyd-0.002
 erupt-0.002
Token asked
Token ID1965
Feature activation+1.62e-01

Pos logit contributions
 bowls+0.026
 boiling+0.025
 frying+0.025
 hyd+0.024
 burgers+0.024
Neg logit contributions
oot-0.037
aces-0.036
emaker-0.033
py-0.031
 runner-0.031
Token a
Token ID257
Feature activation-4.93e-01

Pos logit contributions
 erupt+0.062
 bowls+0.062
ksh+0.062
 frying+0.061
 hyd+0.061
Neg logit contributions
aces-0.068
oot-0.066
ance-0.061
 runner-0.058
iest-0.057
Token big
Token ID1263
Feature activation-1.42e+00

Pos logit contributions
ksh+0.018
 bowls+0.017
 hyd+0.016
 apr+0.016
 erupt+0.015
Neg logit contributions
 racer-0.017
 runner-0.017
oot-0.015
iest-0.014
br-0.014
Token cake
Token ID12187
Feature activation-3.22e-01

Pos logit contributions
ksh+0.048
 hyd+0.043
 bowls+0.043
 erupt+0.042
 frying+0.042
Neg logit contributions
 runner-0.049
oot-0.049
 racer-0.048
ebra-0.046
aces-0.046
Token on
Token ID319
Feature activation+2.01e+00

Pos logit contributions
 bowls+0.013
ksh+0.013
 frying+0.013
 erupt+0.013
 hyd+0.012
Neg logit contributions
oot-0.009
aces-0.009
emaker-0.008
 runner-0.008
iest-0.008
Token the
Token ID262
Feature activation+7.85e-01

Pos logit contributions
oot+0.061
aces+0.060
 runner+0.055
emaker+0.055
mate+0.054
Neg logit contributions
 frying-0.073
ksh-0.073
 hyd-0.070
 bowls-0.070
 erupt-0.070
Token table
Token ID3084
Feature activation-3.69e+00

Pos logit contributions
aces+0.031
oot+0.029
 runner+0.028
 racer+0.028
iest+0.028
Neg logit contributions
ksh-0.021
 erupt-0.020
 empt-0.020
 hyd-0.019
 bowls-0.019
Token.
Token ID13
Feature activation+2.60e-01

Pos logit contributions
 bowls+0.122
 frying+0.117
 erupt+0.115
 boiling+0.115
 hyd+0.115
Neg logit contributions
aces-0.140
oot-0.140
emaker-0.125
 runner-0.121
ance-0.119
Token It
Token ID632
Feature activation+4.86e-01

Pos logit contributions
aces+0.008
oot+0.007
 runner+0.006
ance+0.006
emaker+0.006
Neg logit contributions
 erupt-0.011
 hyd-0.010
 bowls-0.010
 frying-0.010
 boiling-0.010
Token is
Token ID318
Feature activation-1.91e+00

Pos logit contributions
aces+0.013
oot+0.011
br+0.011
py+0.010
elle+0.010
Neg logit contributions
 hyd-0.020
 bowls-0.019
ksh-0.019
 frying-0.019
 burgers-0.019
Token purple
Token ID14032
Feature activation+1.36e+00

Pos logit contributions
ksh+0.065
 hyd+0.063
 bowls+0.063
 erupt+0.061
 reel+0.060
Neg logit contributions
aces-0.065
oot-0.059
 runner-0.053
 racer-0.052
iest-0.051
Token too
Token ID1165
Feature activation+9.63e-01

Pos logit contributions
oot+0.053
aces+0.052
emaker+0.048
 runner+0.046
ance+0.045
Neg logit contributions
 bowls-0.045
 frying-0.043
 boiling-0.042
 hyd-0.042
 erupt-0.042
Token something
Token ID1223
Feature activation-1.10e+00

Pos logit contributions
aces+0.023
oot+0.023
emaker+0.020
 runner+0.020
ance+0.020
Neg logit contributions
 bowls-0.015
 frying-0.014
 boiling-0.014
 hyd-0.014
 erupt-0.014
Token special
Token ID2041
Feature activation+3.58e-01

Pos logit contributions
 bowls+0.037
 frying+0.035
ksh+0.035
 boiling+0.034
 erupt+0.033
Neg logit contributions
oot-0.042
aces-0.041
iest-0.037
 runner-0.036
emaker-0.036
Token to
Token ID284
Feature activation-1.60e-01

Pos logit contributions
oot+0.015
aces+0.014
emaker+0.014
 runner+0.013
Tweet+0.013
Neg logit contributions
 bowls-0.011
 hyd-0.010
 erupt-0.010
 boiling-0.010
 grill-0.010
Token offer
Token ID2897
Feature activation+3.94e-02

Pos logit contributions
 bowls+0.005
 frying+0.004
 boiling+0.004
 hyd+0.004
 erupt+0.004
Neg logit contributions
oot-0.007
aces-0.007
emaker-0.006
 runner-0.006
ance-0.006
Token,
Token ID11
Feature activation+8.75e-01

Pos logit contributions
oot+0.001
aces+0.001
emaker+0.001
 runner+0.001
ance+0.001
Neg logit contributions
 bowls-0.001
 hyd-0.001
 frying-0.001
 boiling-0.001
 erupt-0.001
Token like
Token ID588
Feature activation-3.45e+00

Pos logit contributions
oot+0.034
aces+0.034
emaker+0.031
 runner+0.030
ance+0.029
Neg logit contributions
 bowls-0.028
 erupt-0.027
 hyd-0.027
 boiling-0.027
 frying-0.027
Token Billy
Token ID15890
Feature activation+6.72e-01

Pos logit contributions
 bowls+0.096
 burgers+0.092
 y+0.092
 erupt+0.091
 grill+0.090
Neg logit contributions
aces-0.148
oot-0.147
emaker-0.139
 runner-0.129
ross-0.127
Token's
Token ID338
Feature activation-1.14e+00

Pos logit contributions
oot+0.027
aces+0.027
emaker+0.024
 runner+0.023
ance+0.023
Neg logit contributions
 bowls-0.021
 frying-0.020
 boiling-0.020
 erupt-0.020
 hyd-0.020
Token powerful
Token ID3665
Feature activation-6.27e-02

Pos logit contributions
 bowls+0.038
 erupt+0.036
 frying+0.035
 hyd+0.035
 boiling+0.035
Neg logit contributions
oot-0.044
aces-0.043
emaker-0.039
 runner-0.037
ance-0.037
Token shots
Token ID6934
Feature activation+1.65e+00

Pos logit contributions
 bowls+0.002
 grill+0.002
 sink+0.002
 dish+0.002
 bowl+0.002
Neg logit contributions
oot-0.003
aces-0.002
Tweet-0.002
emaker-0.002
py-0.002
Token in
Token ID287
Feature activation+3.49e-01

Pos logit contributions
oot+0.066
aces+0.064
emaker+0.059
 runner+0.057
ance+0.055
Neg logit contributions
 bowls-0.051
 erupt-0.048
 hyd-0.048
 boiling-0.048
 frying-0.047
Token bottle
Token ID9294
Feature activation+7.29e-01

Pos logit contributions
ksh+0.042
rig+0.038
 erupt+0.034
 hyd+0.034
 frying+0.031
Neg logit contributions
 runner-0.058
aces-0.057
oot-0.057
 racer-0.056
emaker-0.055
Token of
Token ID286
Feature activation+8.35e-01

Pos logit contributions
oot+0.015
aces+0.014
emaker+0.012
 runner+0.011
iest+0.011
Neg logit contributions
 bowls-0.037
 erupt-0.036
 frying-0.036
ksh-0.036
 hyd-0.036
Token wine
Token ID8237
Feature activation-1.04e+00

Pos logit contributions
aces+0.038
oot+0.037
emaker+0.034
iest+0.034
 runner+0.033
Neg logit contributions
 erupt-0.020
 bowls-0.019
ksh-0.019
 hyd-0.019
 frying-0.019
Token on
Token ID319
Feature activation+1.94e+00

Pos logit contributions
ksh+0.048
 bowls+0.047
 erupt+0.046
 hyd+0.046
 frying+0.045
Neg logit contributions
aces-0.025
oot-0.023
iest-0.020
 runner-0.019
emaker-0.019
Token the
Token ID262
Feature activation+4.04e-01

Pos logit contributions
aces+0.062
oot+0.060
emaker+0.056
mate+0.055
 runner+0.053
Neg logit contributions
ksh-0.069
 frying-0.067
 hyd-0.066
 erupt-0.065
 bowls-0.065
Token table
Token ID3084
Feature activation-3.83e+00

Pos logit contributions
aces+0.017
oot+0.016
 runner+0.015
mate+0.015
iest+0.015
Neg logit contributions
ksh-0.010
 erupt-0.010
rig-0.009
 empt-0.009
 bowls-0.009
Token.
Token ID13
Feature activation-2.73e-01

Pos logit contributions
 bowls+0.130
 frying+0.126
 erupt+0.125
ksh+0.125
 hyd+0.124
Neg logit contributions
aces-0.141
oot-0.138
emaker-0.123
 runner-0.119
iest-0.117
Token They
Token ID1119
Feature activation-2.05e-01

Pos logit contributions
 erupt+0.011
 bowls+0.011
 frying+0.011
 hyd+0.011
 boiling+0.011
Neg logit contributions
aces-0.008
oot-0.007
 runner-0.006
 Kit-0.006
emaker-0.006
Token did
Token ID750
Feature activation+1.51e+00

Pos logit contributions
ksh+0.007
 hyd+0.007
 erupt+0.007
rig+0.006
 las+0.006
Neg logit contributions
aces-0.007
oot-0.007
emaker-0.006
 runner-0.006
stretched-0.006
Token not
Token ID407
Feature activation+1.38e+00

Pos logit contributions
aces+0.040
oot+0.038
ves+0.031
mate+0.029
 runner+0.028
Neg logit contributions
ksh-0.068
 frying-0.063
 bowls-0.063
 hyd-0.062
 Son-0.060
Token know
Token ID760
Feature activation-3.11e-02

Pos logit contributions
aces+0.050
oot+0.049
emaker+0.045
 runner+0.044
 racer+0.042
Neg logit contributions
ksh-0.048
 bowls-0.047
 boiling-0.047
 frying-0.046
 hyd-0.046
Token letting
Token ID9616
Feature activation-2.36e-01

Pos logit contributions
 bowls+0.013
 boiling+0.012
 erupt+0.012
 hyd+0.012
 frying+0.012
Neg logit contributions
aces-0.015
oot-0.015
emaker-0.013
 runner-0.013
iest-0.013
Token him
Token ID683
Feature activation-1.35e+00

Pos logit contributions
 bowls+0.006
 erupt+0.006
 clean+0.006
 un+0.006
 hyd+0.006
Neg logit contributions
aces-0.011
oot-0.010
emaker-0.009
iest-0.009
 runner-0.009
Token play
Token ID711
Feature activation+7.99e-01

Pos logit contributions
 bowls+0.035
 frying+0.033
 erupt+0.033
 hyd+0.033
 boiling+0.032
Neg logit contributions
oot-0.061
aces-0.061
emaker-0.056
 runner-0.054
ance-0.053
Token with
Token ID351
Feature activation-8.17e-01

Pos logit contributions
aces+0.035
oot+0.035
emaker+0.034
ross+0.032
ance+0.031
Neg logit contributions
 bowls-0.020
 hyd-0.020
 clean-0.020
 erupt-0.020
 y-0.020
Token the
Token ID262
Feature activation+6.93e-01

Pos logit contributions
 bowls+0.022
 clean+0.020
 pasta+0.020
 boiling+0.020
 y+0.020
Neg logit contributions
oot-0.038
aces-0.038
 runner-0.034
ance-0.034
iest-0.034
Token amazing
Token ID4998
Feature activation-3.40e+00

Pos logit contributions
oot+0.026
aces+0.026
emaker+0.023
 runner+0.023
ance+0.022
Neg logit contributions
 bowls-0.023
 frying-0.022
 boiling-0.022
 erupt-0.022
 hyd-0.022
Token je
Token ID11223
Feature activation+1.30e+00

Pos logit contributions
 bowls+0.096
 erupt+0.092
 hyd+0.090
 dish+0.087
 y+0.087
Neg logit contributions
aces-0.147
oot-0.143
emaker-0.134
ross-0.129
ance-0.128
Tokenep
Token ID538
Feature activation-1.55e-01

Pos logit contributions
aces+0.057
oot+0.056
emaker+0.052
 runner+0.051
ance+0.051
Neg logit contributions
 bowls-0.033
 hyd-0.032
 erupt-0.032
 frying-0.030
 boiling-0.030
Token.
Token ID13
Feature activation+2.90e-03

Pos logit contributions
 erupt+0.003
 hyd+0.003
 bowls+0.003
 clean+0.003
 cook+0.003
Neg logit contributions
oot-0.007
aces-0.007
emaker-0.007
 runner-0.007
ross-0.006
Token Lily
Token ID20037
Feature activation+1.12e-01

Pos logit contributions
oot+0.000
aces+0.000
iest+0.000
emaker+0.000
 runner+0.000
Neg logit contributions
 bowls-0.000
 Dad-0.000
 clean-0.000
ksh-0.000
 y-0.000
Token smiled
Token ID13541
Feature activation+7.72e-01

Pos logit contributions
oot+0.004
aces+0.004
emaker+0.004
 runner+0.004
ance+0.004
Neg logit contributions
 bowls-0.004
 frying-0.004
 boiling-0.004
 erupt-0.004
 hyd-0.004