TOP ACTIVATIONS
MAX = 10.060

big , round cookie with spec ks of sugar on the
high they were just tiny spec ks in the sky .
the leaf there were little spec ks of gold ! She
spoon . He puts some flour , some sugar , some
is cheaper than sugar and flour . We are not very
sorry . They heard mom coming back and ran to hide
dish . Tom puts some flour and water in another bowl
with a messy pile of flour and sugar . " Do
They measured the flour , the sugar , and
They did not hear Mom coming home . They did not
and Mia hear their mom coming . They know she will
tells Sara to mix the flour , the eggs and the
. They saw their dad coming home from work . He
oons , cups and some flour . " Let
They heard their mom coming . She saw the mess
a big mess with the flour . She laughs and says
irens and saw red trucks coming . The trucks had big
. Now the stuffing is coming out . And you have
pieces . They heard mom coming and tried to hide under
. They see a giant coming to the hill . He

MIN ACTIVATIONS
MIN = -10.048

lovely little dog called Zig zag . Zig zag was a
played hide - and - seek . After a while the
play hide - and - seek behind them . Suddenly ,
play hide - and - seek with her friends . One
and hide - and - seek . Mia was so happy
played hide - and - seek and had a grand time
like hide - and - seek and tag . One day
of hide - and - seek , so she decided to
, hide - and - seek , and even a game
playing hide - and - seek . Sammy was hiding behind
play hide - and - seek with her friends . One
played hide - and - seek , tag , and other
finally , the z ig zag had an idea . It
would splash and z ig zag in the water together .
playing hide - and - seek . Tim my was hiding
ement as the z ig zag soared in the sky .
playing hide - and - seek with her friends . <|endoftext|>
playing hide - and - seek behind the old barn .
and hide - and - seek . The monkey was very
He had to z ig zag around and make big circles

INTERVAL 5.033 - 10.060
CONTAINS 0.404%

porch . They both reached out to touch them , feeling
to prevent things from getting out of hand . Every day
for this . It 's called a net ." He takes
. They got out the pots and pans , and started
her test . She hugged Mr . Fox and said ,

INTERVAL 0.006 - 5.033
CONTAINS 49.869%

slide . It will make you happy ." Ben
when her little brother came in . "
found the biggest , brightest rad ish and he hopped back
Today we 're going on a picnic !" Maria was very
" Maybe we should have played with Frost y

INTERVAL -5.021 - 0.006
CONTAINS 49.083%

delicious , but because the monster wasn 't scary after all
little boy . He was three years old and had lots
had an idea . R emy went to the
brave Princess for protecting the castle and saving the day .
special as the butter he found when he climbed the wall

INTERVAL -10.048 - -5.021
CONTAINS 0.644%

. He wanted it so badly ! "
wanted to play hide and seek with the sun . The
something so hard ! <|endoftext|> One day , a little boy
he wanted to try to win . He kept trying and
the bridge shakes . Sara loses her balance and drops the
Token big
Token ID1263
Feature activation+2.27e+00

Pos logit contributions
 counters+0.016
nam+0.015
 forward+0.015
 pans+0.015
 spec+0.015
Neg logit contributions
zag-0.025
gy-0.021
 sometime-0.021
 seek-0.021
 now-0.020
Token,
Token ID11
Feature activation-6.26e-01

Pos logit contributions
nam+0.113
 pans+0.113
 ding+0.113
 counters+0.110
 forward+0.108
Neg logit contributions
zag-0.124
oot-0.116
uzz-0.112
seek-0.109
 sometime-0.105
Token round
Token ID2835
Feature activation+1.30e+00

Pos logit contributions
zag+0.031
 seek+0.030
 now+0.030
gy+0.028
 sometime+0.028
Neg logit contributions
 forward-0.026
 spec-0.026
pared-0.026
cient-0.025
 counters-0.024
Token cookie
Token ID19751
Feature activation-2.06e+00

Pos logit contributions
 ding+0.060
 pans+0.059
 counters+0.058
nam+0.058
 y+0.057
Neg logit contributions
zag-0.075
oot-0.072
uzz-0.070
seek-0.069
 sometime-0.065
Token with
Token ID351
Feature activation-4.10e-02

Pos logit contributions
zag+0.107
oot+0.100
uzz+0.096
seek+0.093
 sometime+0.090
Neg logit contributions
nam-0.108
 pans-0.108
 ding-0.107
 counters-0.105
 forward-0.103
Token spec
Token ID1020
Feature activation+1.01e+01

Pos logit contributions
uzz+0.002
zag+0.002
ad+0.002
oot+0.002
seek+0.002
Neg logit contributions
 forward-0.002
 counters-0.002
 stressed-0.002
 pans-0.002
sc-0.002
Tokenks
Token ID591
Feature activation-3.81e-01

Pos logit contributions
nam+0.466
 forward+0.462
 ding+0.459
 pans+0.450
 spec+0.440
Neg logit contributions
zag-0.575
oot-0.519
seek-0.509
 sometime-0.489
gy-0.483
Token of
Token ID286
Feature activation+3.20e+00

Pos logit contributions
zag+0.019
oot+0.018
uzz+0.018
seek+0.017
gy+0.016
Neg logit contributions
nam-0.021
 pans-0.020
 counters-0.019
 ding-0.019
 spec-0.019
Token sugar
Token ID7543
Feature activation+3.81e+00

Pos logit contributions
 forward+0.148
sc+0.145
 counters+0.139
nam+0.138
 ding+0.138
Neg logit contributions
zag-0.166
uzz-0.162
oot-0.160
seek-0.153
 sometime-0.151
Token on
Token ID319
Feature activation-4.39e-01

Pos logit contributions
nam+0.211
 ding+0.208
 pans+0.206
 counters+0.201
 forward+0.200
Neg logit contributions
zag-0.191
oot-0.175
uzz-0.164
seek-0.163
gy-0.159
Token the
Token ID262
Feature activation+3.42e-01

Pos logit contributions
zag+0.023
oot+0.021
uzz+0.020
seek+0.019
gy+0.019
Neg logit contributions
nam-0.023
 pans-0.023
 ding-0.023
 counters-0.022
 forward-0.022
Token high
Token ID1029
Feature activation+1.41e+00

Pos logit contributions
 counters+0.023
nam+0.022
sc+0.022
 pans+0.021
 forward+0.021
Neg logit contributions
zag-0.046
uzz-0.044
oot-0.044
 sometime-0.041
seek-0.040
Token they
Token ID484
Feature activation+1.07e+00

Pos logit contributions
 ding+0.066
 pans+0.065
 forward+0.063
 counters+0.063
nam+0.063
Neg logit contributions
zag-0.081
oot-0.076
uzz-0.076
seek-0.072
 sometime-0.069
Token were
Token ID547
Feature activation+1.27e+00

Pos logit contributions
 counters+0.046
 pans+0.046
 ding+0.044
nam+0.044
 forward+0.041
Neg logit contributions
zag-0.066
oot-0.062
uzz-0.060
gy-0.057
seek-0.057
Token just
Token ID655
Feature activation-7.43e-01

Pos logit contributions
nam+0.055
 pans+0.055
 ding+0.055
 counters+0.053
 forward+0.052
Neg logit contributions
zag-0.078
oot-0.073
uzz-0.071
seek-0.070
 sometime-0.067
Token tiny
Token ID7009
Feature activation+2.19e+00

Pos logit contributions
zag+0.038
uzz+0.036
oot+0.036
 sometime+0.033
gy+0.033
Neg logit contributions
 pans-0.038
 counters-0.038
nam-0.037
sc-0.036
 ding-0.036
Token spec
Token ID1020
Feature activation+9.88e+00

Pos logit contributions
nam+0.121
 ding+0.120
 pans+0.120
 counters+0.118
 forward+0.115
Neg logit contributions
zag-0.107
oot-0.099
uzz-0.095
seek-0.093
 sometime-0.089
Tokenks
Token ID591
Feature activation-4.49e-01

Pos logit contributions
nam+0.482
 ding+0.481
 pans+0.478
 forward+0.473
 counters+0.464
Neg logit contributions
zag-0.542
oot-0.503
seek-0.482
uzz-0.466
 sometime-0.461
Token in
Token ID287
Feature activation+6.65e-01

Pos logit contributions
zag+0.021
oot+0.020
uzz+0.019
seek+0.018
 sometime+0.017
Neg logit contributions
nam-0.027
 pans-0.026
 counters-0.025
 ding-0.025
 ju-0.024
Token the
Token ID262
Feature activation+2.69e-01

Pos logit contributions
nam+0.031
 pans+0.031
 ding+0.030
 counters+0.030
 forward+0.029
Neg logit contributions
zag-0.039
oot-0.037
uzz-0.036
seek-0.035
 sometime-0.033
Token sky
Token ID6766
Feature activation+1.62e+00

Pos logit contributions
nam+0.013
 stressed+0.011
 pans+0.011
ults+0.011
 counters+0.011
Neg logit contributions
zag-0.014
istle-0.012
gy-0.012
seek-0.012
ad-0.012
Token.
Token ID13
Feature activation-3.70e-01

Pos logit contributions
nam+0.095
 pans+0.093
 counters+0.091
 ding+0.091
 forward+0.087
Neg logit contributions
zag-0.078
oot-0.070
uzz-0.067
seek-0.065
gy-0.064
Token the
Token ID262
Feature activation+1.48e-01

Pos logit contributions
zag+0.031
oot+0.029
uzz+0.028
seek+0.027
 sometime+0.027
Neg logit contributions
nam-0.031
 pans-0.030
 ding-0.030
 counters-0.030
 forward-0.028
Token leaf
Token ID12835
Feature activation-8.35e-01

Pos logit contributions
nam+0.007
 pans+0.007
 ding+0.007
 counters+0.007
 forward+0.006
Neg logit contributions
zag-0.009
oot-0.008
uzz-0.008
seek-0.008
 sometime-0.008
Token there
Token ID612
Feature activation-6.93e-02

Pos logit contributions
zag+0.043
oot+0.041
uzz+0.039
seek+0.038
 sometime+0.036
Neg logit contributions
 pans-0.043
nam-0.043
 ding-0.043
 counters-0.042
 forward-0.041
Token were
Token ID547
Feature activation+1.10e+00

Pos logit contributions
zag+0.004
oot+0.004
uzz+0.004
seek+0.004
 sometime+0.004
Neg logit contributions
 pans-0.003
nam-0.003
 ding-0.003
 counters-0.003
 forward-0.003
Token little
Token ID1310
Feature activation+3.16e+00

Pos logit contributions
 pans+0.047
nam+0.047
 ding+0.047
 counters+0.046
 forward+0.046
Neg logit contributions
zag-0.066
oot-0.062
uzz-0.061
seek-0.059
 sometime-0.058
Token spec
Token ID1020
Feature activation+9.73e+00

Pos logit contributions
nam+0.146
 ding+0.145
 pans+0.144
 forward+0.142
 counters+0.141
Neg logit contributions
zag-0.177
oot-0.168
uzz-0.163
seek-0.158
 sometime-0.155
Tokenks
Token ID591
Feature activation-5.77e-01

Pos logit contributions
nam+0.465
 forward+0.455
 ding+0.454
 pans+0.445
 spec+0.444
Neg logit contributions
zag-0.545
oot-0.501
seek-0.480
 sometime-0.460
gy-0.452
Token of
Token ID286
Feature activation+3.02e+00

Pos logit contributions
zag+0.030
oot+0.028
uzz+0.027
seek+0.026
 sometime+0.025
Neg logit contributions
nam-0.031
 pans-0.030
 ding-0.029
 counters-0.029
 ju-0.028
Token gold
Token ID3869
Feature activation+4.01e-01

Pos logit contributions
 pans+0.129
nam+0.129
 ding+0.128
 counters+0.125
 forward+0.123
Neg logit contributions
zag-0.183
oot-0.174
uzz-0.171
seek-0.164
 sometime-0.160
Token!
Token ID0
Feature activation-1.38e+00

Pos logit contributions
nam+0.022
 pans+0.022
 ding+0.022
 counters+0.021
 forward+0.021
Neg logit contributions
zag-0.020
oot-0.019
uzz-0.018
seek-0.017
 sometime-0.017
Token She
Token ID1375
Feature activation-3.18e-01

Pos logit contributions
uzz+0.061
zag+0.060
seek+0.056
oot+0.056
 sometime+0.053
Neg logit contributions
 pans-0.083
 ding-0.079
nam-0.078
 forward-0.076
 brightest-0.074
Token spoon
Token ID24556
Feature activation+2.15e+00

Pos logit contributions
nam+0.119
 pans+0.113
 forward+0.112
 ding+0.112
 counters+0.112
Neg logit contributions
zag-0.174
oot-0.160
uzz-0.159
gy-0.152
 sometime-0.151
Token.
Token ID13
Feature activation+3.12e-01

Pos logit contributions
 pans+0.096
 ding+0.096
 forward+0.093
 counters+0.093
 y+0.091
Neg logit contributions
zag-0.124
oot-0.117
seek-0.114
uzz-0.111
 sometime-0.111
Token He
Token ID679
Feature activation-2.83e-02

Pos logit contributions
nam+0.016
 pans+0.016
 ding+0.015
 counters+0.015
 forward+0.015
Neg logit contributions
zag-0.017
oot-0.016
uzz-0.016
seek-0.015
 sometime-0.015
Token puts
Token ID7584
Feature activation-6.18e-01

Pos logit contributions
zag+0.002
oot+0.002
uzz+0.002
seek+0.002
 sometime+0.002
Neg logit contributions
 pans-0.001
nam-0.001
 ding-0.001
 counters-0.001
 forward-0.001
Token some
Token ID617
Feature activation-1.70e+00

Pos logit contributions
zag+0.025
uzz+0.024
gy+0.022
oot+0.022
 sometime+0.022
Neg logit contributions
 counters-0.035
nam-0.035
 ding-0.035
 spec-0.034
 stressed-0.034
Token flour
Token ID10601
Feature activation+8.43e+00

Pos logit contributions
zag+0.081
uzz+0.078
 sometime+0.075
oot+0.074
 now+0.072
Neg logit contributions
nam-0.083
 ding-0.079
pared-0.076
 forward-0.076
 stressed-0.074
Token,
Token ID11
Feature activation+1.68e-01

Pos logit contributions
nam+0.479
 ding+0.461
 pans+0.458
 counters+0.457
 spec+0.440
Neg logit contributions
zag-0.410
oot-0.377
uzz-0.367
gy-0.348
seek-0.339
Token some
Token ID617
Feature activation-1.71e+00

Pos logit contributions
 forward+0.007
nam+0.007
 ding+0.007
 spec+0.007
sc+0.007
Neg logit contributions
zag-0.009
 sometime-0.009
oot-0.008
uzz-0.008
gy-0.008
Token sugar
Token ID7543
Feature activation+4.30e+00

Pos logit contributions
zag+0.085
 sometime+0.084
uzz+0.080
 now+0.079
oot+0.078
Neg logit contributions
nam-0.081
 ding-0.074
 forward-0.074
pared-0.069
 stressed-0.068
Token,
Token ID11
Feature activation+1.97e-01

Pos logit contributions
nam+0.236
 pans+0.235
 ding+0.234
 counters+0.230
 forward+0.225
Neg logit contributions
zag-0.213
oot-0.198
uzz-0.191
seek-0.185
 sometime-0.177
Token some
Token ID617
Feature activation-1.71e+00

Pos logit contributions
nam+0.012
 forward+0.012
 ding+0.012
 counters+0.011
 spec+0.011
Neg logit contributions
zag-0.008
 sometime-0.007
uzz-0.007
oot-0.007
gy-0.007
Token is
Token ID318
Feature activation+7.33e-01

Pos logit contributions
 pans+0.012
 ding+0.012
nam+0.012
 counters+0.012
 forward+0.012
Neg logit contributions
zag-0.017
oot-0.016
uzz-0.015
seek-0.015
gy-0.015
Token cheaper
Token ID11721
Feature activation-1.66e+00

Pos logit contributions
 counters+0.035
 pans+0.034
nam+0.033
 ding+0.033
 forward+0.032
Neg logit contributions
zag-0.041
uzz-0.038
oot-0.037
 sometime-0.036
seek-0.035
Token than
Token ID621
Feature activation+8.53e-01

Pos logit contributions
zag+0.095
oot+0.089
uzz+0.085
seek+0.085
ogo+0.079
Neg logit contributions
 pans-0.079
nam-0.079
 ding-0.076
 forward-0.076
 counters-0.076
Token sugar
Token ID7543
Feature activation+4.31e+00

Pos logit contributions
 pans+0.045
 ding+0.045
 counters+0.045
nam+0.044
 forward+0.043
Neg logit contributions
zag-0.042
oot-0.040
uzz-0.039
seek-0.037
 sometime-0.037
Token and
Token ID290
Feature activation+4.86e-01

Pos logit contributions
nam+0.235
 pans+0.233
 ding+0.233
 counters+0.228
 forward+0.222
Neg logit contributions
zag-0.216
oot-0.199
uzz-0.191
seek-0.186
 sometime-0.181
Token flour
Token ID10601
Feature activation+8.42e+00

Pos logit contributions
 forward+0.021
 ding+0.020
 counters+0.020
nam+0.020
 pans+0.019
Neg logit contributions
zag-0.028
oot-0.026
 sometime-0.026
uzz-0.026
seek-0.025
Token.
Token ID13
Feature activation+2.89e-01

Pos logit contributions
nam+0.476
 pans+0.464
 ding+0.461
 counters+0.457
 forward+0.439
Neg logit contributions
zag-0.407
oot-0.376
uzz-0.361
seek-0.344
 sometime-0.341
Token We
Token ID775
Feature activation+3.00e+00

Pos logit contributions
 pans+0.013
nam+0.013
 ding+0.013
 counters+0.013
 forward+0.012
Neg logit contributions
zag-0.017
uzz-0.016
oot-0.016
 sometime-0.015
seek-0.015
Token are
Token ID389
Feature activation+1.33e+00

Pos logit contributions
nam+0.126
 ding+0.125
 pans+0.124
 forward+0.121
 y+0.120
Neg logit contributions
zag-0.190
oot-0.179
seek-0.172
uzz-0.171
ippy-0.161
Token not
Token ID407
Feature activation-1.68e+00

Pos logit contributions
sc+0.056
 spec+0.054
 counters+0.053
 pans+0.053
 ding+0.050
Neg logit contributions
zag-0.076
uzz-0.076
 sometime-0.073
oot-0.072
 now-0.070
Token very
Token ID845
Feature activation+1.63e+00

Pos logit contributions
zag+0.094
oot+0.092
uzz+0.091
 sometime+0.087
gy+0.084
Neg logit contributions
 counters-0.073
sc-0.073
 spec-0.072
 ding-0.071
 pans-0.071
Token sorry
Token ID7926
Feature activation+3.69e+00

Pos logit contributions
 brightest+0.034
 ju+0.034
sc+0.032
 pans+0.031
 counters+0.031
Neg logit contributions
 now-0.027
uzz-0.027
oot-0.027
zag-0.025
 drowned-0.024
Token.
Token ID13
Feature activation+6.92e-01

Pos logit contributions
 ding+0.168
 forward+0.163
 pans+0.163
 y+0.161
 counters+0.157
Neg logit contributions
zag-0.226
oot-0.207
seek-0.204
uzz-0.200
gy-0.194
Token They
Token ID1119
Feature activation+6.32e-01

Pos logit contributions
nam+0.029
 pans+0.029
 ding+0.029
 counters+0.028
 forward+0.028
Neg logit contributions
zag-0.044
oot-0.041
uzz-0.040
seek-0.039
 sometime-0.038
Token heard
Token ID2982
Feature activation+1.55e+00

Pos logit contributions
 pans+0.032
 ding+0.031
nam+0.030
 counters+0.030
 forward+0.030
Neg logit contributions
zag-0.033
oot-0.032
uzz-0.031
seek-0.029
gy-0.029
Token mom
Token ID1995
Feature activation+2.23e+00

Pos logit contributions
 ding+0.068
nam+0.066
 pans+0.065
 counters+0.064
 y+0.063
Neg logit contributions
zag-0.099
oot-0.092
seek-0.089
uzz-0.088
 sometime-0.085
Token coming
Token ID2406
Feature activation+8.40e+00

Pos logit contributions
nam+0.129
 ju+0.124
 brightest+0.119
 redd+0.115
 pans+0.110
Neg logit contributions
zag-0.112
oot-0.106
gy-0.105
uzz-0.099
ad-0.099
Token back
Token ID736
Feature activation-1.43e+00

Pos logit contributions
nam+0.450
 pans+0.448
 ding+0.446
 counters+0.437
 forward+0.429
Neg logit contributions
zag-0.429
oot-0.399
uzz-0.385
seek-0.373
 sometime-0.359
Token and
Token ID290
Feature activation+8.45e-01

Pos logit contributions
zag+0.084
oot+0.079
seek+0.075
uzz+0.074
ogo+0.071
Neg logit contributions
 pans-0.066
 forward-0.064
 ding-0.063
nam-0.063
 counters-0.062
Token ran
Token ID4966
Feature activation+1.61e+00

Pos logit contributions
 brightest+0.053
 ju+0.052
sc+0.050
 redd+0.049
ifying+0.049
Neg logit contributions
gy-0.030
 again-0.030
 now-0.030
uzz-0.029
oot-0.029
Token to
Token ID284
Feature activation-4.96e-01

Pos logit contributions
nam+0.094
 pans+0.094
 ding+0.093
 counters+0.091
 forward+0.089
Neg logit contributions
zag-0.074
oot-0.068
uzz-0.066
seek-0.064
 sometime-0.061
Token hide
Token ID7808
Feature activation-3.41e-01

Pos logit contributions
zag+0.033
oot+0.031
seek+0.029
uzz+0.029
ogo+0.028
Neg logit contributions
nam-0.020
 pans-0.020
 ding-0.020
 forward-0.019
 counters-0.019
Token dish
Token ID9433
Feature activation+2.59e-01

Pos logit contributions
nam+0.168
 stressed+0.145
 forward+0.144
 pans+0.137
ults+0.137
Neg logit contributions
zag-0.161
oot-0.136
seek-0.133
ippy-0.131
ad-0.129
Token.
Token ID13
Feature activation+5.03e-01

Pos logit contributions
nam+0.017
 pans+0.015
 ding+0.015
 spec+0.015
 counters+0.015
Neg logit contributions
zag-0.011
oot-0.010
uzz-0.009
seek-0.009
 sometime-0.009
Token Tom
Token ID4186
Feature activation+1.08e-01

Pos logit contributions
 pans+0.023
nam+0.023
 ding+0.023
 counters+0.022
 forward+0.022
Neg logit contributions
zag-0.029
oot-0.028
uzz-0.027
seek-0.026
 sometime-0.025
Token puts
Token ID7584
Feature activation-7.84e-01

Pos logit contributions
nam+0.005
 pans+0.005
 ding+0.005
 forward+0.005
 counters+0.005
Neg logit contributions
zag-0.006
oot-0.005
uzz-0.005
seek-0.005
 sometime-0.005
Token some
Token ID617
Feature activation-1.63e+00

Pos logit contributions
zag+0.027
uzz+0.027
 sometime+0.024
 again+0.024
gy+0.024
Neg logit contributions
 counters-0.048
nam-0.047
 ding-0.045
 spec-0.045
 pans-0.045
Token flour
Token ID10601
Feature activation+8.39e+00

Pos logit contributions
zag+0.074
 sometime+0.074
 again+0.071
oot+0.069
ad+0.068
Neg logit contributions
nam-0.081
 ding-0.076
 forward-0.073
 counters-0.072
cient-0.071
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
nam+0.432
 ding+0.414
 counters+0.412
 pans+0.411
 spec+0.389
Neg logit contributions
zag-0.450
oot-0.419
uzz-0.411
gy-0.385
 sometime-0.383
Token water
Token ID1660
Feature activation+2.97e+00

Pos logit contributions
 forward+0.046
nam+0.045
 ding+0.043
 counters+0.041
sc+0.040
Neg logit contributions
zag-0.057
 sometime-0.055
uzz-0.052
oot-0.051
seek-0.051
Token in
Token ID287
Feature activation+1.28e+00

Pos logit contributions
nam+0.153
 counters+0.143
 ding+0.142
 pans+0.142
 brightest+0.137
Neg logit contributions
zag-0.162
uzz-0.150
oot-0.149
seek-0.140
gy-0.137
Token another
Token ID1194
Feature activation-4.17e+00

Pos logit contributions
nam+0.066
 ding+0.066
 pans+0.066
 counters+0.065
 forward+0.063
Neg logit contributions
zag-0.067
oot-0.062
uzz-0.061
seek-0.058
 sometime-0.057
Token bowl
Token ID9396
Feature activation+3.02e+00

Pos logit contributions
zag+0.172
 sometime+0.170
 again+0.163
gy+0.153
 now+0.142
Neg logit contributions
nam-0.245
 ding-0.229
 spec-0.210
 Hungry-0.209
 capt-0.209
Token with
Token ID351
Feature activation+5.03e-01

Pos logit contributions
nam+0.045
 pans+0.045
 ding+0.044
 counters+0.044
 spec+0.041
Neg logit contributions
zag-0.044
oot-0.041
uzz-0.040
seek-0.038
 sometime-0.036
Token a
Token ID257
Feature activation+9.32e-01

Pos logit contributions
sc+0.028
 forward+0.027
 counters+0.027
 ding+0.027
 stressed+0.026
Neg logit contributions
uzz-0.021
ad-0.020
zag-0.019
oot-0.019
 sometime-0.018
Token messy
Token ID24097
Feature activation-6.48e-01

Pos logit contributions
nam+0.044
 forward+0.041
 counters+0.041
sc+0.040
 stressed+0.039
Neg logit contributions
zag-0.052
onna-0.044
uzz-0.042
ah-0.042
 sometime-0.041
Token pile
Token ID14540
Feature activation+1.09e+00

Pos logit contributions
zag+0.042
oot+0.039
uzz+0.038
seek+0.037
gy+0.037
Neg logit contributions
nam-0.026
 ding-0.025
 pans-0.025
 forward-0.025
 counters-0.024
Token of
Token ID286
Feature activation+3.69e+00

Pos logit contributions
nam+0.055
 pans+0.054
 ding+0.054
 counters+0.052
 forward+0.050
Neg logit contributions
zag-0.059
oot-0.056
uzz-0.055
seek-0.051
gy-0.050
Token flour
Token ID10601
Feature activation+8.38e+00

Pos logit contributions
 forward+0.205
sc+0.193
pared+0.185
nam+0.176
ults+0.171
Neg logit contributions
ad-0.149
uzz-0.145
 now-0.145
 sometime-0.144
zag-0.138
Token and
Token ID290
Feature activation+4.25e-01

Pos logit contributions
nam+0.484
 pans+0.464
 ding+0.463
 counters+0.457
 forward+0.444
Neg logit contributions
zag-0.401
oot-0.368
uzz-0.351
gy-0.333
seek-0.330
Token sugar
Token ID7543
Feature activation+4.25e+00

Pos logit contributions
 forward+0.020
 ding+0.017
nam+0.017
 stressed+0.016
sc+0.016
Neg logit contributions
zag-0.023
 sometime-0.023
uzz-0.022
seek-0.021
gy-0.021
Token.
Token ID13
Feature activation+9.19e-02

Pos logit contributions
nam+0.211
 ding+0.205
 pans+0.204
 counters+0.200
 forward+0.197
Neg logit contributions
zag-0.236
oot-0.219
uzz-0.211
seek-0.204
gy-0.200
Token "
Token ID366
Feature activation+2.66e+00

Pos logit contributions
nam+0.005
 pans+0.005
 ding+0.004
 counters+0.004
 forward+0.004
Neg logit contributions
zag-0.005
uzz-0.005
oot-0.005
 sometime-0.004
seek-0.004
TokenDo
Token ID5211
Feature activation+2.08e+00

Pos logit contributions
 counters+0.121
nam+0.121
 forward+0.121
 pans+0.118
 ding+0.117
Neg logit contributions
zag-0.144
uzz-0.138
seek-0.134
 sometime-0.133
oot-0.132
Token
Token ID198
Feature activation+5.90e-01

Pos logit contributions
nam+0.031
 pans+0.030
 ding+0.030
 counters+0.030
 forward+0.029
Neg logit contributions
zag-0.027
oot-0.025
uzz-0.025
seek-0.024
 sometime-0.023
Token
Token ID198
Feature activation+6.33e-01

Pos logit contributions
 ding+0.024
 pans+0.023
 counters+0.023
nam+0.022
 y+0.022
Neg logit contributions
zag-0.037
oot-0.035
uzz-0.034
seek-0.034
gy-0.033
TokenThey
Token ID2990
Feature activation+6.82e-01

Pos logit contributions
nam+0.037
 pans+0.036
 ding+0.036
 counters+0.036
 forward+0.035
Neg logit contributions
zag-0.030
oot-0.028
uzz-0.027
seek-0.026
 sometime-0.025
Token measured
Token ID8630
Feature activation+6.03e-01

Pos logit contributions
 pans+0.030
nam+0.030
 ding+0.030
 counters+0.029
 forward+0.029
Neg logit contributions
zag-0.041
oot-0.038
uzz-0.037
seek-0.036
 sometime-0.035
Token the
Token ID262
Feature activation+9.22e-01

Pos logit contributions
nam+0.036
 counters+0.036
 pans+0.036
 stressed+0.035
sc+0.035
Neg logit contributions
zag-0.025
uzz-0.023
 sometime-0.023
gy-0.022
oot-0.021
Token flour
Token ID10601
Feature activation+8.38e+00

Pos logit contributions
nam+0.041
 forward+0.039
 ding+0.037
sc+0.036
 pans+0.035
Neg logit contributions
zag-0.055
 sometime-0.048
uzz-0.048
gy-0.047
oot-0.047
Token,
Token ID11
Feature activation+3.00e-01

Pos logit contributions
nam+0.553
 pans+0.526
 counters+0.516
 ding+0.516
 brightest+0.497
Neg logit contributions
zag-0.343
oot-0.303
uzz-0.290
 sometime-0.275
gy-0.275
Token the
Token ID262
Feature activation+9.51e-01

Pos logit contributions
 forward+0.018
sc+0.017
 ding+0.017
pared+0.017
nam+0.016
Neg logit contributions
 sometime-0.011
zag-0.010
uzz-0.010
 again-0.010
gy-0.010
Token sugar
Token ID7543
Feature activation+4.30e+00

Pos logit contributions
 forward+0.041
nam+0.040
sc+0.040
 ding+0.037
pared+0.036
Neg logit contributions
zag-0.053
uzz-0.048
 sometime-0.047
 fault-0.047
gy-0.047
Token,
Token ID11
Feature activation+3.22e-01

Pos logit contributions
nam+0.277
 ding+0.263
 pans+0.262
 forward+0.258
 counters+0.256
Neg logit contributions
zag-0.185
oot-0.161
uzz-0.152
gy-0.149
 sometime-0.146
Token and
Token ID290
Feature activation+7.32e-01

Pos logit contributions
nam+0.021
sc+0.020
 forward+0.020
 counters+0.020
 spec+0.020
Neg logit contributions
zag-0.010
 sometime-0.010
uzz-0.009
 again-0.009
gy-0.009
TokenThey
Token ID2990
Feature activation+4.16e-01

Pos logit contributions
nam+0.019
 ding+0.018
 spec+0.018
 counters+0.018
 forward+0.018
Neg logit contributions
zag-0.014
oot-0.013
uzz-0.012
seek-0.012
 sometime-0.012
Token did
Token ID750
Feature activation-8.68e-01

Pos logit contributions
 ding+0.021
 forward+0.021
 pans+0.020
nam+0.020
 counters+0.020
Neg logit contributions
zag-0.020
uzz-0.019
oot-0.019
 sometime-0.018
gy-0.018
Token not
Token ID407
Feature activation-1.53e+00

Pos logit contributions
zag+0.042
oot+0.041
uzz+0.037
seek+0.036
ippy+0.035
Neg logit contributions
 ding-0.051
 y-0.050
nam-0.049
 counters-0.049
 pans-0.049
Token hear
Token ID3285
Feature activation-8.13e-01

Pos logit contributions
zag+0.100
oot+0.092
uzz+0.088
seek+0.087
ippy+0.085
Neg logit contributions
 pans-0.066
 ding-0.065
nam-0.065
 counters-0.063
 forward-0.062
Token Mom
Token ID11254
Feature activation+4.25e+00

Pos logit contributions
zag+0.055
oot+0.051
seek+0.049
uzz+0.048
ippy+0.047
Neg logit contributions
 ding-0.034
nam-0.032
 y-0.032
 pans-0.032
 counters-0.032
Token coming
Token ID2406
Feature activation+8.38e+00

Pos logit contributions
nam+0.219
 ju+0.204
 brightest+0.202
 pans+0.197
 redd+0.188
Neg logit contributions
zag-0.243
oot-0.221
gy-0.220
uzz-0.214
seek-0.213
Token home
Token ID1363
Feature activation-5.41e+00

Pos logit contributions
nam+0.455
 ding+0.443
 pans+0.442
 counters+0.434
 ju+0.426
Neg logit contributions
zag-0.423
oot-0.396
uzz-0.388
seek-0.365
gy-0.361
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
zag+0.283
oot+0.264
uzz+0.254
seek+0.247
 sometime+0.237
Neg logit contributions
nam-0.282
 pans-0.282
 ding-0.280
 counters-0.275
 forward-0.270
Token They
Token ID1119
Feature activation+4.24e-01

Pos logit contributions
nam+0.028
 ding+0.027
 pans+0.027
 forward+0.026
 brightest+0.026
Neg logit contributions
uzz-0.025
zag-0.024
 sometime-0.022
oot-0.022
seek-0.021
Token did
Token ID750
Feature activation-8.93e-01

Pos logit contributions
 pans+0.020
nam+0.020
 ding+0.020
 counters+0.020
 forward+0.019
Neg logit contributions
zag-0.024
oot-0.022
uzz-0.022
seek-0.021
gy-0.020
Token not
Token ID407
Feature activation-1.53e+00

Pos logit contributions
oot+0.049
zag+0.048
uzz+0.043
ippy+0.042
seek+0.041
Neg logit contributions
 y-0.048
 ding-0.048
nam-0.047
 pans-0.045
 counters-0.045
Token and
Token ID290
Feature activation+1.05e+00

Pos logit contributions
zag+0.036
oot+0.034
uzz+0.034
seek+0.033
 sometime+0.031
Neg logit contributions
 ding-0.023
 pans-0.023
 counters-0.022
 forward-0.022
 y-0.021
Token Mia
Token ID32189
Feature activation-5.45e-01

Pos logit contributions
 ding+0.053
 pans+0.052
nam+0.052
 y+0.050
 forward+0.050
Neg logit contributions
zag-0.058
oot-0.056
seek-0.051
uzz-0.050
gy-0.049
Token hear
Token ID3285
Feature activation-4.76e-01

Pos logit contributions
zag+0.028
oot+0.026
uzz+0.025
seek+0.024
 sometime+0.024
Neg logit contributions
 pans-0.029
nam-0.028
 counters-0.027
 ding-0.027
 ju-0.026
Token their
Token ID511
Feature activation+9.91e-01

Pos logit contributions
zag+0.033
oot+0.031
seek+0.029
uzz+0.028
gy+0.028
Neg logit contributions
 ding-0.020
 pans-0.019
 counters-0.018
 y-0.018
 forward-0.017
Token mom
Token ID1995
Feature activation+2.18e+00

Pos logit contributions
 pans+0.050
 ding+0.050
nam+0.049
 counters+0.049
 y+0.047
Neg logit contributions
zag-0.054
oot-0.051
uzz-0.049
seek-0.048
 sometime-0.047
Token coming
Token ID2406
Feature activation+8.37e+00

Pos logit contributions
nam+0.136
 ju+0.131
 brightest+0.128
 pans+0.124
 redd+0.123
Neg logit contributions
zag-0.101
oot-0.096
uzz-0.091
gy-0.089
ad-0.085
Token.
Token ID13
Feature activation+7.62e-01

Pos logit contributions
nam+0.460
 ding+0.449
 pans+0.446
 counters+0.437
 ju+0.433
Neg logit contributions
zag-0.421
oot-0.392
uzz-0.385
seek-0.363
gy-0.358
Token They
Token ID1119
Feature activation+8.36e-01

Pos logit contributions
nam+0.041
 ju+0.039
 brightest+0.038
 forward+0.038
 pans+0.038
Neg logit contributions
zag-0.040
uzz-0.038
gy-0.035
oot-0.035
seek-0.034
Token know
Token ID760
Feature activation-2.44e+00

Pos logit contributions
 pans+0.044
nam+0.044
 counters+0.042
 ding+0.042
 ju+0.041
Neg logit contributions
zag-0.043
oot-0.040
uzz-0.039
gy-0.037
seek-0.036
Token she
Token ID673
Feature activation+2.16e+00

Pos logit contributions
zag+0.145
oot+0.135
uzz+0.131
seek+0.128
gy+0.123
Neg logit contributions
nam-0.112
 pans-0.112
 ding-0.111
 counters-0.109
 forward-0.106
Token will
Token ID481
Feature activation+2.00e+00

Pos logit contributions
 counters+0.079
 pans+0.079
 ding+0.078
 y+0.076
 forward+0.075
Neg logit contributions
zag-0.143
oot-0.139
uzz-0.135
seek-0.130
 sometime-0.127
Token tells
Token ID4952
Feature activation+1.82e-01

Pos logit contributions
 pans+0.023
 ding+0.023
nam+0.022
 counters+0.022
 y+0.022
Neg logit contributions
zag-0.043
oot-0.041
uzz-0.040
seek-0.039
gy-0.038
Token Sara
Token ID24799
Feature activation-4.75e-01

Pos logit contributions
 ding+0.009
nam+0.009
 pans+0.009
 counters+0.009
 forward+0.009
Neg logit contributions
zag-0.010
oot-0.009
uzz-0.009
seek-0.009
 sometime-0.009
Token to
Token ID284
Feature activation-5.89e-01

Pos logit contributions
zag+0.026
oot+0.024
seek+0.023
uzz+0.023
 sometime+0.021
Neg logit contributions
 pans-0.024
nam-0.023
 counters-0.023
 y-0.023
 ding-0.023
Token mix
Token ID5022
Feature activation+6.76e-01

Pos logit contributions
zag+0.034
oot+0.032
uzz+0.031
seek+0.030
 sometime+0.029
Neg logit contributions
 ding-0.027
 pans-0.027
nam-0.027
 counters-0.027
 y-0.026
Token the
Token ID262
Feature activation+8.22e-01

Pos logit contributions
nam+0.038
 ding+0.037
 counters+0.037
 spec+0.036
 pans+0.036
Neg logit contributions
zag-0.029
uzz-0.028
 sometime-0.027
oot-0.026
gy-0.024
Token flour
Token ID10601
Feature activation+8.37e+00

Pos logit contributions
nam+0.039
 forward+0.037
 ding+0.036
pared+0.034
sc+0.033
Neg logit contributions
zag-0.045
 fault-0.039
 sometime-0.039
uzz-0.039
onna-0.038
Token,
Token ID11
Feature activation+3.23e-01

Pos logit contributions
nam+0.483
 pans+0.472
 ding+0.469
 counters+0.465
 forward+0.448
Neg logit contributions
zag-0.396
oot-0.359
uzz-0.349
 sometime-0.330
seek-0.329
Token the
Token ID262
Feature activation+8.66e-01

Pos logit contributions
 forward+0.017
 ding+0.017
 spec+0.016
sc+0.016
nam+0.016
Neg logit contributions
zag-0.014
 sometime-0.014
uzz-0.013
oot-0.013
gy-0.013
Token eggs
Token ID9653
Feature activation+3.67e+00

Pos logit contributions
nam+0.036
 forward+0.036
pared+0.033
sc+0.031
 ding+0.031
Neg logit contributions
zag-0.050
 fault-0.044
onna-0.043
 sometime-0.043
uzz-0.042
Token and
Token ID290
Feature activation+7.79e-01

Pos logit contributions
nam+0.221
 pans+0.215
 ding+0.213
 counters+0.212
 forward+0.206
Neg logit contributions
zag-0.169
oot-0.150
uzz-0.145
gy-0.139
 sometime-0.138
Token the
Token ID262
Feature activation+8.82e-01

Pos logit contributions
 forward+0.043
sc+0.040
 spec+0.040
 ding+0.040
 counters+0.039
Neg logit contributions
 sometime-0.033
zag-0.032
uzz-0.030
 now-0.029
gy-0.029
Token.
Token ID13
Feature activation+6.18e-01

Pos logit contributions
nam+0.068
 counters+0.065
 ju+0.065
 ding+0.064
 pans+0.064
Neg logit contributions
uzz-0.049
zag-0.047
oot-0.046
 again-0.045
 sometime-0.043
Token They
Token ID1119
Feature activation+5.72e-01

Pos logit contributions
nam+0.030
 pans+0.029
 ding+0.029
 forward+0.028
 counters+0.028
Neg logit contributions
zag-0.035
uzz-0.033
oot-0.032
seek-0.031
 sometime-0.031
Token saw
Token ID2497
Feature activation+1.81e+00

Pos logit contributions
nam+0.024
 pans+0.024
 ding+0.024
 counters+0.023
 forward+0.023
Neg logit contributions
zag-0.035
oot-0.033
uzz-0.032
seek-0.032
 sometime-0.031
Token their
Token ID511
Feature activation+1.03e+00

Pos logit contributions
nam+0.091
 pans+0.090
 counters+0.088
 forward+0.088
 ding+0.087
Neg logit contributions
zag-0.094
uzz-0.089
oot-0.087
seek-0.082
gy-0.080
Token dad
Token ID9955
Feature activation+3.63e+00

Pos logit contributions
 pans+0.050
 ding+0.050
nam+0.050
 counters+0.049
 forward+0.047
Neg logit contributions
zag-0.057
oot-0.055
uzz-0.052
seek-0.051
 sometime-0.049
Token coming
Token ID2406
Feature activation+8.36e+00

Pos logit contributions
nam+0.198
 pans+0.191
 ju+0.190
 brightest+0.185
 ding+0.181
Neg logit contributions
zag-0.187
oot-0.170
uzz-0.167
gy-0.162
 sometime-0.161
Token home
Token ID1363
Feature activation-5.38e+00

Pos logit contributions
nam+0.396
 pans+0.393
 ding+0.391
 counters+0.383
 forward+0.372
Neg logit contributions
zag-0.479
oot-0.450
uzz-0.438
seek-0.424
 sometime-0.410
Token from
Token ID422
Feature activation+1.74e+00

Pos logit contributions
zag+0.276
oot+0.256
uzz+0.247
seek+0.240
 sometime+0.231
Neg logit contributions
nam-0.288
 pans-0.286
 ding-0.284
 counters-0.279
 forward-0.274
Token work
Token ID670
Feature activation-3.04e+00

Pos logit contributions
 pans+0.073
nam+0.070
 ding+0.069
 counters+0.067
 forward+0.066
Neg logit contributions
zag-0.118
oot-0.112
seek-0.104
uzz-0.103
ogo-0.098
Token.
Token ID13
Feature activation+6.48e-01

Pos logit contributions
zag+0.132
oot+0.120
uzz+0.117
seek+0.110
gy+0.104
Neg logit contributions
nam-0.189
 ding-0.182
 pans-0.182
 ju-0.181
 brightest-0.178
Token He
Token ID679
Feature activation+4.19e-01

Pos logit contributions
nam+0.034
 pans+0.033
 ding+0.033
 counters+0.033
 forward+0.032
Neg logit contributions
zag-0.034
uzz-0.032
oot-0.031
seek-0.030
gy-0.029
Tokenoons
Token ID13022
Feature activation+2.46e+00

Pos logit contributions
nam+0.056
 ding+0.053
 pans+0.052
 forward+0.052
 counters+0.050
Neg logit contributions
zag-0.072
oot-0.068
uzz-0.065
seek-0.063
ippy-0.062
Token,
Token ID11
Feature activation-6.74e-02

Pos logit contributions
 pans+0.134
nam+0.133
 ding+0.133
 counters+0.130
 forward+0.129
Neg logit contributions
zag-0.122
oot-0.114
uzz-0.109
seek-0.106
 sometime-0.101
Token cups
Token ID14180
Feature activation+4.58e+00

Pos logit contributions
zag+0.003
 sometime+0.003
uzz+0.003
gy+0.003
oot+0.003
Neg logit contributions
 forward-0.004
 ding-0.004
nam-0.004
 spec-0.003
pared-0.003
Token and
Token ID290
Feature activation+4.35e-01

Pos logit contributions
nam+0.290
 ding+0.284
 pans+0.278
 counters+0.272
 forward+0.271
Neg logit contributions
zag-0.196
oot-0.180
uzz-0.172
seek-0.164
 sometime-0.158
Token some
Token ID617
Feature activation-1.80e+00

Pos logit contributions
 forward+0.020
 ding+0.019
nam+0.018
 counters+0.017
 spec+0.017
Neg logit contributions
zag-0.025
uzz-0.023
 sometime-0.023
seek-0.022
oot-0.022
Token flour
Token ID10601
Feature activation+8.36e+00

Pos logit contributions
 sometime+0.082
zag+0.080
uzz+0.079
ad+0.074
 now+0.072
Neg logit contributions
 ding-0.089
nam-0.087
 forward-0.086
pared-0.084
 stressed-0.078
Token.
Token ID13
Feature activation+3.66e-01

Pos logit contributions
nam+0.503
 ding+0.491
 pans+0.484
 counters+0.480
 forward+0.469
Neg logit contributions
zag-0.382
oot-0.348
uzz-0.336
seek-0.317
gy-0.316
Token
Token ID198
Feature activation+3.29e-01

Pos logit contributions
nam+0.017
 ding+0.017
 pans+0.017
 counters+0.016
 forward+0.016
Neg logit contributions
zag-0.021
uzz-0.020
oot-0.020
 sometime-0.018
seek-0.018
Token
Token ID198
Feature activation+4.10e-01

Pos logit contributions
 pans+0.012
 ding+0.012
 counters+0.011
 forward+0.011
 y+0.011
Neg logit contributions
zag-0.022
oot-0.021
seek-0.020
gy-0.019
uzz-0.019
Token"
Token ID1
Feature activation-1.77e-01

Pos logit contributions
 pans+0.020
nam+0.020
 ding+0.020
 counters+0.019
 forward+0.019
Neg logit contributions
zag-0.023
oot-0.022
uzz-0.021
seek-0.021
gy-0.020
TokenLet
Token ID5756
Feature activation+3.91e+00

Pos logit contributions
zag+0.010
 sometime+0.009
uzz+0.009
seek+0.009
oot+0.009
Neg logit contributions
nam-0.008
 forward-0.008
 counters-0.008
 ding-0.007
 stressed-0.007
Token
Token ID198
Feature activation+5.99e-01

Pos logit contributions
 pans+0.019
 ding+0.019
 counters+0.018
 y+0.018
nam+0.018
Neg logit contributions
zag-0.037
oot-0.034
seek-0.033
gy-0.032
uzz-0.032
TokenThey
Token ID2990
Feature activation+5.21e-01

Pos logit contributions
 pans+0.028
 ding+0.027
nam+0.027
 counters+0.026
 forward+0.026
Neg logit contributions
zag-0.036
oot-0.034
uzz-0.032
seek-0.032
gy-0.031
Token heard
Token ID2982
Feature activation+1.48e+00

Pos logit contributions
 pans+0.023
 ding+0.023
nam+0.023
 counters+0.023
 forward+0.022
Neg logit contributions
zag-0.031
oot-0.029
uzz-0.028
seek-0.027
 sometime-0.027
Token their
Token ID511
Feature activation+8.63e-01

Pos logit contributions
 ding+0.064
nam+0.061
 pans+0.060
 counters+0.060
 y+0.060
Neg logit contributions
zag-0.096
oot-0.089
seek-0.085
uzz-0.082
 sometime-0.082
Token mom
Token ID1995
Feature activation+2.36e+00

Pos logit contributions
 ding+0.045
 pans+0.044
nam+0.044
 counters+0.043
 y+0.042
Neg logit contributions
zag-0.046
oot-0.044
uzz-0.042
seek-0.041
 sometime-0.039
Token coming
Token ID2406
Feature activation+8.36e+00

Pos logit contributions
nam+0.129
 ju+0.126
 brightest+0.119
 redd+0.118
 pans+0.116
Neg logit contributions
zag-0.129
oot-0.120
gy-0.118
ad-0.114
uzz-0.112
Token.
Token ID13
Feature activation+9.34e-01

Pos logit contributions
nam+0.484
 pans+0.467
 ju+0.466
 ding+0.464
 counters+0.456
Neg logit contributions
zag-0.398
oot-0.371
uzz-0.371
gy-0.342
seek-0.336
Token She
Token ID1375
Feature activation+7.79e-01

Pos logit contributions
nam+0.041
 pans+0.040
 ding+0.039
 counters+0.039
 forward+0.038
Neg logit contributions
zag-0.056
uzz-0.053
oot-0.053
seek-0.050
gy-0.049
Token saw
Token ID2497
Feature activation+1.72e+00

Pos logit contributions
nam+0.039
 pans+0.038
 ding+0.037
 counters+0.037
 forward+0.037
Neg logit contributions
zag-0.043
oot-0.040
uzz-0.039
gy-0.037
seek-0.036
Token the
Token ID262
Feature activation+9.47e-01

Pos logit contributions
nam+0.084
 pans+0.084
 ding+0.083
 counters+0.081
 y+0.079
Neg logit contributions
zag-0.098
oot-0.091
seek-0.087
uzz-0.086
 sometime-0.083
Token mess
Token ID2085
Feature activation-7.08e-01

Pos logit contributions
nam+0.046
 ding+0.045
 pans+0.045
 forward+0.044
 counters+0.044
Neg logit contributions
zag-0.052
oot-0.048
uzz-0.046
seek-0.045
gy-0.044
Token a
Token ID257
Feature activation+6.60e-01

Pos logit contributions
nam+0.025
 pans+0.024
 ding+0.024
 forward+0.024
 counters+0.024
Neg logit contributions
zag-0.024
oot-0.022
uzz-0.022
seek-0.021
 sometime-0.020
Token big
Token ID1263
Feature activation+2.74e+00

Pos logit contributions
nam+0.031
 forward+0.028
sc+0.027
 stressed+0.027
 counters+0.026
Neg logit contributions
zag-0.039
onna-0.032
gy-0.031
castle-0.031
 mistake-0.031
Token mess
Token ID2085
Feature activation-8.40e-01

Pos logit contributions
nam+0.127
 pans+0.123
 counters+0.119
 ding+0.119
 forward+0.118
Neg logit contributions
zag-0.160
oot-0.148
uzz-0.143
seek-0.138
 sometime-0.137
Token with
Token ID351
Feature activation+5.05e-01

Pos logit contributions
zag+0.040
oot+0.037
uzz+0.036
seek+0.034
 sometime+0.034
Neg logit contributions
nam-0.048
 pans-0.046
 ding-0.045
 ju-0.045
 counters-0.044
Token the
Token ID262
Feature activation+6.50e-01

Pos logit contributions
 ding+0.027
 counters+0.027
 forward+0.027
nam+0.026
sc+0.026
Neg logit contributions
uzz-0.022
zag-0.022
oot-0.020
 sometime-0.019
seek-0.019
Token flour
Token ID10601
Feature activation+8.36e+00

Pos logit contributions
nam+0.028
 forward+0.028
 ding+0.024
sc+0.023
 stressed+0.023
Neg logit contributions
zag-0.039
 fault-0.034
 sometime-0.032
gy-0.032
seek-0.031
Token.
Token ID13
Feature activation+5.13e-01

Pos logit contributions
nam+0.520
 pans+0.496
 ding+0.492
 counters+0.485
 forward+0.476
Neg logit contributions
zag-0.370
oot-0.329
uzz-0.314
gy-0.299
 sometime-0.298
Token She
Token ID1375
Feature activation+5.65e-01

Pos logit contributions
nam+0.027
 pans+0.026
 ding+0.026
 forward+0.025
 spec+0.025
Neg logit contributions
zag-0.026
uzz-0.024
oot-0.024
seek-0.023
 sometime-0.023
Token laughs
Token ID22051
Feature activation+1.62e+00

Pos logit contributions
 pans+0.022
 ding+0.022
nam+0.022
 counters+0.021
 y+0.020
Neg logit contributions
zag-0.037
oot-0.036
uzz-0.034
seek-0.034
gy-0.033
Token and
Token ID290
Feature activation+8.57e-01

Pos logit contributions
nam+0.098
 pans+0.097
 counters+0.095
 ding+0.094
 ju+0.091
Neg logit contributions
zag-0.072
oot-0.067
uzz-0.064
seek-0.061
 sometime-0.060
Token says
Token ID1139
Feature activation+1.60e+00

Pos logit contributions
nam+0.041
 forward+0.039
 counters+0.038
 pans+0.038
 ding+0.037
Neg logit contributions
zag-0.047
oot-0.043
seek-0.043
uzz-0.042
 sometime-0.042
Tokenirens
Token ID42917
Feature activation+2.38e+00

Pos logit contributions
 ding+0.062
 pans+0.062
 counters+0.061
 forward+0.058
nam+0.058
Neg logit contributions
zag-0.088
oot-0.081
uzz-0.081
gy-0.078
 sometime-0.077
Token and
Token ID290
Feature activation+7.33e-01

Pos logit contributions
nam+0.168
 ju+0.161
 pans+0.160
 brightest+0.155
 redd+0.153
Neg logit contributions
zag-0.090
oot-0.082
seek-0.074
uzz-0.071
gy-0.070
Token saw
Token ID2497
Feature activation+1.78e+00

Pos logit contributions
 forward+0.038
sc+0.037
 ju+0.037
 counters+0.036
nam+0.036
Neg logit contributions
zag-0.034
uzz-0.031
 sometime-0.030
seek-0.030
gy-0.030
Token red
Token ID2266
Feature activation+1.71e+00

Pos logit contributions
nam+0.089
 pans+0.088
 ju+0.085
 counters+0.085
 forward+0.085
Neg logit contributions
zag-0.089
uzz-0.088
oot-0.083
gy-0.079
seek-0.078
Token trucks
Token ID13960
Feature activation+2.61e+00

Pos logit contributions
nam+0.074
 pans+0.070
 ding+0.069
 forward+0.069
 counters+0.067
Neg logit contributions
zag-0.106
oot-0.099
uzz-0.096
seek-0.094
gy-0.093
Token coming
Token ID2406
Feature activation+8.36e+00

Pos logit contributions
nam+0.151
 pans+0.149
 counters+0.142
 ding+0.141
 ju+0.141
Neg logit contributions
zag-0.127
oot-0.116
uzz-0.109
seek-0.109
 sometime-0.102
Token.
Token ID13
Feature activation+5.97e-01

Pos logit contributions
nam+0.431
 ju+0.411
 pans+0.408
 counters+0.404
 brightest+0.387
Neg logit contributions
zag-0.457
uzz-0.437
oot-0.425
gy-0.418
 sometime-0.387
Token The
Token ID383
Feature activation-6.81e-01

Pos logit contributions
nam+0.029
 pans+0.028
 ding+0.028
 counters+0.027
 forward+0.026
Neg logit contributions
zag-0.033
uzz-0.031
oot-0.031
seek-0.029
 sometime-0.029
Token trucks
Token ID13960
Feature activation+2.62e+00

Pos logit contributions
zag+0.038
gy+0.033
uzz+0.032
seek+0.030
oot+0.030
Neg logit contributions
nam-0.035
 forward-0.031
 ju-0.031
 ding-0.030
sc-0.030
Token had
Token ID550
Feature activation-7.04e-01

Pos logit contributions
nam+0.121
 pans+0.118
 ding+0.114
 counters+0.114
 ju+0.111
Neg logit contributions
zag-0.157
oot-0.144
uzz-0.139
seek-0.135
gy-0.132
Token big
Token ID1263
Feature activation+3.00e+00

Pos logit contributions
zag+0.045
oot+0.043
uzz+0.041
seek+0.040
 sometime+0.039
Neg logit contributions
 pans-0.029
 ding-0.029
nam-0.029
 counters-0.028
 y-0.027
Token.
Token ID13
Feature activation+4.46e-01

Pos logit contributions
zag+0.039
oot+0.037
uzz+0.036
seek+0.034
 sometime+0.033
Neg logit contributions
nam-0.041
 pans-0.041
 ding-0.041
 counters-0.040
 forward-0.039
Token Now
Token ID2735
Feature activation+3.21e-01

Pos logit contributions
nam+0.017
 pans+0.017
 ding+0.017
 counters+0.017
 forward+0.016
Neg logit contributions
zag-0.029
oot-0.028
uzz-0.027
seek-0.026
 sometime-0.026
Token the
Token ID262
Feature activation+9.48e-01

Pos logit contributions
 pans+0.016
nam+0.016
 counters+0.016
 ding+0.015
 forward+0.015
Neg logit contributions
zag-0.017
oot-0.016
uzz-0.015
 sometime-0.015
seek-0.015
Token stuffing
Token ID43672
Feature activation+3.17e+00

Pos logit contributions
 pans+0.048
nam+0.047
 ding+0.047
 counters+0.046
 forward+0.046
Neg logit contributions
zag-0.051
oot-0.046
uzz-0.045
seek-0.044
 sometime-0.042
Token is
Token ID318
Feature activation+3.88e-01

Pos logit contributions
 pans+0.143
nam+0.143
 ding+0.143
 counters+0.139
 forward+0.136
Neg logit contributions
zag-0.186
oot-0.175
uzz-0.170
seek-0.165
 sometime-0.159
Token coming
Token ID2406
Feature activation+8.34e+00

Pos logit contributions
nam+0.018
 pans+0.018
 ding+0.018
 counters+0.018
 spec+0.018
Neg logit contributions
zag-0.022
oot-0.020
uzz-0.019
gy-0.019
seek-0.018
Token out
Token ID503
Feature activation+6.36e+00

Pos logit contributions
 ding+0.418
 pans+0.417
nam+0.415
 counters+0.404
 forward+0.402
Neg logit contributions
zag-0.456
oot-0.425
uzz-0.410
seek-0.403
 sometime-0.385
Token.
Token ID13
Feature activation+4.74e-01

Pos logit contributions
nam+0.371
 pans+0.360
 ding+0.357
 counters+0.353
 forward+0.343
Neg logit contributions
zag-0.296
oot-0.274
uzz-0.263
 sometime-0.251
seek-0.250
Token And
Token ID843
Feature activation+1.84e+00

Pos logit contributions
nam+0.021
 pans+0.020
 ding+0.020
 counters+0.019
 forward+0.019
Neg logit contributions
zag-0.028
uzz-0.027
oot-0.027
seek-0.026
 sometime-0.025
Token you
Token ID345
Feature activation+2.22e+00

Pos logit contributions
 counters+0.092
 pans+0.092
 ding+0.091
 forward+0.089
nam+0.089
Neg logit contributions
zag-0.092
oot-0.087
uzz-0.085
 sometime-0.084
seek-0.078
Token have
Token ID423
Feature activation-3.56e+00

Pos logit contributions
nam+0.095
 pans+0.094
 ding+0.094
 y+0.093
 counters+0.090
Neg logit contributions
zag-0.139
oot-0.131
uzz-0.127
seek-0.127
ippy-0.120
Token pieces
Token ID5207
Feature activation-1.20e+00

Pos logit contributions
zag+0.031
oot+0.029
uzz+0.028
seek+0.028
 sometime+0.027
Neg logit contributions
 pans-0.019
nam-0.019
 ding-0.019
 counters-0.018
 forward-0.017
Token.
Token ID13
Feature activation+4.68e-01

Pos logit contributions
zag+0.058
oot+0.054
uzz+0.051
seek+0.049
 sometime+0.047
Neg logit contributions
nam-0.068
 pans-0.067
 ding-0.067
 counters-0.066
 ju-0.064
Token They
Token ID1119
Feature activation+4.88e-01

Pos logit contributions
nam+0.021
 pans+0.021
 ding+0.021
 counters+0.020
 forward+0.020
Neg logit contributions
zag-0.028
oot-0.027
uzz-0.026
seek-0.025
 sometime-0.024
Token heard
Token ID2982
Feature activation+1.46e+00

Pos logit contributions
 pans+0.022
 ding+0.022
 forward+0.022
 counters+0.022
nam+0.022
Neg logit contributions
zag-0.027
oot-0.026
uzz-0.025
seek-0.024
gy-0.024
Token mom
Token ID1995
Feature activation+2.13e+00

Pos logit contributions
nam+0.076
 pans+0.076
 counters+0.073
 forward+0.073
 ding+0.073
Neg logit contributions
zag-0.073
oot-0.069
uzz-0.069
seek-0.064
 sometime-0.062
Token coming
Token ID2406
Feature activation+8.34e+00

Pos logit contributions
nam+0.130
 ju+0.128
 brightest+0.123
 redd+0.120
 fres+0.113
Neg logit contributions
zag-0.104
gy-0.097
oot-0.095
uzz-0.090
istle-0.089
Token and
Token ID290
Feature activation+7.36e-01

Pos logit contributions
nam+0.452
 ding+0.438
 pans+0.438
 counters+0.430
 ju+0.427
Neg logit contributions
zag-0.426
oot-0.399
uzz-0.392
seek-0.365
gy-0.365
Token tried
Token ID3088
Feature activation-6.18e-01

Pos logit contributions
 brightest+0.049
 ju+0.048
 redd+0.046
sc+0.044
 forward+0.044
Neg logit contributions
uzz-0.025
gy-0.024
 now-0.024
oot-0.023
 again-0.023
Token to
Token ID284
Feature activation-5.60e-01

Pos logit contributions
zag+0.040
oot+0.040
ebra+0.037
ogo+0.037
ippy+0.036
Neg logit contributions
nam-0.024
 pans-0.024
 ding-0.023
 y-0.023
 forward-0.022
Token hide
Token ID7808
Feature activation-4.00e-01

Pos logit contributions
zag+0.033
oot+0.031
uzz+0.030
seek+0.029
 sometime+0.028
Neg logit contributions
 pans-0.026
nam-0.026
 ding-0.026
 counters-0.025
 forward-0.024
Token under
Token ID739
Feature activation+4.07e-01

Pos logit contributions
zag+0.023
oot+0.022
uzz+0.021
seek+0.021
 sometime+0.020
Neg logit contributions
nam-0.019
 pans-0.019
 ding-0.018
 counters-0.018
 forward-0.018
Token.
Token ID13
Feature activation+6.53e-01

Pos logit contributions
nam+0.162
 pans+0.158
 ding+0.156
 counters+0.154
 ju+0.150
Neg logit contributions
zag-0.142
oot-0.131
uzz-0.128
seek-0.122
 sometime-0.121
Token They
Token ID1119
Feature activation+8.22e-01

Pos logit contributions
nam+0.030
 pans+0.029
 ding+0.029
 counters+0.028
 forward+0.028
Neg logit contributions
zag-0.038
uzz-0.036
oot-0.036
seek-0.034
 sometime-0.034
Token see
Token ID766
Feature activation-6.85e-02

Pos logit contributions
 pans+0.045
nam+0.045
 counters+0.044
 ding+0.044
 forward+0.043
Neg logit contributions
zag-0.040
oot-0.036
uzz-0.035
seek-0.034
gy-0.033
Token a
Token ID257
Feature activation+9.59e-01

Pos logit contributions
zag+0.003
uzz+0.003
oot+0.003
seek+0.003
gy+0.003
Neg logit contributions
 pans-0.004
nam-0.004
 ding-0.003
 counters-0.003
 forward-0.003
Token giant
Token ID6175
Feature activation+1.10e+00

Pos logit contributions
nam+0.041
 counters+0.039
 forward+0.039
 pans+0.038
sc+0.037
Neg logit contributions
zag-0.060
oot-0.054
uzz-0.052
gy-0.050
 sometime-0.050
Token coming
Token ID2406
Feature activation+8.34e+00

Pos logit contributions
nam+0.064
 pans+0.061
 counters+0.060
 ding+0.060
 forward+0.059
Neg logit contributions
zag-0.053
oot-0.048
uzz-0.046
seek-0.044
 sometime-0.044
Token to
Token ID284
Feature activation-5.20e-01

Pos logit contributions
nam+0.375
 pans+0.366
 ding+0.360
 counters+0.360
 forward+0.342
Neg logit contributions
zag-0.503
oot-0.474
uzz-0.466
seek-0.445
gy-0.433
Token the
Token ID262
Feature activation+9.07e-01

Pos logit contributions
zag+0.036
oot+0.034
uzz+0.031
seek+0.031
ippy+0.030
Neg logit contributions
 pans-0.021
 ding-0.021
nam-0.020
 y-0.020
 counters-0.019
Token hill
Token ID12788
Feature activation-1.08e+00

Pos logit contributions
nam+0.043
 pans+0.043
 ding+0.042
 counters+0.041
 forward+0.040
Neg logit contributions
zag-0.052
oot-0.049
uzz-0.048
seek-0.046
 sometime-0.045
Token.
Token ID13
Feature activation+6.61e-01

Pos logit contributions
zag+0.054
oot+0.050
uzz+0.048
seek+0.047
 sometime+0.045
Neg logit contributions
nam-0.059
 pans-0.059
 ding-0.058
 counters-0.057
 forward-0.056
Token He
Token ID679
Feature activation+6.21e-01

Pos logit contributions
nam+0.034
 pans+0.032
 ding+0.032
 counters+0.032
 forward+0.031
Neg logit contributions
zag-0.036
uzz-0.034
oot-0.033
seek-0.032
 sometime-0.031
Token lovely
Token ID14081
Feature activation+7.79e-01

Pos logit contributions
 ding+0.089
 pans+0.086
 y+0.084
 forward+0.083
nam+0.081
Neg logit contributions
zag-0.145
oot-0.138
seek-0.136
uzz-0.133
 sometime-0.129
Token little
Token ID1310
Feature activation+2.92e+00

Pos logit contributions
 pans+0.039
nam+0.039
 ding+0.039
 counters+0.038
 forward+0.037
Neg logit contributions
zag-0.042
oot-0.039
uzz-0.038
seek-0.037
 sometime-0.035
Token dog
Token ID3290
Feature activation-2.15e+00

Pos logit contributions
nam+0.130
 counters+0.124
 pans+0.124
 ding+0.123
 forward+0.115
Neg logit contributions
zag-0.171
oot-0.163
uzz-0.160
gy-0.155
 sometime-0.154
Token called
Token ID1444
Feature activation+3.85e+00

Pos logit contributions
zag+0.109
oot+0.102
uzz+0.099
seek+0.095
 sometime+0.091
Neg logit contributions
 ding-0.113
 pans-0.113
nam-0.113
 counters-0.111
 forward-0.110
Token Zig
Token ID24992
Feature activation-4.81e+00

Pos logit contributions
 pans+0.218
nam+0.217
 ding+0.215
 counters+0.213
 forward+0.204
Neg logit contributions
zag-0.184
oot-0.171
uzz-0.167
seek-0.158
gy-0.153
Tokenzag
Token ID50183
Feature activation-1.00e+01

Pos logit contributions
oot+0.081
seek+0.067
 sometime+0.061
uzz+0.058
zag+0.052
Neg logit contributions
 forward-0.367
 ding-0.364
 de-0.358
 spec-0.356
 low-0.352
Token.
Token ID13
Feature activation-2.78e-01

Pos logit contributions
zag+0.529
oot+0.523
uzz+0.501
seek+0.480
 sometime+0.473
Neg logit contributions
 ding-0.481
 pans-0.474
nam-0.474
 counters-0.465
 forward-0.457
Token Zig
Token ID24992
Feature activation-3.88e+00

Pos logit contributions
zag+0.015
oot+0.014
seek+0.013
uzz+0.013
 sometime+0.013
Neg logit contributions
 ding-0.014
nam-0.013
 pans-0.013
 forward-0.013
 counters-0.013
Tokenzag
Token ID50183
Feature activation-9.38e+00

Pos logit contributions
oot+0.064
seek+0.050
 sometime+0.050
 recess+0.046
 seeker+0.042
Neg logit contributions
 ding-0.291
 de-0.291
 spec-0.284
 low-0.280
 forward-0.278
Token was
Token ID373
Feature activation-6.26e-01

Pos logit contributions
oot+0.543
zag+0.542
uzz+0.528
seek+0.499
 sometime+0.490
Neg logit contributions
 ding-0.391
 pans-0.379
nam-0.375
 counters-0.374
 y-0.369
Token a
Token ID257
Feature activation+6.24e-01

Pos logit contributions
zag+0.041
oot+0.038
uzz+0.037
gy+0.036
seek+0.036
Neg logit contributions
 pans-0.026
nam-0.026
 counters-0.025
 ding-0.024
 ju-0.023
Token played
Token ID2826
Feature activation-2.97e+00

Pos logit contributions
nam+0.051
 pans+0.051
 ding+0.050
 forward+0.049
 counters+0.049
Neg logit contributions
zag-0.077
oot-0.073
uzz-0.070
seek-0.070
 sometime-0.067
Token hide
Token ID7808
Feature activation-1.20e+00

Pos logit contributions
zag+0.197
oot+0.193
uzz+0.183
seek+0.177
ogo+0.174
Neg logit contributions
 y-0.111
 ding-0.110
 pans-0.109
 forward-0.109
 counters-0.108
Token-
Token ID12
Feature activation-1.23e+00

Pos logit contributions
zag+0.069
oot+0.064
seek+0.061
uzz+0.060
ogo+0.057
Neg logit contributions
 pans-0.058
nam-0.057
 forward-0.056
 counters-0.056
 y-0.055
Tokenand
Token ID392
Feature activation+1.87e+00

Pos logit contributions
zag+0.083
oot+0.079
uzz+0.077
seek+0.076
 sometime+0.073
Neg logit contributions
nam-0.045
 pans-0.045
 ding-0.045
 counters-0.043
 forward-0.042
Token-
Token ID12
Feature activation-1.28e+00

Pos logit contributions
 pans+0.103
nam+0.102
 ding+0.101
 counters+0.100
 forward+0.098
Neg logit contributions
zag-0.091
oot-0.084
uzz-0.082
seek-0.078
 sometime-0.077
Tokenseek
Token ID36163
Feature activation-9.94e+00

Pos logit contributions
zag+0.018
oot+0.013
uzz+0.013
 sometime+0.009
ogo+0.008
Neg logit contributions
sc-0.109
nam-0.109
 ding-0.109
 counters-0.108
 pans-0.107
Token.
Token ID13
Feature activation-2.61e-03

Pos logit contributions
zag+0.589
oot+0.573
uzz+0.538
seek+0.520
gy+0.509
Neg logit contributions
nam-0.430
 pans-0.428
 ding-0.426
 forward-0.423
 counters-0.419
Token After
Token ID2293
Feature activation+5.48e-01

Pos logit contributions
zag+0.000
oot+0.000
uzz+0.000
seek+0.000
 sometime+0.000
Neg logit contributions
nam-0.000
 pans-0.000
 ding-0.000
 counters-0.000
 forward-0.000
Token a
Token ID257
Feature activation+7.23e-01

Pos logit contributions
 y+0.021
 ding+0.019
 pans+0.019
nam+0.019
 ready+0.018
Neg logit contributions
zag-0.038
oot-0.036
uzz-0.034
asured-0.033
gy-0.033
Token while
Token ID981
Feature activation+3.14e+00

Pos logit contributions
nam+0.031
 counters+0.031
 pans+0.030
 ding+0.030
 forward+0.028
Neg logit contributions
zag-0.046
oot-0.041
 sometime-0.041
seek-0.041
uzz-0.038
Token the
Token ID262
Feature activation+6.62e-01

Pos logit contributions
 ding+0.157
 pans+0.157
nam+0.155
 forward+0.154
 counters+0.150
Neg logit contributions
zag-0.171
oot-0.160
uzz-0.155
seek-0.153
gy-0.143
Token play
Token ID711
Feature activation-4.31e+00

Pos logit contributions
zag+0.079
oot+0.077
uzz+0.074
seek+0.071
ogo+0.068
Neg logit contributions
nam-0.065
 ding-0.065
 pans-0.064
 counters-0.063
 y-0.063
Token hide
Token ID7808
Feature activation-1.13e+00

Pos logit contributions
zag+0.325
oot+0.315
ogo+0.314
 fault+0.301
ippy+0.296
Neg logit contributions
 y-0.141
sc-0.131
 forward-0.125
 low-0.118
 pans-0.112
Token-
Token ID12
Feature activation-1.12e+00

Pos logit contributions
zag+0.070
oot+0.065
seek+0.062
uzz+0.060
ogo+0.058
Neg logit contributions
 pans-0.051
nam-0.050
 forward-0.049
 counters-0.048
 y-0.047
Tokenand
Token ID392
Feature activation+2.02e+00

Pos logit contributions
zag+0.075
oot+0.071
uzz+0.069
seek+0.068
gy+0.065
Neg logit contributions
 pans-0.043
nam-0.043
 ding-0.043
 counters-0.042
 forward-0.040
Token-
Token ID12
Feature activation-1.19e+00

Pos logit contributions
 pans+0.114
nam+0.114
 ding+0.112
 counters+0.111
 forward+0.109
Neg logit contributions
zag-0.097
oot-0.089
uzz-0.087
seek-0.083
 sometime-0.081
Tokenseek
Token ID36163
Feature activation-9.90e+00

Pos logit contributions
zag+0.016
uzz+0.013
oot+0.013
 sometime+0.010
ogo+0.010
Neg logit contributions
nam-0.101
sc-0.101
 counters-0.100
 ding-0.099
 forward-0.099
Token behind
Token ID2157
Feature activation+1.32e+00

Pos logit contributions
zag+0.582
oot+0.561
uzz+0.523
seek+0.509
gy+0.503
Neg logit contributions
nam-0.447
 pans-0.441
 forward-0.434
 ding-0.432
 counters-0.428
Token them
Token ID606
Feature activation+1.43e-01

Pos logit contributions
 pans+0.058
nam+0.057
 ding+0.057
 counters+0.056
 forward+0.056
Neg logit contributions
zag-0.080
oot-0.076
uzz-0.072
seek-0.071
 sometime-0.067
Token.
Token ID13
Feature activation-3.87e-01

Pos logit contributions
 pans+0.008
nam+0.008
 ding+0.008
 counters+0.008
 forward+0.008
Neg logit contributions
zag-0.007
oot-0.006
uzz-0.006
seek-0.006
 sometime-0.006
Token Suddenly
Token ID24975
Feature activation+1.60e+00

Pos logit contributions
zag+0.024
oot+0.023
uzz+0.022
seek+0.022
 sometime+0.021
Neg logit contributions
nam-0.016
 pans-0.016
 ding-0.016
 counters-0.016
 forward-0.015
Token,
Token ID11
Feature activation-6.90e-01

Pos logit contributions
 pans+0.085
nam+0.085
 ding+0.085
 counters+0.083
 forward+0.082
Neg logit contributions
zag-0.081
oot-0.076
uzz-0.073
seek-0.071
 sometime-0.068
Token play
Token ID711
Feature activation-4.21e+00

Pos logit contributions
zag+0.079
oot+0.076
uzz+0.075
seek+0.070
ippy+0.069
Neg logit contributions
 pans-0.069
 y-0.069
nam-0.068
 ding-0.067
 counters-0.067
Token hide
Token ID7808
Feature activation-1.02e+00

Pos logit contributions
zag+0.320
uzz+0.311
oot+0.304
seek+0.290
ogo+0.286
Neg logit contributions
 pans-0.126
 y-0.123
 ding-0.122
 counters-0.120
nam-0.117
Token-
Token ID12
Feature activation-1.08e+00

Pos logit contributions
zag+0.059
oot+0.053
uzz+0.052
seek+0.051
 sometime+0.049
Neg logit contributions
 pans-0.052
nam-0.050
 counters-0.049
 y-0.048
 ding-0.047
Tokenand
Token ID392
Feature activation+2.09e+00

Pos logit contributions
zag+0.074
oot+0.070
uzz+0.068
seek+0.067
 sometime+0.064
Neg logit contributions
nam-0.040
 pans-0.039
 ding-0.039
 counters-0.038
 forward-0.037
Token-
Token ID12
Feature activation-1.13e+00

Pos logit contributions
nam+0.123
 pans+0.122
 ding+0.122
 counters+0.120
 forward+0.118
Neg logit contributions
zag-0.096
oot-0.089
uzz-0.085
seek-0.082
 sometime-0.078
Tokenseek
Token ID36163
Feature activation-9.88e+00

Pos logit contributions
zag+0.016
uzz+0.012
 sometime+0.012
oot+0.012
ogo+0.008
Neg logit contributions
nam-0.095
 counters-0.095
sc-0.094
 pans-0.094
 ding-0.094
Token with
Token ID351
Feature activation-2.27e-01

Pos logit contributions
zag+0.620
oot+0.600
uzz+0.566
seek+0.545
gy+0.539
Neg logit contributions
nam-0.409
 pans-0.403
 ding-0.394
 counters-0.391
 forward-0.390
Token her
Token ID607
Feature activation-5.22e-01

Pos logit contributions
zag+0.014
oot+0.013
uzz+0.012
seek+0.012
 sometime+0.012
Neg logit contributions
nam-0.011
 pans-0.010
 ding-0.010
 counters-0.010
 y-0.010
Token friends
Token ID2460
Feature activation-3.03e+00

Pos logit contributions
zag+0.026
oot+0.025
seek+0.024
uzz+0.024
 sometime+0.022
Neg logit contributions
 pans-0.029
nam-0.029
 y-0.028
 ding-0.027
 counters-0.027
Token.
Token ID13
Feature activation-6.76e-01

Pos logit contributions
zag+0.156
oot+0.144
uzz+0.140
seek+0.135
 sometime+0.132
Neg logit contributions
 ding-0.162
 pans-0.162
nam-0.161
 counters-0.158
 forward-0.152
Token One
Token ID1881
Feature activation-4.26e+00

Pos logit contributions
zag+0.035
oot+0.033
uzz+0.030
seek+0.030
ogo+0.028
Neg logit contributions
nam-0.036
 ding-0.035
 counters-0.035
 pans-0.035
 forward-0.035
Token and
Token ID290
Feature activation-4.29e-01

Pos logit contributions
zag+0.133
oot+0.123
uzz+0.118
seek+0.116
 sometime+0.112
Neg logit contributions
nam-0.138
 pans-0.137
 ding-0.135
 counters-0.133
 forward-0.130
Token hide
Token ID7808
Feature activation-1.11e+00

Pos logit contributions
zag+0.026
oot+0.024
uzz+0.023
seek+0.023
 sometime+0.022
Neg logit contributions
nam-0.019
 pans-0.019
 ding-0.019
 counters-0.018
 forward-0.018
Token-
Token ID12
Feature activation-1.05e+00

Pos logit contributions
zag+0.067
oot+0.062
seek+0.059
uzz+0.058
ogo+0.055
Neg logit contributions
 pans-0.053
nam-0.051
 counters-0.049
 y-0.049
 ding-0.048
Tokenand
Token ID392
Feature activation+1.85e+00

Pos logit contributions
zag+0.066
oot+0.062
uzz+0.061
seek+0.059
 sometime+0.057
Neg logit contributions
nam-0.044
 pans-0.044
 ding-0.043
 counters-0.042
 forward-0.041
Token-
Token ID12
Feature activation-1.13e+00

Pos logit contributions
 pans+0.103
nam+0.103
 ding+0.101
 counters+0.100
 forward+0.099
Neg logit contributions
zag-0.089
oot-0.082
uzz-0.080
seek-0.076
 sometime-0.075
Tokenseek
Token ID36163
Feature activation-9.84e+00

Pos logit contributions
zag+0.015
uzz+0.012
oot+0.011
 sometime+0.007
ogo+0.007
Neg logit contributions
sc-0.096
nam-0.096
 ding-0.095
 counters-0.095
 pans-0.095
Token.
Token ID13
Feature activation-7.12e-06

Pos logit contributions
zag+0.557
oot+0.535
uzz+0.504
seek+0.488
gy+0.474
Neg logit contributions
nam-0.462
 pans-0.460
 ding-0.457
 counters-0.448
 forward-0.447
Token Mia
Token ID32189
Feature activation-8.45e-01

Feature not active on prev token;
no predictions were affected.
Token was
Token ID373
Feature activation-4.67e-01

Pos logit contributions
zag+0.051
oot+0.050
uzz+0.047
seek+0.045
ippy+0.043
Neg logit contributions
 ding-0.035
 pans-0.035
 counters-0.035
 y-0.035
nam-0.034
Token so
Token ID523
Feature activation+5.63e-01

Pos logit contributions
zag+0.032
oot+0.030
uzz+0.029
seek+0.029
 sometime+0.028
Neg logit contributions
 pans-0.017
nam-0.017
 counters-0.016
 ding-0.016
 forward-0.015
Token happy
Token ID3772
Feature activation+2.90e-01

Pos logit contributions
 pans+0.025
 counters+0.025
nam+0.023
 spec+0.023
sc+0.023
Neg logit contributions
zag-0.035
uzz-0.033
oot-0.032
seek-0.031
 sometime-0.030
Token played
Token ID2826
Feature activation-3.24e+00

Pos logit contributions
zag+0.039
uzz+0.036
gy+0.035
oot+0.034
 sometime+0.033
Neg logit contributions
 pans-0.043
nam-0.042
 counters-0.041
 ding-0.041
 spec-0.040
Token hide
Token ID7808
Feature activation-1.06e+00

Pos logit contributions
zag+0.181
oot+0.168
uzz+0.163
seek+0.159
 sometime+0.154
Neg logit contributions
nam-0.159
 pans-0.157
 ding-0.156
 counters-0.152
 forward-0.149
Token-
Token ID12
Feature activation-1.10e+00

Pos logit contributions
zag+0.053
oot+0.049
uzz+0.047
seek+0.046
 sometime+0.044
Neg logit contributions
 pans-0.058
nam-0.057
 ding-0.057
 counters-0.056
 forward-0.056
Tokenand
Token ID392
Feature activation+2.06e+00

Pos logit contributions
zag+0.067
oot+0.064
seek+0.064
uzz+0.060
gy+0.057
Neg logit contributions
nam-0.051
 pans-0.050
 ding-0.049
 counters-0.048
 spec-0.047
Token-
Token ID12
Feature activation-1.12e+00

Pos logit contributions
nam+0.131
 ding+0.128
 pans+0.126
 counters+0.124
 ju+0.122
Neg logit contributions
zag-0.088
oot-0.083
uzz-0.075
seek-0.075
gy-0.071
Tokenseek
Token ID36163
Feature activation-9.84e+00

Pos logit contributions
zag+0.024
oot+0.020
uzz+0.018
seek+0.017
 sometime+0.014
Neg logit contributions
nam-0.094
 pans-0.094
 ding-0.093
 counters-0.092
 forward-0.091
Token and
Token ID290
Feature activation-4.27e-01

Pos logit contributions
zag+0.516
oot+0.481
uzz+0.464
seek+0.451
 sometime+0.434
Neg logit contributions
nam-0.508
 pans-0.507
 ding-0.504
 counters-0.494
 forward-0.485
Token had
Token ID550
Feature activation-1.61e+00

Pos logit contributions
zag+0.022
oot+0.020
uzz+0.020
seek+0.019
 sometime+0.018
Neg logit contributions
nam-0.023
 pans-0.023
 ding-0.023
 counters-0.022
 forward-0.022
Token a
Token ID257
Feature activation+4.00e-01

Pos logit contributions
zag+0.103
oot+0.097
uzz+0.094
seek+0.092
 sometime+0.089
Neg logit contributions
nam-0.066
 pans-0.066
 ding-0.065
 counters-0.063
 forward-0.062
Token grand
Token ID4490
Feature activation+1.65e+00

Pos logit contributions
nam+0.015
 pans+0.015
 counters+0.015
 ding+0.015
 forward+0.013
Neg logit contributions
zag-0.027
uzz-0.024
oot-0.024
 sometime-0.024
gy-0.023
Token time
Token ID640
Feature activation+2.42e+00

Pos logit contributions
 ding+0.096
 counters+0.095
 pans+0.095
 forward+0.092
 y+0.092
Neg logit contributions
zag-0.077
oot-0.070
uzz-0.069
seek-0.065
 sometime-0.063
Token like
Token ID588
Feature activation+3.82e-01

Pos logit contributions
zag+0.031
oot+0.028
uzz+0.027
seek+0.027
 sometime+0.025
Neg logit contributions
nam-0.036
 pans-0.035
 ding-0.035
 counters-0.035
 forward-0.034
Token hide
Token ID7808
Feature activation-1.14e+00

Pos logit contributions
nam+0.022
 pans+0.022
 counters+0.021
 ding+0.021
 forward+0.021
Neg logit contributions
zag-0.018
oot-0.017
uzz-0.016
seek-0.016
 sometime-0.015
Token-
Token ID12
Feature activation-1.19e+00

Pos logit contributions
zag+0.059
oot+0.055
uzz+0.053
seek+0.052
 sometime+0.049
Neg logit contributions
 pans-0.061
nam-0.059
 ding-0.059
 counters-0.059
 y-0.058
Tokenand
Token ID392
Feature activation+2.05e+00

Pos logit contributions
zag+0.077
oot+0.073
seek+0.071
uzz+0.070
gy+0.066
Neg logit contributions
nam-0.049
 ding-0.048
 pans-0.048
 counters-0.047
 forward-0.045
Token-
Token ID12
Feature activation-1.20e+00

Pos logit contributions
nam+0.128
 ding+0.126
 pans+0.123
 counters+0.122
 forward+0.122
Neg logit contributions
zag-0.089
oot-0.083
seek-0.077
uzz-0.076
gy-0.072
Tokenseek
Token ID36163
Feature activation-9.82e+00

Pos logit contributions
zag+0.013
oot+0.009
uzz+0.008
 sometime+0.006
gy+0.003
Neg logit contributions
nam-0.108
 pans-0.108
 ding-0.107
 counters-0.106
 forward-0.106
Token and
Token ID290
Feature activation-6.38e-01

Pos logit contributions
zag+0.537
oot+0.513
uzz+0.487
seek+0.470
gy+0.454
Neg logit contributions
 pans-0.480
nam-0.478
 ding-0.476
 counters-0.467
 forward-0.463
Token tag
Token ID7621
Feature activation-2.37e+00

Pos logit contributions
zag+0.032
oot+0.029
uzz+0.028
seek+0.027
 sometime+0.026
Neg logit contributions
 pans-0.035
nam-0.035
 ding-0.035
 counters-0.035
 forward-0.034
Token.
Token ID13
Feature activation-9.52e-01

Pos logit contributions
zag+0.123
oot+0.115
uzz+0.111
seek+0.108
 sometime+0.103
Neg logit contributions
nam-0.124
 pans-0.124
 ding-0.123
 counters-0.121
 forward-0.119
Token One
Token ID1881
Feature activation-4.37e+00

Pos logit contributions
zag+0.051
oot+0.049
uzz+0.045
seek+0.045
gy+0.042
Neg logit contributions
nam-0.048
 ding-0.048
 pans-0.048
 counters-0.047
 forward-0.046
Token day
Token ID1110
Feature activation-3.28e-01

Pos logit contributions
zag+0.282
oot+0.277
uzz+0.267
seek+0.264
 sometime+0.250
Neg logit contributions
 ding-0.165
 pans-0.165
 y-0.159
 forward-0.159
nam-0.159
Token of
Token ID286
Feature activation+2.89e+00

Pos logit contributions
zag+0.230
oot+0.212
uzz+0.211
gy+0.204
seek+0.200
Neg logit contributions
 forward-0.168
nam-0.165
 pans-0.165
sc-0.164
 y-0.161
Token hide
Token ID7808
Feature activation-1.02e+00

Pos logit contributions
nam+0.142
 pans+0.141
 ding+0.139
 y+0.137
 counters+0.136
Neg logit contributions
zag-0.164
oot-0.155
uzz-0.149
seek-0.144
gy-0.142
Token-
Token ID12
Feature activation-1.14e+00

Pos logit contributions
zag+0.058
oot+0.053
seek+0.051
uzz+0.050
 sometime+0.048
Neg logit contributions
 pans-0.051
nam-0.050
 counters-0.049
 forward-0.049
 ding-0.048
Tokenand
Token ID392
Feature activation+2.06e+00

Pos logit contributions
zag+0.075
oot+0.072
uzz+0.069
seek+0.068
 sometime+0.066
Neg logit contributions
nam-0.044
 pans-0.044
 ding-0.044
 counters-0.043
 forward-0.041
Token-
Token ID12
Feature activation-1.15e+00

Pos logit contributions
 pans+0.118
nam+0.118
 ding+0.117
 counters+0.115
 forward+0.113
Neg logit contributions
zag-0.098
oot-0.090
uzz-0.087
seek-0.083
 sometime-0.081
Tokenseek
Token ID36163
Feature activation-9.82e+00

Pos logit contributions
zag+0.016
uzz+0.011
oot+0.011
 sometime+0.008
gy+0.007
Neg logit contributions
nam-0.101
 counters-0.100
 ding-0.100
 pans-0.100
 forward-0.099
Token,
Token ID11
Feature activation-8.16e-01

Pos logit contributions
zag+0.543
oot+0.514
uzz+0.488
seek+0.474
gy+0.460
Neg logit contributions
 pans-0.479
nam-0.479
 ding-0.470
 counters-0.467
 forward-0.461
Token so
Token ID523
Feature activation+4.24e-01

Pos logit contributions
zag+0.045
oot+0.042
uzz+0.041
 sometime+0.040
seek+0.040
Neg logit contributions
 pans-0.038
nam-0.038
 ding-0.037
 counters-0.036
 forward-0.036
Token she
Token ID673
Feature activation+9.86e-01

Pos logit contributions
nam+0.015
 pans+0.015
 ding+0.015
 counters+0.014
 forward+0.014
Neg logit contributions
zag-0.030
oot-0.028
uzz-0.027
seek-0.027
 sometime-0.026
Token decided
Token ID3066
Feature activation+7.19e-01

Pos logit contributions
 pans+0.037
nam+0.036
 y+0.036
 counters+0.036
 ding+0.035
Neg logit contributions
zag-0.065
oot-0.063
uzz-0.060
seek-0.059
ippy-0.057
Token to
Token ID284
Feature activation-1.36e+00

Pos logit contributions
nam+0.032
 forward+0.032
 ding+0.031
 pans+0.031
 y+0.030
Neg logit contributions
zag-0.042
uzz-0.040
oot-0.038
ippy-0.038
gy-0.037
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
zag+0.121
oot+0.114
uzz+0.110
seek+0.106
 sometime+0.102
Neg logit contributions
 ding-0.129
 pans-0.129
nam-0.128
 counters-0.126
 forward-0.125
Token hide
Token ID7808
Feature activation-1.11e+00

Pos logit contributions
zag+0.055
oot+0.049
seek+0.048
uzz+0.047
 sometime+0.045
Neg logit contributions
nam-0.053
 pans-0.053
 ding-0.053
 counters-0.052
 forward-0.052
Token-
Token ID12
Feature activation-1.12e+00

Pos logit contributions
zag+0.056
oot+0.052
uzz+0.050
seek+0.049
 sometime+0.047
Neg logit contributions
 pans-0.060
nam-0.059
 ding-0.059
 counters-0.058
 forward-0.057
Tokenand
Token ID392
Feature activation+2.06e+00

Pos logit contributions
zag+0.072
oot+0.068
seek+0.067
uzz+0.065
gy+0.061
Neg logit contributions
nam-0.048
 pans-0.048
 ding-0.047
 counters-0.046
 forward-0.044
Token-
Token ID12
Feature activation-1.16e+00

Pos logit contributions
nam+0.124
 ding+0.123
 pans+0.122
 counters+0.120
 forward+0.118
Neg logit contributions
zag-0.093
oot-0.086
uzz-0.081
seek-0.079
gy-0.075
Tokenseek
Token ID36163
Feature activation-9.81e+00

Pos logit contributions
zag+0.013
oot+0.008
uzz+0.007
 sometime+0.004
seek+0.004
Neg logit contributions
nam-0.107
 ding-0.107
 pans-0.106
 counters-0.105
 forward-0.105
Token,
Token ID11
Feature activation-8.77e-01

Pos logit contributions
zag+0.498
oot+0.463
uzz+0.447
seek+0.433
 sometime+0.416
Neg logit contributions
nam-0.524
 pans-0.523
 ding-0.520
 counters-0.510
 forward-0.500
Token and
Token ID290
Feature activation-4.03e-01

Pos logit contributions
zag+0.036
oot+0.030
seek+0.030
uzz+0.029
gy+0.028
Neg logit contributions
nam-0.056
 pans-0.055
 ding-0.054
 counters-0.054
 forward-0.052
Token even
Token ID772
Feature activation-2.97e+00

Pos logit contributions
zag+0.020
oot+0.019
uzz+0.018
seek+0.018
 sometime+0.017
Neg logit contributions
 pans-0.022
 ding-0.021
nam-0.021
 counters-0.021
 forward-0.021
Token a
Token ID257
Feature activation+2.63e-01

Pos logit contributions
zag+0.156
seek+0.139
oot+0.138
uzz+0.137
 sometime+0.137
Neg logit contributions
 pans-0.155
 counters-0.155
 ding-0.152
nam-0.147
 forward-0.144
Token game
Token ID983
Feature activation-3.85e+00

Pos logit contributions
nam+0.011
 counters+0.011
 pans+0.011
 ding+0.011
 forward+0.011
Neg logit contributions
zag-0.016
uzz-0.014
 sometime-0.014
oot-0.014
seek-0.013
Token playing
Token ID2712
Feature activation-1.46e+00

Pos logit contributions
 pans+0.062
nam+0.061
 counters+0.060
 ding+0.059
 ju+0.058
Neg logit contributions
zag-0.049
oot-0.044
uzz-0.042
gy-0.040
seek-0.040
Token hide
Token ID7808
Feature activation-1.09e+00

Pos logit contributions
zag+0.101
oot+0.099
uzz+0.095
seek+0.091
ogo+0.090
Neg logit contributions
 pans-0.052
 y-0.052
 ding-0.051
nam-0.051
 forward-0.051
Token-
Token ID12
Feature activation-1.18e+00

Pos logit contributions
zag+0.061
oot+0.057
uzz+0.054
seek+0.054
 sometime+0.051
Neg logit contributions
 pans-0.056
nam-0.054
 counters-0.054
 ding-0.053
 forward-0.052
Tokenand
Token ID392
Feature activation+2.12e+00

Pos logit contributions
zag+0.079
oot+0.075
uzz+0.073
seek+0.072
gy+0.068
Neg logit contributions
nam-0.045
 pans-0.045
 ding-0.045
 counters-0.043
 forward-0.042
Token-
Token ID12
Feature activation-1.20e+00

Pos logit contributions
nam+0.123
 pans+0.123
 ding+0.122
 counters+0.120
 forward+0.118
Neg logit contributions
zag-0.100
oot-0.092
uzz-0.088
seek-0.085
 sometime-0.082
Tokenseek
Token ID36163
Feature activation-9.76e+00

Pos logit contributions
zag+0.016
uzz+0.012
oot+0.012
 sometime+0.009
ogo+0.008
Neg logit contributions
nam-0.104
 counters-0.103
sc-0.103
 pans-0.103
 ding-0.102
Token.
Token ID13
Feature activation-5.03e-01

Pos logit contributions
zag+0.574
oot+0.546
uzz+0.522
seek+0.507
gy+0.490
Neg logit contributions
nam-0.440
 pans-0.439
 ding-0.434
 counters-0.427
 forward-0.422
Token Sammy
Token ID44067
Feature activation-1.05e+00

Pos logit contributions
zag+0.029
oot+0.028
uzz+0.027
seek+0.026
 sometime+0.025
Neg logit contributions
nam-0.023
 pans-0.023
 ding-0.023
 counters-0.022
 forward-0.022
Token was
Token ID373
Feature activation-8.28e-01

Pos logit contributions
zag+0.065
oot+0.062
uzz+0.061
seek+0.058
 sometime+0.056
Neg logit contributions
 pans-0.044
 ding-0.043
 counters-0.043
nam-0.043
 y-0.042
Token hiding
Token ID11816
Feature activation-5.04e+00

Pos logit contributions
zag+0.054
oot+0.051
uzz+0.049
seek+0.048
 sometime+0.047
Neg logit contributions
nam-0.033
 ding-0.033
 pans-0.032
 counters-0.032
 forward-0.031
Token behind
Token ID2157
Feature activation+1.29e+00

Pos logit contributions
zag+0.367
oot+0.356
seek+0.343
uzz+0.331
 sometime+0.322
Neg logit contributions
 pans-0.166
 forward-0.165
nam-0.164
 ding-0.154
 y-0.153
Token play
Token ID711
Feature activation-4.64e+00

Pos logit contributions
zag+0.081
oot+0.077
uzz+0.076
seek+0.070
ogo+0.068
Neg logit contributions
 pans-0.077
nam-0.076
 y-0.075
 ding-0.074
 counters-0.074
Token hide
Token ID7808
Feature activation-1.29e+00

Pos logit contributions
zag+0.342
uzz+0.329
oot+0.326
seek+0.305
ogo+0.301
Neg logit contributions
 pans-0.149
 ding-0.146
 y-0.145
 counters-0.144
nam-0.140
Token-
Token ID12
Feature activation-1.12e+00

Pos logit contributions
zag+0.070
oot+0.063
uzz+0.062
seek+0.060
 sometime+0.058
Neg logit contributions
 pans-0.068
nam-0.066
 counters-0.066
 ding-0.064
 y-0.063
Tokenand
Token ID392
Feature activation+2.17e+00

Pos logit contributions
zag+0.075
oot+0.071
uzz+0.069
seek+0.068
gy+0.066
Neg logit contributions
nam-0.041
 pans-0.041
 ding-0.041
 counters-0.040
 forward-0.039
Token-
Token ID12
Feature activation-1.12e+00

Pos logit contributions
nam+0.128
 pans+0.127
 ding+0.127
 counters+0.124
 forward+0.122
Neg logit contributions
zag-0.099
oot-0.092
uzz-0.088
seek-0.085
 sometime-0.081
Tokenseek
Token ID36163
Feature activation-9.75e+00

Pos logit contributions
zag+0.016
 sometime+0.013
uzz+0.013
oot+0.012
ogo+0.010
Neg logit contributions
nam-0.094
 counters-0.093
 forward-0.092
sc-0.092
 ding-0.092
Token with
Token ID351
Feature activation-5.38e-01

Pos logit contributions
zag+0.623
oot+0.600
uzz+0.564
seek+0.546
gy+0.539
Neg logit contributions
nam-0.406
 pans-0.400
 ding-0.387
 y-0.384
 counters-0.383
Token her
Token ID607
Feature activation-7.10e-01

Pos logit contributions
zag+0.032
oot+0.030
uzz+0.028
seek+0.028
 sometime+0.027
Neg logit contributions
nam-0.026
 pans-0.026
 ding-0.025
 counters-0.025
 y-0.024
Token friends
Token ID2460
Feature activation-3.23e+00

Pos logit contributions
zag+0.035
oot+0.034
uzz+0.032
seek+0.031
 sometime+0.030
Neg logit contributions
nam-0.040
 pans-0.040
 y-0.038
 ding-0.038
 counters-0.038
Token.
Token ID13
Feature activation-9.98e-01

Pos logit contributions
zag+0.166
oot+0.154
uzz+0.149
seek+0.144
 sometime+0.139
Neg logit contributions
 pans-0.173
nam-0.173
 ding-0.172
 counters-0.169
 forward-0.164
Token One
Token ID1881
Feature activation-4.51e+00

Pos logit contributions
zag+0.048
oot+0.044
uzz+0.042
seek+0.041
gy+0.039
Neg logit contributions
nam-0.057
 pans-0.056
 ding-0.056
 counters-0.056
 forward-0.055
Token played
Token ID2826
Feature activation-3.16e+00

Pos logit contributions
zag+0.043
oot+0.041
seek+0.039
uzz+0.038
ippy+0.037
Neg logit contributions
nam-0.032
 pans-0.029
 ding-0.028
 y-0.028
 forward-0.028
Token hide
Token ID7808
Feature activation-1.01e+00

Pos logit contributions
zag+0.212
oot+0.208
uzz+0.205
seek+0.194
ogo+0.189
Neg logit contributions
 y-0.117
sc-0.111
 ding-0.109
 forward-0.107
 pans-0.106
Token-
Token ID12
Feature activation-1.01e+00

Pos logit contributions
zag+0.057
oot+0.053
seek+0.051
uzz+0.051
 sometime+0.049
Neg logit contributions
 pans-0.050
nam-0.048
 counters-0.048
 y-0.047
 ding-0.047
Tokenand
Token ID392
Feature activation+2.20e+00

Pos logit contributions
zag+0.068
oot+0.065
uzz+0.063
seek+0.062
 sometime+0.060
Neg logit contributions
nam-0.037
 pans-0.037
 ding-0.036
 counters-0.035
 forward-0.034
Token-
Token ID12
Feature activation-1.04e+00

Pos logit contributions
 pans+0.125
nam+0.125
 ding+0.123
 counters+0.122
 forward+0.119
Neg logit contributions
zag-0.104
oot-0.095
uzz-0.093
seek-0.089
 sometime-0.087
Tokenseek
Token ID36163
Feature activation-9.73e+00

Pos logit contributions
zag+0.015
uzz+0.012
 sometime+0.011
oot+0.010
ogo+0.009
Neg logit contributions
sc-0.088
nam-0.087
 counters-0.086
 ding-0.086
 forward-0.085
Token,
Token ID11
Feature activation-7.44e-01

Pos logit contributions
zag+0.569
oot+0.557
uzz+0.522
seek+0.499
ogo+0.493
Neg logit contributions
nam-0.426
 pans-0.425
 ding-0.424
 y-0.422
 forward-0.419
Token tag
Token ID7621
Feature activation-2.18e+00

Pos logit contributions
zag+0.037
oot+0.033
uzz+0.032
seek+0.031
gy+0.031
Neg logit contributions
 pans-0.041
nam-0.040
 ding-0.040
 counters-0.040
 forward-0.039
Token,
Token ID11
Feature activation-6.69e-01

Pos logit contributions
zag+0.112
oot+0.107
uzz+0.102
seek+0.097
 sometime+0.095
Neg logit contributions
 pans-0.113
 ding-0.112
nam-0.112
 counters-0.110
 forward-0.108
Token and
Token ID290
Feature activation-4.27e-01

Pos logit contributions
zag+0.029
oot+0.026
uzz+0.025
seek+0.024
gy+0.023
Neg logit contributions
nam-0.041
 pans-0.041
 ding-0.041
 counters-0.040
 forward-0.040
Token other
Token ID584
Feature activation+4.49e-01

Pos logit contributions
zag+0.022
oot+0.020
uzz+0.019
seek+0.019
 sometime+0.018
Neg logit contributions
nam-0.023
 pans-0.023
 ding-0.023
 counters-0.022
 forward-0.022
Token finally
Token ID3443
Feature activation-3.92e+00

Pos logit contributions
zag+0.025
oot+0.023
uzz+0.022
seek+0.022
gy+0.021
Neg logit contributions
 ding-0.028
nam-0.028
 pans-0.028
 forward-0.027
 counters-0.027
Token,
Token ID11
Feature activation-5.77e-01

Pos logit contributions
zag+0.235
uzz+0.220
oot+0.212
seek+0.203
ogo+0.203
Neg logit contributions
 forward-0.177
 ding-0.172
 y-0.161
nam-0.159
 spec-0.155
Token the
Token ID262
Feature activation+5.62e-01

Pos logit contributions
zag+0.032
oot+0.030
uzz+0.029
seek+0.028
 sometime+0.028
Neg logit contributions
 pans-0.028
nam-0.028
 ding-0.028
 counters-0.027
 forward-0.026
Token z
Token ID1976
Feature activation-2.45e+00

Pos logit contributions
nam+0.027
 pans+0.026
 counters+0.026
 ding+0.026
 forward+0.025
Neg logit contributions
zag-0.031
oot-0.027
uzz-0.027
 sometime-0.026
seek-0.026
Tokenig
Token ID328
Feature activation-6.83e+00

Pos logit contributions
gy+0.074
zag+0.074
uzz+0.074
seek+0.073
oot+0.069
Neg logit contributions
 forward-0.165
 ding-0.161
 spec-0.155
 pans-0.149
 brightest-0.147
Tokenzag
Token ID50183
Feature activation-9.73e+00

Pos logit contributions
uzz+0.371
oot+0.369
zag+0.365
seek+0.356
 sometime+0.343
Neg logit contributions
 ding-0.302
 pans-0.294
 counters-0.292
 forward-0.290
 y-0.276
Token had
Token ID550
Feature activation-1.52e+00

Pos logit contributions
zag+0.538
oot+0.513
uzz+0.500
seek+0.483
 sometime+0.465
Neg logit contributions
 ding-0.461
 pans-0.458
nam-0.455
 counters-0.449
 forward-0.440
Token an
Token ID281
Feature activation-1.16e+00

Pos logit contributions
zag+0.093
oot+0.087
uzz+0.085
ippy+0.081
seek+0.079
Neg logit contributions
 y-0.068
 ding-0.067
nam-0.066
 counters-0.065
 ju-0.065
Token idea
Token ID2126
Feature activation-2.74e+00

Pos logit contributions
zag+0.078
uzz+0.072
oot+0.071
seek+0.071
gy+0.068
Neg logit contributions
nam-0.044
 ding-0.044
 forward-0.042
 y-0.042
 counters-0.042
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
zag+0.146
oot+0.134
uzz+0.130
seek+0.128
gy+0.123
Neg logit contributions
 pans-0.138
 ding-0.138
nam-0.137
 counters-0.136
 forward-0.135
Token It
Token ID632
Feature activation-1.46e+00

Pos logit contributions
zag+0.008
oot+0.007
uzz+0.007
seek+0.007
 sometime+0.007
Neg logit contributions
 pans-0.006
nam-0.006
 ding-0.006
 counters-0.006
 forward-0.006
Token would
Token ID561
Feature activation+1.73e+00

Pos logit contributions
nam+0.034
 forward+0.033
 ding+0.032
 pans+0.032
 y+0.031
Neg logit contributions
zag-0.054
oot-0.051
seek-0.049
uzz-0.049
ippy-0.047
Token splash
Token ID22870
Feature activation-1.95e+00

Pos logit contributions
 y+0.072
 ding+0.070
 forward+0.069
 neat+0.065
 low+0.065
Neg logit contributions
oot-0.102
zag-0.101
seek-0.099
uzz-0.094
ippy-0.092
Token and
Token ID290
Feature activation-3.67e-01

Pos logit contributions
zag+0.138
oot+0.131
seek+0.126
uzz+0.125
ippy+0.120
Neg logit contributions
 pans-0.069
nam-0.068
 ding-0.068
 forward-0.067
 y-0.065
Token z
Token ID1976
Feature activation-2.49e+00

Pos logit contributions
zag+0.017
oot+0.016
uzz+0.015
seek+0.015
 sometime+0.014
Neg logit contributions
nam-0.021
 pans-0.021
 ding-0.021
 counters-0.020
 forward-0.020
Tokenig
Token ID328
Feature activation-6.56e+00

Pos logit contributions
zag+0.129
seek+0.124
gy+0.122
 sometime+0.119
 mistake+0.113
Neg logit contributions
 forward-0.121
 ding-0.104
 pans-0.100
sc-0.099
 y-0.097
Tokenzag
Token ID50183
Feature activation-9.73e+00

Pos logit contributions
 sometime+0.251
uzz+0.247
oot+0.246
zag+0.246
seek+0.240
Neg logit contributions
 pans-0.373
 forward-0.372
 ding-0.372
 counters-0.359
 y-0.351
Token in
Token ID287
Feature activation+4.26e-01

Pos logit contributions
zag+0.603
oot+0.576
uzz+0.557
seek+0.543
 sometime+0.526
Neg logit contributions
 ding-0.399
 pans-0.398
nam-0.396
 counters-0.386
 forward-0.382
Token the
Token ID262
Feature activation+2.86e-01

Pos logit contributions
nam+0.015
 y+0.015
 pans+0.015
 forward+0.015
 ding+0.014
Neg logit contributions
zag-0.031
oot-0.030
seek-0.028
ogo-0.027
uzz-0.027
Token water
Token ID1660
Feature activation+2.27e+00

Pos logit contributions
nam+0.015
 pans+0.014
 ding+0.014
 counters+0.013
 forward+0.013
Neg logit contributions
zag-0.015
oot-0.013
gy-0.013
uzz-0.013
seek-0.013
Token together
Token ID1978
Feature activation-2.80e+00

Pos logit contributions
nam+0.124
 pans+0.124
 ding+0.123
 counters+0.121
 forward+0.117
Neg logit contributions
zag-0.113
oot-0.105
uzz-0.101
seek-0.098
 sometime-0.095
Token.
Token ID13
Feature activation-4.12e-01

Pos logit contributions
zag+0.138
oot+0.128
uzz+0.123
seek+0.119
 sometime+0.116
Neg logit contributions
 pans-0.155
nam-0.155
 ding-0.154
 counters-0.152
 forward-0.145
Token playing
Token ID2712
Feature activation-1.36e+00

Pos logit contributions
 pans+0.071
nam+0.069
 counters+0.068
 ding+0.067
 ju+0.066
Neg logit contributions
zag-0.049
oot-0.043
gy-0.041
uzz-0.040
seek-0.039
Token hide
Token ID7808
Feature activation-9.43e-01

Pos logit contributions
zag+0.097
oot+0.095
uzz+0.092
ogo+0.088
seek+0.087
Neg logit contributions
 y-0.045
 pans-0.044
 ding-0.044
 counters-0.043
 forward-0.043
Token-
Token ID12
Feature activation-1.05e+00

Pos logit contributions
zag+0.053
oot+0.048
uzz+0.047
seek+0.046
 sometime+0.044
Neg logit contributions
 pans-0.049
 counters-0.047
nam-0.047
 ding-0.046
 forward-0.045
Tokenand
Token ID392
Feature activation+2.23e+00

Pos logit contributions
zag+0.071
oot+0.067
uzz+0.065
seek+0.064
 sometime+0.062
Neg logit contributions
nam-0.038
 pans-0.038
 ding-0.038
 counters-0.037
 forward-0.036
Token-
Token ID12
Feature activation-1.07e+00

Pos logit contributions
 pans+0.127
nam+0.126
 ding+0.125
 counters+0.123
 forward+0.121
Neg logit contributions
zag-0.107
oot-0.098
uzz-0.096
seek-0.091
 sometime-0.089
Tokenseek
Token ID36163
Feature activation-9.71e+00

Pos logit contributions
zag+0.015
uzz+0.013
oot+0.012
 sometime+0.011
ogo+0.010
Neg logit contributions
nam-0.091
sc-0.090
 counters-0.090
 ding-0.089
 pans-0.088
Token.
Token ID13
Feature activation-6.46e-01

Pos logit contributions
zag+0.587
oot+0.563
uzz+0.534
seek+0.516
gy+0.502
Neg logit contributions
nam-0.423
 pans-0.420
 ding-0.415
 counters-0.409
 forward-0.406
Token Tim
Token ID5045
Feature activation-1.74e+00

Pos logit contributions
zag+0.035
oot+0.032
uzz+0.031
seek+0.030
gy+0.030
Neg logit contributions
nam-0.033
 pans-0.033
 ding-0.033
 counters-0.032
 forward-0.032
Tokenmy
Token ID1820
Feature activation+8.64e-01

Pos logit contributions
zag+0.120
oot+0.119
uzz+0.118
seek+0.115
 sometime+0.106
Neg logit contributions
 counters-0.054
 pans-0.053
 ding-0.053
 y-0.052
 forward-0.051
Token was
Token ID373
Feature activation-7.59e-01

Pos logit contributions
 counters+0.031
 y+0.031
 pans+0.031
 ding+0.030
nam+0.029
Neg logit contributions
zag-0.057
oot-0.056
uzz-0.055
seek-0.052
ippy-0.050
Token hiding
Token ID11816
Feature activation-4.96e+00

Pos logit contributions
zag+0.049
oot+0.047
uzz+0.045
seek+0.044
 sometime+0.043
Neg logit contributions
nam-0.030
 ding-0.030
 pans-0.029
 forward-0.029
 counters-0.029
Tokenement
Token ID972
Feature activation+5.16e-01

Pos logit contributions
nam+0.175
 pans+0.174
 ding+0.173
 counters+0.168
 forward+0.164
Neg logit contributions
zag-0.302
oot-0.286
uzz-0.278
seek-0.272
 sometime-0.264
Token as
Token ID355
Feature activation-7.99e-01

Pos logit contributions
 pans+0.027
nam+0.027
 ding+0.027
 counters+0.027
 forward+0.026
Neg logit contributions
zag-0.026
oot-0.025
uzz-0.024
seek-0.023
 sometime-0.022
Token the
Token ID262
Feature activation+6.01e-01

Pos logit contributions
zag+0.035
uzz+0.033
oot+0.032
 sometime+0.030
seek+0.028
Neg logit contributions
 counters-0.047
 pans-0.046
nam-0.046
 ding-0.045
 ju-0.045
Token z
Token ID1976
Feature activation-2.35e+00

Pos logit contributions
nam+0.029
 forward+0.028
 counters+0.028
 pans+0.027
 ding+0.027
Neg logit contributions
zag-0.032
oot-0.029
uzz-0.028
ad-0.027
seek-0.026
Tokenig
Token ID328
Feature activation-6.72e+00

Pos logit contributions
uzz+0.080
 sometime+0.079
seek+0.079
zag+0.079
gy+0.074
Neg logit contributions
 ding-0.143
 forward-0.142
 spec-0.141
 pans-0.139
 de-0.134
Tokenzag
Token ID50183
Feature activation-9.70e+00

Pos logit contributions
zag+0.317
oot+0.305
uzz+0.302
seek+0.293
 sometime+0.283
Neg logit contributions
 pans-0.359
 ding-0.359
nam-0.348
 counters-0.348
 forward-0.346
Token soared
Token ID35292
Feature activation-3.49e-02

Pos logit contributions
zag+0.551
oot+0.510
uzz+0.490
seek+0.479
gy+0.463
Neg logit contributions
nam-0.470
 pans-0.466
 ding-0.459
 counters-0.453
 forward-0.442
Token in
Token ID287
Feature activation+5.08e-01

Pos logit contributions
zag+0.002
oot+0.002
uzz+0.002
seek+0.002
 sometime+0.002
Neg logit contributions
nam-0.001
 pans-0.001
 ding-0.001
 counters-0.001
 forward-0.001
Token the
Token ID262
Feature activation+4.79e-01

Pos logit contributions
 ding+0.020
 pans+0.019
 forward+0.019
nam+0.019
 y+0.018
Neg logit contributions
zag-0.034
oot-0.033
seek-0.031
uzz-0.030
ogo-0.029
Token sky
Token ID6766
Feature activation+1.50e+00

Pos logit contributions
nam+0.020
 pans+0.019
 counters+0.018
 forward+0.017
 stressed+0.016
Neg logit contributions
zag-0.031
oot-0.027
gy-0.027
ad-0.027
seek-0.027
Token.
Token ID13
Feature activation+1.94e-01

Pos logit contributions
nam+0.088
 pans+0.086
 counters+0.084
 ding+0.084
 forward+0.081
Neg logit contributions
zag-0.072
oot-0.065
uzz-0.063
seek-0.061
 sometime-0.060
Token playing
Token ID2712
Feature activation-1.39e+00

Pos logit contributions
 pans+0.129
 ding+0.128
nam+0.127
 counters+0.125
 forward+0.121
Neg logit contributions
zag-0.179
oot-0.170
uzz-0.164
seek-0.160
 sometime-0.156
Token hide
Token ID7808
Feature activation-9.50e-01

Pos logit contributions
zag+0.096
oot+0.091
uzz+0.089
seek+0.085
ogo+0.085
Neg logit contributions
 forward-0.049
 counters-0.048
 pans-0.048
 ding-0.048
nam-0.047
Token-
Token ID12
Feature activation-1.08e+00

Pos logit contributions
zag+0.051
oot+0.047
uzz+0.046
seek+0.045
 sometime+0.042
Neg logit contributions
nam-0.048
 pans-0.048
 forward-0.047
 counters-0.047
 ding-0.047
Tokenand
Token ID392
Feature activation+2.30e+00

Pos logit contributions
zag+0.070
oot+0.066
seek+0.064
uzz+0.064
gy+0.061
Neg logit contributions
 pans-0.045
nam-0.044
 ding-0.044
 counters-0.043
 forward-0.041
Token-
Token ID12
Feature activation-1.09e+00

Pos logit contributions
nam+0.136
 pans+0.136
 ding+0.136
 counters+0.133
 forward+0.129
Neg logit contributions
zag-0.106
oot-0.098
uzz-0.093
seek-0.091
gy-0.086
Tokenseek
Token ID36163
Feature activation-9.68e+00

Pos logit contributions
zag+0.013
oot+0.009
uzz+0.008
 sometime+0.005
ogo+0.004
Neg logit contributions
nam-0.099
 ding-0.098
 pans-0.097
 counters-0.097
 forward-0.097
Token with
Token ID351
Feature activation-2.14e-01

Pos logit contributions
zag+0.509
oot+0.475
uzz+0.458
seek+0.443
gy+0.425
Neg logit contributions
nam-0.499
 pans-0.496
 ding-0.494
 counters-0.485
 forward-0.480
Token her
Token ID607
Feature activation-3.57e-01

Pos logit contributions
zag+0.011
oot+0.011
uzz+0.010
seek+0.010
 sometime+0.010
Neg logit contributions
 ding-0.011
 pans-0.011
nam-0.011
 counters-0.011
 forward-0.010
Token friends
Token ID2460
Feature activation-2.97e+00

Pos logit contributions
zag+0.020
oot+0.018
uzz+0.018
seek+0.017
 sometime+0.016
Neg logit contributions
nam-0.018
 pans-0.018
 ding-0.017
 counters-0.017
 forward-0.017
Token.
Token ID13
Feature activation-3.88e-01

Pos logit contributions
zag+0.149
oot+0.139
uzz+0.134
seek+0.130
 sometime+0.124
Neg logit contributions
nam-0.160
 pans-0.159
 ding-0.158
 counters-0.155
 forward-0.153
Token<|endoftext|>
Token ID50256
Feature activation-4.54e-01

Pos logit contributions
zag+0.025
oot+0.023
uzz+0.022
seek+0.022
ogo+0.021
Neg logit contributions
 forward-0.015
nam-0.015
 ding-0.015
 counters-0.014
 pans-0.014
Token playing
Token ID2712
Feature activation-1.61e+00

Pos logit contributions
 pans+0.068
nam+0.065
 counters+0.065
 ju+0.064
 ding+0.064
Neg logit contributions
zag-0.059
oot-0.053
uzz-0.052
seek-0.050
gy-0.050
Token hide
Token ID7808
Feature activation-1.25e+00

Pos logit contributions
zag+0.106
oot+0.102
uzz+0.098
seek+0.094
ogo+0.091
Neg logit contributions
 pans-0.063
nam-0.063
 ding-0.062
 counters-0.061
 forward-0.061
Token-
Token ID12
Feature activation-1.08e+00

Pos logit contributions
zag+0.065
oot+0.060
uzz+0.058
seek+0.056
 sometime+0.054
Neg logit contributions
 pans-0.066
nam-0.066
 ding-0.065
 counters-0.065
 forward-0.064
Tokenand
Token ID392
Feature activation+2.18e+00

Pos logit contributions
zag+0.071
oot+0.067
seek+0.065
uzz+0.065
gy+0.061
Neg logit contributions
 pans-0.043
 ding-0.043
nam-0.043
 counters-0.041
 forward-0.040
Token-
Token ID12
Feature activation-1.09e+00

Pos logit contributions
nam+0.127
 pans+0.127
 ding+0.126
 counters+0.124
 forward+0.122
Neg logit contributions
zag-0.101
oot-0.093
uzz-0.089
seek-0.087
 sometime-0.082
Tokenseek
Token ID36163
Feature activation-9.68e+00

Pos logit contributions
zag+0.013
oot+0.010
uzz+0.010
 sometime+0.008
ogo+0.007
Neg logit contributions
nam-0.095
 counters-0.094
sc-0.094
 ding-0.094
 forward-0.094
Token behind
Token ID2157
Feature activation+1.08e+00

Pos logit contributions
zag+0.542
oot+0.511
uzz+0.491
seek+0.477
 sometime+0.459
Neg logit contributions
nam-0.467
 pans-0.465
 ding-0.461
 counters-0.453
 forward-0.445
Token the
Token ID262
Feature activation+2.55e-01

Pos logit contributions
nam+0.045
 pans+0.045
 counters+0.044
 ding+0.043
 y+0.042
Neg logit contributions
zag-0.069
oot-0.067
uzz-0.061
seek-0.060
ogo-0.058
Token old
Token ID1468
Feature activation+3.33e-01

Pos logit contributions
nam+0.011
 ding+0.011
 pans+0.011
 forward+0.010
 counters+0.010
Neg logit contributions
zag-0.016
oot-0.015
uzz-0.014
seek-0.014
gy-0.014
Token barn
Token ID25203
Feature activation+8.32e-01

Pos logit contributions
 pans+0.015
nam+0.015
 ding+0.014
 counters+0.014
 spec+0.013
Neg logit contributions
zag-0.020
oot-0.019
uzz-0.019
seek-0.018
 sometime-0.018
Token.
Token ID13
Feature activation-7.64e-01

Pos logit contributions
nam+0.046
 pans+0.046
 ding+0.045
 counters+0.044
 forward+0.044
Neg logit contributions
zag-0.041
oot-0.038
uzz-0.036
seek-0.036
gy-0.035
Token and
Token ID290
Feature activation+6.52e-01

Pos logit contributions
zag+0.172
oot+0.163
uzz+0.162
 sometime+0.155
gy+0.153
Neg logit contributions
 pans-0.125
 ding-0.125
 counters-0.125
nam-0.122
 forward-0.115
Token hide
Token ID7808
Feature activation-8.14e-01

Pos logit contributions
 pans+0.031
 ding+0.031
 counters+0.031
 forward+0.031
nam+0.030
Neg logit contributions
zag-0.035
uzz-0.032
oot-0.032
 sometime-0.030
seek-0.030
Token-
Token ID12
Feature activation-7.65e-01

Pos logit contributions
zag+0.051
oot+0.048
seek+0.046
uzz+0.045
 sometime+0.043
Neg logit contributions
 pans-0.036
nam-0.035
 counters-0.034
 ding-0.034
 forward-0.034
Tokenand
Token ID392
Feature activation+1.89e+00

Pos logit contributions
zag+0.050
oot+0.048
uzz+0.046
seek+0.046
 sometime+0.043
Neg logit contributions
nam-0.030
 pans-0.030
 ding-0.030
 counters-0.029
 forward-0.028
Token-
Token ID12
Feature activation-1.01e+00

Pos logit contributions
 pans+0.098
nam+0.098
 ding+0.097
 counters+0.096
 forward+0.095
Neg logit contributions
zag-0.098
oot-0.090
uzz-0.088
seek-0.084
 sometime-0.082
Tokenseek
Token ID36163
Feature activation-9.68e+00

Pos logit contributions
zag+0.020
oot+0.015
uzz+0.015
 sometime+0.012
gy+0.011
Neg logit contributions
nam-0.081
 ding-0.080
sc-0.080
 counters-0.080
 forward-0.079
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
zag+0.550
oot+0.531
uzz+0.498
seek+0.482
gy+0.471
Neg logit contributions
nam-0.446
 pans-0.445
 ding-0.442
 forward-0.436
 counters-0.435
Token The
Token ID383
Feature activation-1.29e+00

Pos logit contributions
nam+0.007
 pans+0.007
 ding+0.007
 counters+0.006
 forward+0.006
Neg logit contributions
zag-0.008
oot-0.008
uzz-0.008
seek-0.007
 sometime-0.007
Token monkey
Token ID21657
Feature activation-3.04e+00

Pos logit contributions
zag+0.071
oot+0.066
uzz+0.064
seek+0.062
 sometime+0.060
Neg logit contributions
nam-0.063
 pans-0.062
 ding-0.062
 counters-0.061
 forward-0.060
Token was
Token ID373
Feature activation-4.86e-01

Pos logit contributions
zag+0.180
oot+0.178
uzz+0.170
seek+0.163
ippy+0.158
Neg logit contributions
 ding-0.129
 pans-0.126
 counters-0.126
 y-0.126
nam-0.122
Token very
Token ID845
Feature activation+1.56e+00

Pos logit contributions
zag+0.035
oot+0.033
uzz+0.033
seek+0.032
 sometime+0.031
Neg logit contributions
 pans-0.016
nam-0.016
 ding-0.015
 counters-0.015
 forward-0.014
Token He
Token ID679
Feature activation-6.76e-01

Pos logit contributions
zag+0.040
seek+0.037
oot+0.037
uzz+0.035
gy+0.034
Neg logit contributions
 pans-0.045
nam-0.045
 ding-0.044
 forward-0.043
 counters-0.042
Token had
Token ID550
Feature activation-1.49e+00

Pos logit contributions
zag+0.043
oot+0.042
uzz+0.041
seek+0.040
ippy+0.039
Neg logit contributions
 pans-0.027
 ding-0.026
nam-0.026
 y-0.026
 counters-0.026
Token to
Token ID284
Feature activation-1.26e+00

Pos logit contributions
zag+0.082
oot+0.079
uzz+0.075
ippy+0.070
seek+0.069
Neg logit contributions
nam-0.074
 ding-0.074
 pans-0.073
 y-0.073
 counters-0.072
Token z
Token ID1976
Feature activation-2.40e+00

Pos logit contributions
zag+0.082
oot+0.079
uzz+0.076
seek+0.073
ogo+0.070
Neg logit contributions
 ding-0.051
nam-0.051
 pans-0.051
 counters-0.050
 y-0.049
Tokenig
Token ID328
Feature activation-6.49e+00

Pos logit contributions
gy+0.134
zag+0.131
seek+0.124
 sometime+0.121
onna+0.115
Neg logit contributions
 forward-0.128
 ding-0.106
 pans-0.094
nam-0.094
 counters-0.091
Tokenzag
Token ID50183
Feature activation-9.68e+00

Pos logit contributions
uzz+0.399
 sometime+0.396
oot+0.382
seek+0.380
zag+0.369
Neg logit contributions
 ding-0.240
 forward-0.240
 counters-0.219
 pans-0.218
nam-0.203
Token around
Token ID1088
Feature activation-2.47e-01

Pos logit contributions
zag+0.542
oot+0.534
uzz+0.515
seek+0.492
ippy+0.483
Neg logit contributions
 ding-0.444
 forward-0.432
 pans-0.428
nam-0.428
 counters-0.421
Token and
Token ID290
Feature activation-2.22e-01

Pos logit contributions
zag+0.014
oot+0.013
uzz+0.012
seek+0.012
 sometime+0.011
Neg logit contributions
 ding-0.012
nam-0.012
 pans-0.012
 counters-0.012
 forward-0.012
Token make
Token ID787
Feature activation-1.54e-01

Pos logit contributions
zag+0.012
oot+0.010
seek+0.010
uzz+0.010
 sometime+0.010
Neg logit contributions
 pans-0.012
nam-0.011
 ding-0.011
 counters-0.011
 forward-0.011
Token big
Token ID1263
Feature activation+2.18e+00

Pos logit contributions
zag+0.009
oot+0.008
uzz+0.008
seek+0.008
 sometime+0.008
Neg logit contributions
nam-0.007
 pans-0.007
 ding-0.007
 counters-0.007
 forward-0.007
Token circles
Token ID13332
Feature activation-6.96e-01

Pos logit contributions
nam+0.095
 pans+0.095
 ding+0.094
 counters+0.092
 forward+0.090
Neg logit contributions
zag-0.132
oot-0.125
uzz-0.121
seek-0.118
 sometime-0.114
Token porch
Token ID33179
Feature activation+1.32e+00

Pos logit contributions
nam+0.012
 forward+0.012
 ding+0.012
sc+0.012
 pans+0.012
Neg logit contributions
zag-0.013
gy-0.012
oot-0.011
uzz-0.011
seek-0.011
Token.
Token ID13
Feature activation+9.91e-02

Pos logit contributions
nam+0.077
 pans+0.077
 ding+0.074
 counters+0.072
 forward+0.071
Neg logit contributions
zag-0.063
oot-0.057
uzz-0.055
seek-0.054
gy-0.052
Token They
Token ID1119
Feature activation+1.53e-01

Pos logit contributions
nam+0.005
 pans+0.005
 ding+0.005
 counters+0.004
 forward+0.004
Neg logit contributions
zag-0.006
uzz-0.005
oot-0.005
seek-0.005
 sometime-0.005
Token both
Token ID1111
Feature activation-1.89e+00

Pos logit contributions
nam+0.006
 pans+0.006
 ding+0.006
 counters+0.006
 forward+0.006
Neg logit contributions
zag-0.010
oot-0.009
uzz-0.009
seek-0.009
gy-0.008
Token reached
Token ID4251
Feature activation+6.36e-01

Pos logit contributions
zag+0.115
oot+0.108
uzz+0.106
seek+0.102
 sometime+0.100
Neg logit contributions
 pans-0.083
nam-0.082
 ding-0.081
 counters-0.080
 forward-0.078
Token out
Token ID503
Feature activation+5.87e+00

Pos logit contributions
nam+0.020
 pans+0.020
 ding+0.020
 counters+0.019
 forward+0.019
Neg logit contributions
zag-0.047
oot-0.044
uzz-0.043
seek-0.043
 sometime-0.041
Token to
Token ID284
Feature activation-1.13e+00

Pos logit contributions
 forward+0.284
 ding+0.282
 pans+0.279
 y+0.274
nam+0.271
Neg logit contributions
zag-0.328
oot-0.308
seek-0.302
uzz-0.281
gy-0.279
Token touch
Token ID3638
Feature activation-6.58e-01

Pos logit contributions
zag+0.071
oot+0.067
seek+0.063
uzz+0.062
ogo+0.060
Neg logit contributions
nam-0.050
 pans-0.049
 ding-0.049
 y-0.047
 counters-0.046
Token them
Token ID606
Feature activation+3.63e-01

Pos logit contributions
zag+0.031
oot+0.029
uzz+0.029
 sometime+0.027
seek+0.026
Neg logit contributions
nam-0.037
 pans-0.037
 counters-0.036
 ding-0.036
 forward-0.034
Token,
Token ID11
Feature activation-4.23e-01

Pos logit contributions
 pans+0.021
nam+0.021
 ding+0.021
 counters+0.021
 forward+0.020
Neg logit contributions
zag-0.017
oot-0.016
uzz-0.015
seek-0.014
 sometime-0.014
Token feeling
Token ID4203
Feature activation-3.03e+00

Pos logit contributions
zag+0.020
uzz+0.019
oot+0.017
 sometime+0.017
seek+0.016
Neg logit contributions
 pans-0.024
nam-0.023
 counters-0.023
 ding-0.022
sc-0.021
Token to
Token ID284
Feature activation-1.60e+00

Pos logit contributions
zag+0.049
oot+0.045
uzz+0.043
seek+0.042
 sometime+0.041
Neg logit contributions
nam-0.045
 pans-0.045
 ding-0.044
 counters-0.044
 forward-0.041
Token prevent
Token ID2948
Feature activation+3.66e-01

Pos logit contributions
zag+0.089
oot+0.085
uzz+0.082
seek+0.079
ippy+0.076
Neg logit contributions
 ding-0.079
nam-0.078
 pans-0.078
 counters-0.076
 y-0.074
Token things
Token ID1243
Feature activation+9.14e-01

Pos logit contributions
nam+0.019
 pans+0.019
 ding+0.019
 counters+0.019
 ju+0.018
Neg logit contributions
zag-0.019
oot-0.018
uzz-0.017
seek-0.016
gy-0.016
Token from
Token ID422
Feature activation+6.70e-01

Pos logit contributions
nam+0.051
 pans+0.049
 ding+0.048
 counters+0.048
 spec+0.047
Neg logit contributions
zag-0.047
oot-0.044
seek-0.039
uzz-0.038
gy-0.038
Token getting
Token ID1972
Feature activation+6.90e-01

Pos logit contributions
nam+0.031
 pans+0.031
 ding+0.031
 counters+0.029
 forward+0.029
Neg logit contributions
zag-0.039
oot-0.037
uzz-0.036
seek-0.035
 sometime-0.033
Token out
Token ID503
Feature activation+5.28e+00

Pos logit contributions
 counters+0.033
 pans+0.033
nam+0.033
 ding+0.032
 spec+0.032
Neg logit contributions
zag-0.036
oot-0.034
uzz-0.032
seek-0.031
gy-0.031
Token of
Token ID286
Feature activation+2.66e+00

Pos logit contributions
nam+0.253
 ding+0.249
 pans+0.249
 counters+0.241
 forward+0.234
Neg logit contributions
zag-0.297
oot-0.277
uzz-0.269
seek-0.260
 sometime-0.255
Token hand
Token ID1021
Feature activation+3.18e+00

Pos logit contributions
 pans+0.128
nam+0.128
 ding+0.127
 counters+0.124
 forward+0.122
Neg logit contributions
zag-0.151
oot-0.142
uzz-0.136
seek-0.134
 sometime-0.127
Token.
Token ID13
Feature activation-6.90e-01

Pos logit contributions
nam+0.201
 ding+0.192
 pans+0.185
 brightest+0.181
 forward+0.181
Neg logit contributions
zag-0.135
oot-0.123
gy-0.116
seek-0.115
uzz-0.110
Token Every
Token ID3887
Feature activation-1.44e+00

Pos logit contributions
zag+0.041
oot+0.039
uzz+0.037
seek+0.037
 sometime+0.035
Neg logit contributions
nam-0.031
 pans-0.031
 ding-0.031
 counters-0.030
 forward-0.029
Token day
Token ID1110
Feature activation-7.90e-01

Pos logit contributions
zag+0.087
oot+0.082
uzz+0.080
seek+0.078
 sometime+0.075
Neg logit contributions
nam-0.063
 pans-0.062
 ding-0.062
 counters-0.061
 forward-0.059
Token for
Token ID329
Feature activation-8.35e-01

Pos logit contributions
 pans+0.087
nam+0.086
 ding+0.085
 forward+0.084
 counters+0.084
Neg logit contributions
zag-0.093
oot-0.087
uzz-0.084
seek-0.082
 sometime-0.078
Token this
Token ID428
Feature activation-1.85e+00

Pos logit contributions
zag+0.057
oot+0.053
uzz+0.052
seek+0.051
gy+0.049
Neg logit contributions
nam-0.031
 pans-0.031
 ding-0.031
 counters-0.029
 forward-0.029
Token.
Token ID13
Feature activation+3.66e-01

Pos logit contributions
zag+0.098
oot+0.090
uzz+0.086
 sometime+0.084
seek+0.084
Neg logit contributions
nam-0.096
 pans-0.095
 ding-0.094
 counters-0.093
 forward-0.090
Token It
Token ID632
Feature activation-6.41e-01

Pos logit contributions
 pans+0.017
nam+0.017
 counters+0.016
 ding+0.016
 y+0.015
Neg logit contributions
zag-0.021
uzz-0.021
oot-0.020
 sometime-0.019
seek-0.019
Token's
Token ID338
Feature activation+1.18e+00

Pos logit contributions
zag+0.038
oot+0.034
gy+0.033
uzz+0.033
 sometime+0.032
Neg logit contributions
nam-0.032
 pans-0.029
 ding-0.029
 counters-0.029
 forward-0.029
Token called
Token ID1444
Feature activation+5.46e+00

Pos logit contributions
 counters+0.062
 ding+0.061
 pans+0.060
 spec+0.060
nam+0.060
Neg logit contributions
zag-0.059
uzz-0.055
oot-0.054
 sometime-0.052
gy-0.051
Token a
Token ID257
Feature activation+8.38e-01

Pos logit contributions
nam+0.280
 pans+0.276
 counters+0.274
 ding+0.271
 spec+0.265
Neg logit contributions
zag-0.282
oot-0.268
uzz-0.263
gy-0.241
 sometime-0.240
Token net
Token ID2010
Feature activation+9.51e-01

Pos logit contributions
 counters+0.044
nam+0.044
 spec+0.041
 pans+0.040
 forward+0.040
Neg logit contributions
zag-0.044
 sometime-0.036
oot-0.035
gy-0.035
uzz-0.034
Token."
Token ID526
Feature activation-7.13e-01

Pos logit contributions
nam+0.052
 pans+0.051
 ding+0.051
 counters+0.050
 forward+0.049
Neg logit contributions
zag-0.048
oot-0.044
uzz-0.043
seek-0.042
 sometime-0.040
Token He
Token ID679
Feature activation+5.03e-01

Pos logit contributions
zag+0.043
oot+0.040
uzz+0.039
seek+0.038
gy+0.036
Neg logit contributions
 pans-0.032
 ding-0.032
nam-0.032
 counters-0.031
 forward-0.030
Token takes
Token ID2753
Feature activation+2.00e+00

Pos logit contributions
 pans+0.017
 ding+0.017
 counters+0.016
 y+0.016
nam+0.016
Neg logit contributions
zag-0.035
oot-0.034
uzz-0.033
seek-0.033
gy-0.032
Token.
Token ID13
Feature activation-3.72e-01

Pos logit contributions
nam+0.317
 ding+0.308
 pans+0.300
 forward+0.299
 brightest+0.298
Neg logit contributions
zag-0.172
 sometime-0.151
seek-0.146
uzz-0.139
oot-0.139
Token They
Token ID1119
Feature activation-1.66e-01

Pos logit contributions
zag+0.021
uzz+0.020
oot+0.019
seek+0.019
 sometime+0.018
Neg logit contributions
nam-0.019
 pans-0.018
 ding-0.018
 counters-0.017
 forward-0.017
Token got
Token ID1392
Feature activation-4.01e-01

Pos logit contributions
zag+0.009
oot+0.009
uzz+0.009
seek+0.008
 sometime+0.008
Neg logit contributions
 ding-0.008
nam-0.008
 pans-0.008
 counters-0.008
 forward-0.007
Token out
Token ID503
Feature activation+5.89e+00

Pos logit contributions
uzz+0.017
 sometime+0.016
zag+0.015
 now+0.015
gy+0.015
Neg logit contributions
 ding-0.020
 spec-0.020
pared-0.020
sc-0.019
 de-0.019
Token the
Token ID262
Feature activation+4.82e-01

Pos logit contributions
nam+0.280
 ding+0.276
 pans+0.273
 counters+0.267
 forward+0.261
Neg logit contributions
zag-0.334
oot-0.312
uzz-0.305
seek-0.292
gy-0.285
Token pots
Token ID32195
Feature activation+6.47e+00

Pos logit contributions
nam+0.025
 spec+0.023
 ding+0.023
pared+0.021
 forward+0.021
Neg logit contributions
zag-0.026
ippy-0.022
 fault-0.022
gy-0.021
uzz-0.020
Token and
Token ID290
Feature activation-5.66e-02

Pos logit contributions
nam+0.428
 pans+0.408
 ding+0.406
 counters+0.399
 spec+0.390
Neg logit contributions
zag-0.266
oot-0.242
uzz-0.228
seek-0.214
gy-0.212
Token pans
Token ID36209
Feature activation+7.50e+00

Pos logit contributions
 sometime+0.004
 seek+0.004
gy+0.004
zag+0.004
 now+0.004
Neg logit contributions
 forward-0.002
pared-0.002
 spec-0.001
sc-0.001
 ding-0.001
Token,
Token ID11
Feature activation-4.32e-01

Pos logit contributions
nam+0.518
 ding+0.490
 spec+0.484
 pans+0.478
 Hungry+0.473
Neg logit contributions
zag-0.282
oot-0.235
gy-0.231
uzz-0.230
seek-0.217
Token and
Token ID290
Feature activation+3.16e-02

Pos logit contributions
 sometime+0.014
zag+0.014
 now+0.013
uzz+0.013
gy+0.013
Neg logit contributions
 forward-0.027
 ding-0.026
 spec-0.025
nam-0.025
pared-0.025
Token started
Token ID2067
Feature activation+1.14e+00

Pos logit contributions
 forward+0.002
 ding+0.002
 spec+0.002
pared+0.002
sc+0.002
Neg logit contributions
 sometime-0.001
zag-0.001
 now-0.001
uzz-0.001
gy-0.001
Token her
Token ID607
Feature activation-2.84e-01

Pos logit contributions
zag+0.080
oot+0.074
uzz+0.071
seek+0.069
gy+0.066
Neg logit contributions
nam-0.066
 pans-0.064
 ding-0.062
 y-0.062
 counters-0.062
Token test
Token ID1332
Feature activation-1.57e+00

Pos logit contributions
zag+0.015
oot+0.014
uzz+0.013
seek+0.013
 sometime+0.013
Neg logit contributions
nam-0.015
 ding-0.015
 pans-0.015
 counters-0.015
 forward-0.014
Token.
Token ID13
Feature activation-8.93e-02

Pos logit contributions
zag+0.085
oot+0.080
uzz+0.078
seek+0.074
gy+0.071
Neg logit contributions
nam-0.078
 pans-0.078
 ding-0.077
 counters-0.076
 forward-0.076
Token She
Token ID1375
Feature activation-8.79e-02

Pos logit contributions
zag+0.005
uzz+0.004
oot+0.004
seek+0.004
gy+0.004
Neg logit contributions
nam-0.005
 pans-0.005
 ding-0.005
 forward-0.004
 counters-0.004
Token hugged
Token ID41130
Feature activation+2.73e+00

Pos logit contributions
zag+0.006
oot+0.005
uzz+0.005
seek+0.005
gy+0.005
Neg logit contributions
 pans-0.004
 ding-0.003
nam-0.003
 y-0.003
 counters-0.003
Token Mr
Token ID1770
Feature activation+5.18e+00

Pos logit contributions
 pans+0.148
nam+0.147
 ding+0.146
 counters+0.144
 forward+0.140
Neg logit contributions
zag-0.136
oot-0.128
uzz-0.124
seek-0.119
 sometime-0.116
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
 pans+0.228
 forward+0.221
 de+0.218
 y+0.217
 ding+0.216
Neg logit contributions
zag-0.308
oot-0.290
seek-0.281
uzz-0.273
 sometime-0.256
Token Fox
Token ID5426
Feature activation-1.86e-01

Pos logit contributions
nam+0.024
 pans+0.024
 ding+0.024
 counters+0.024
 forward+0.023
Neg logit contributions
zag-0.020
oot-0.019
uzz-0.018
seek-0.017
 sometime-0.017
Token and
Token ID290
Feature activation+2.34e-01

Pos logit contributions
zag+0.010
oot+0.009
uzz+0.009
seek+0.009
 sometime+0.008
Neg logit contributions
 pans-0.010
 ding-0.009
nam-0.009
 counters-0.009
 forward-0.009
Token said
Token ID531
Feature activation+1.47e+00

Pos logit contributions
nam+0.010
 pans+0.010
 ding+0.010
 counters+0.010
 forward+0.009
Neg logit contributions
zag-0.015
oot-0.014
uzz-0.013
seek-0.013
 sometime-0.013
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
 pans+0.091
 counters+0.089
nam+0.089
 ding+0.087
 brightest+0.085
Neg logit contributions
zag-0.061
oot-0.060
uzz-0.058
seek-0.053
 sometime-0.053
Token slide
Token ID10649
Feature activation-2.24e+00

Pos logit contributions
nam+0.032
 forward+0.032
 ding+0.032
 pans+0.032
 counters+0.031
Neg logit contributions
zag-0.035
oot-0.031
seek-0.030
uzz-0.030
gy-0.029
Token.
Token ID13
Feature activation+5.57e-01

Pos logit contributions
zag+0.114
oot+0.107
uzz+0.103
seek+0.100
 sometime+0.095
Neg logit contributions
nam-0.119
 pans-0.119
 ding-0.118
 counters-0.115
 forward-0.114
Token It
Token ID632
Feature activation-8.85e-01

Pos logit contributions
 pans+0.023
nam+0.023
 counters+0.022
 ding+0.022
 y+0.020
Neg logit contributions
zag-0.034
uzz-0.034
oot-0.033
 sometime-0.032
seek-0.031
Token will
Token ID481
Feature activation+1.68e+00

Pos logit contributions
zag+0.055
oot+0.049
uzz+0.049
 sometime+0.047
seek+0.047
Neg logit contributions
nam-0.040
 pans-0.038
 counters-0.038
 ding-0.037
 forward-0.036
Token make
Token ID787
Feature activation+2.69e-01

Pos logit contributions
 ding+0.084
nam+0.083
 pans+0.081
 y+0.080
 brightest+0.077
Neg logit contributions
zag-0.094
oot-0.091
seek-0.088
uzz-0.087
ippy-0.084
Token you
Token ID345
Feature activation+2.01e+00

Pos logit contributions
nam+0.013
 pans+0.013
 counters+0.013
 forward+0.013
 ju+0.012
Neg logit contributions
zag-0.014
oot-0.014
uzz-0.013
 sometime-0.013
seek-0.012
Token happy
Token ID3772
Feature activation+5.50e-01

Pos logit contributions
nam+0.083
 ding+0.082
 pans+0.082
 counters+0.079
 forward+0.077
Neg logit contributions
zag-0.127
oot-0.121
uzz-0.117
seek-0.115
 sometime-0.110
Token."
Token ID526
Feature activation-7.34e-02

Pos logit contributions
 ding+0.028
 pans+0.028
nam+0.028
 counters+0.027
 forward+0.027
Neg logit contributions
zag-0.030
oot-0.028
uzz-0.027
seek-0.026
ippy-0.025
Token
Token ID198
Feature activation+6.74e-01

Pos logit contributions
zag+0.004
oot+0.004
uzz+0.004
seek+0.003
 sometime+0.003
Neg logit contributions
nam-0.004
 pans-0.004
 ding-0.004
 counters-0.004
 forward-0.004
Token
Token ID198
Feature activation+7.17e-01

Pos logit contributions
 pans+0.030
 ding+0.030
nam+0.030
 counters+0.029
 forward+0.029
Neg logit contributions
zag-0.040
oot-0.038
seek-0.036
uzz-0.036
gy-0.035
TokenBen
Token ID11696
Feature activation-2.88e-01

Pos logit contributions
 pans+0.041
nam+0.041
 ding+0.041
 counters+0.040
 forward+0.039
Neg logit contributions
zag-0.034
oot-0.032
uzz-0.030
seek-0.030
gy-0.028
Token when
Token ID618
Feature activation+4.33e+00

Pos logit contributions
zag+0.034
oot+0.031
seek+0.029
uzz+0.029
 sometime+0.028
Neg logit contributions
 pans-0.030
nam-0.029
 ding-0.029
 counters-0.029
 spec-0.027
Token her
Token ID607
Feature activation-5.16e-01

Pos logit contributions
nam+0.154
 ding+0.137
 pans+0.135
 forward+0.131
 y+0.128
Neg logit contributions
zag-0.322
oot-0.311
uzz-0.295
seek-0.289
ogo-0.284
Token little
Token ID1310
Feature activation+3.15e+00

Pos logit contributions
zag+0.021
oot+0.017
uzz+0.017
gy+0.016
seek+0.016
Neg logit contributions
nam-0.033
sc-0.033
 ding-0.033
 forward-0.032
 counters-0.032
Token brother
Token ID3956
Feature activation-2.04e+00

Pos logit contributions
nam+0.200
 ding+0.199
 counters+0.196
 pans+0.196
sc+0.196
Neg logit contributions
zag-0.119
oot-0.105
gy-0.104
uzz-0.097
 sometime-0.095
Token came
Token ID1625
Feature activation+3.10e+00

Pos logit contributions
zag+0.112
oot+0.104
uzz+0.100
seek+0.099
gy+0.096
Neg logit contributions
nam-0.102
 pans-0.101
 ding-0.100
 counters-0.098
 forward-0.096
Token in
Token ID287
Feature activation+4.74e-01

Pos logit contributions
 forward+0.106
 pans+0.087
nam+0.086
 ding+0.081
 deep+0.080
Neg logit contributions
zag-0.222
oot-0.217
seek-0.211
ogo-0.202
uzz-0.198
Token.
Token ID13
Feature activation-7.60e-01

Pos logit contributions
 pans+0.021
 forward+0.021
 y+0.020
 ding+0.020
 counters+0.020
Neg logit contributions
zag-0.029
oot-0.028
uzz-0.026
seek-0.026
ogo-0.025
Token
Token ID220
Feature activation+3.16e+00

Pos logit contributions
zag+0.035
uzz+0.032
seek+0.031
oot+0.031
 sometime+0.030
Neg logit contributions
nam-0.044
 pans-0.042
 ding-0.042
 forward-0.041
 brightest-0.040
Token
Token ID198
Feature activation-4.79e-01

Pos logit contributions
nam+0.158
 pans+0.158
 ding+0.156
 counters+0.153
 forward+0.150
Neg logit contributions
zag-0.171
oot-0.160
uzz-0.155
seek-0.150
 sometime-0.145
Token
Token ID198
Feature activation-4.39e-01

Pos logit contributions
zag+0.025
oot+0.024
uzz+0.023
seek+0.022
 sometime+0.021
Neg logit contributions
nam-0.025
 pans-0.025
 ding-0.025
 counters-0.024
 forward-0.023
Token"
Token ID1
Feature activation-1.00e+00

Pos logit contributions
zag+0.017
oot+0.014
seek+0.014
uzz+0.014
 sometime+0.014
Neg logit contributions
nam-0.030
 spec-0.029
 ding-0.028
 pans-0.028
 brightest-0.028
Token found
Token ID1043
Feature activation-1.76e+00

Pos logit contributions
zag+0.038
oot+0.036
uzz+0.034
seek+0.034
 sometime+0.032
Neg logit contributions
 pans-0.028
nam-0.028
 ding-0.028
 counters-0.027
 forward-0.026
Token the
Token ID262
Feature activation+2.81e-01

Pos logit contributions
zag+0.070
uzz+0.068
oot+0.067
gy+0.061
seek+0.061
Neg logit contributions
 ding-0.108
nam-0.108
 pans-0.106
 counters-0.105
 forward-0.101
Token biggest
Token ID4094
Feature activation+2.21e+00

Pos logit contributions
 ding+0.011
nam+0.011
 counters+0.011
 pans+0.011
sc+0.011
Neg logit contributions
zag-0.017
gy-0.016
uzz-0.015
oot-0.015
 sometime-0.015
Token,
Token ID11
Feature activation-6.67e-01

Pos logit contributions
nam+0.109
 ding+0.107
 pans+0.106
 counters+0.104
 forward+0.101
Neg logit contributions
zag-0.121
oot-0.113
uzz-0.109
 sometime-0.105
gy-0.105
Token brightest
Token ID33871
Feature activation+2.28e+00

Pos logit contributions
 sometime+0.036
zag+0.036
 now+0.035
gy+0.035
 himself+0.035
Neg logit contributions
 ding-0.023
 counters-0.023
 forward-0.022
 slot-0.021
 channels-0.021
Token rad
Token ID2511
Feature activation+3.37e+00

Pos logit contributions
nam+0.106
 ding+0.106
 pans+0.103
 counters+0.102
 forward+0.099
Neg logit contributions
zag-0.128
oot-0.121
uzz-0.118
 sometime-0.114
gy-0.113
Tokenish
Token ID680
Feature activation-2.67e+00

Pos logit contributions
 ding+0.189
 counters+0.185
nam+0.184
 pans+0.176
 forward+0.173
Neg logit contributions
zag-0.160
oot-0.152
gy-0.146
uzz-0.143
 sometime-0.138
Token and
Token ID290
Feature activation-2.35e-01

Pos logit contributions
zag+0.136
oot+0.127
uzz+0.122
seek+0.116
 sometime+0.114
Neg logit contributions
nam-0.145
 ding-0.143
 pans-0.141
 counters-0.140
 forward-0.135
Token he
Token ID339
Feature activation+8.99e-01

Pos logit contributions
 sometime+0.011
zag+0.011
oot+0.010
 now+0.010
uzz+0.010
Neg logit contributions
 ding-0.012
 forward-0.012
 counters-0.011
nam-0.011
 pans-0.011
Token hopped
Token ID45230
Feature activation+1.44e+00

Pos logit contributions
nam+0.040
 pans+0.040
 ding+0.040
 counters+0.039
 forward+0.038
Neg logit contributions
zag-0.053
oot-0.050
uzz-0.049
seek-0.047
 sometime-0.046
Token back
Token ID736
Feature activation-2.13e+00

Pos logit contributions
nam+0.055
 pans+0.055
 ding+0.054
 counters+0.053
 forward+0.050
Neg logit contributions
zag-0.096
oot-0.091
uzz-0.088
seek-0.086
 sometime-0.084
TokenToday
Token ID8888
Feature activation-3.66e+00

Pos logit contributions
nam+0.097
 counters+0.095
 pans+0.091
 ding+0.090
 y+0.089
Neg logit contributions
zag-0.132
uzz-0.129
 sometime-0.126
oot-0.125
seek-0.123
Token we
Token ID356
Feature activation+6.06e-01

Pos logit contributions
zag+0.174
oot+0.155
 sometime+0.151
uzz+0.148
seek+0.144
Neg logit contributions
nam-0.216
 pans-0.212
 counters-0.205
 ding-0.204
 forward-0.199
Token're
Token ID821
Feature activation+1.97e+00

Pos logit contributions
nam+0.024
 pans+0.024
 ding+0.024
 counters+0.024
 forward+0.023
Neg logit contributions
zag-0.039
oot-0.037
uzz-0.036
seek-0.035
 sometime-0.034
Token going
Token ID1016
Feature activation+4.15e+00

Pos logit contributions
sc+0.102
 counters+0.095
 pans+0.094
nam+0.093
 ding+0.092
Neg logit contributions
zag-0.092
 now-0.090
uzz-0.089
oot-0.089
 sometime-0.088
Token on
Token ID319
Feature activation-4.80e-01

Pos logit contributions
 forward+0.193
 pans+0.180
 ding+0.174
 ready+0.169
 y+0.169
Neg logit contributions
zag-0.245
uzz-0.241
oot-0.241
seek-0.225
ogo-0.215
Token a
Token ID257
Feature activation+3.67e-01

Pos logit contributions
oot+0.037
zag+0.036
uzz+0.035
ogo+0.033
ebra+0.032
Neg logit contributions
 y-0.016
 flour-0.014
 pans-0.014
 ready-0.013
 delicious-0.013
Token picnic
Token ID35715
Feature activation-2.71e+00

Pos logit contributions
nam+0.020
 pans+0.020
 ding+0.020
 counters+0.019
 forward+0.019
Neg logit contributions
zag-0.018
oot-0.017
uzz-0.017
seek-0.016
 sometime-0.015
Token!"
Token ID2474
Feature activation-2.37e+00

Pos logit contributions
zag+0.135
oot+0.128
uzz+0.123
seek+0.118
gy+0.111
Neg logit contributions
 pans-0.147
nam-0.145
 ding-0.145
 counters-0.142
 forward-0.141
Token Maria
Token ID14200
Feature activation+6.03e-01

Pos logit contributions
zag+0.122
uzz+0.112
oot+0.110
 sometime+0.108
gy+0.107
Neg logit contributions
nam-0.129
 forward-0.121
 pans-0.119
 ju-0.119
 ding-0.118
Token was
Token ID373
Feature activation-5.43e-01

Pos logit contributions
 y+0.022
 pans+0.022
 ding+0.022
 counters+0.022
nam+0.021
Neg logit contributions
zag-0.039
oot-0.038
seek-0.036
uzz-0.036
ogo-0.035
Token very
Token ID845
Feature activation+1.65e+00

Pos logit contributions
zag+0.034
uzz+0.032
oot+0.031
 sometime+0.030
seek+0.030
Neg logit contributions
 pans-0.022
 counters-0.021
sc-0.021
nam-0.020
 ding-0.020
Token
Token ID198
Feature activation+2.95e-01

Pos logit contributions
nam+0.011
 pans+0.011
 ding+0.011
 counters+0.011
 forward+0.010
Neg logit contributions
zag-0.015
uzz-0.014
oot-0.014
seek-0.014
 sometime-0.013
Token
Token ID198
Feature activation+3.65e-01

Pos logit contributions
 pans+0.011
 ding+0.011
 counters+0.011
nam+0.011
 y+0.010
Neg logit contributions
zag-0.019
oot-0.018
seek-0.018
uzz-0.017
gy-0.017
Token"
Token ID1
Feature activation-2.25e-01

Pos logit contributions
 pans+0.015
 ding+0.015
nam+0.015
 counters+0.014
 forward+0.014
Neg logit contributions
zag-0.024
oot-0.023
seek-0.021
uzz-0.021
gy-0.021
TokenMaybe
Token ID13300
Feature activation+5.65e-01

Pos logit contributions
zag+0.016
oot+0.015
uzz+0.014
seek+0.014
gy+0.013
Neg logit contributions
 pans-0.008
nam-0.008
 ding-0.008
 counters-0.008
 forward-0.007
Token we
Token ID356
Feature activation+1.14e+00

Pos logit contributions
nam+0.025
 pans+0.025
 ding+0.025
 counters+0.025
 forward+0.024
Neg logit contributions
zag-0.034
oot-0.032
uzz-0.031
seek-0.030
 sometime-0.029
Token should
Token ID815
Feature activation+2.69e-01

Pos logit contributions
nam+0.029
 forward+0.029
 y+0.028
 pans+0.028
 ding+0.028
Neg logit contributions
zag-0.090
oot-0.086
seek-0.084
uzz-0.083
ippy-0.080
Token have
Token ID423
Feature activation-3.74e+00

Pos logit contributions
 y+0.013
nam+0.012
 ding+0.012
 pans+0.012
 counters+0.012
Neg logit contributions
zag-0.016
oot-0.015
seek-0.014
uzz-0.014
ippy-0.014
Token played
Token ID2826
Feature activation-2.67e+00

Pos logit contributions
zag+0.238
oot+0.224
uzz+0.209
ippy+0.199
seek+0.198
Neg logit contributions
nam-0.173
 pans-0.172
 y-0.171
 ding-0.164
 counters-0.160
Token with
Token ID351
Feature activation+3.44e-01

Pos logit contributions
zag+0.188
oot+0.181
uzz+0.169
seek+0.169
ogo+0.166
Neg logit contributions
 y-0.099
 ding-0.096
 pans-0.095
 forward-0.095
nam-0.092
Token Frost
Token ID15122
Feature activation-1.07e+00

Pos logit contributions
nam+0.017
 ding+0.017
 counters+0.017
 pans+0.017
 forward+0.017
Neg logit contributions
zag-0.018
uzz-0.017
oot-0.017
 sometime-0.016
seek-0.015
Tokeny
Token ID88
Feature activation-1.18e+00

Pos logit contributions
oot+0.061
seek+0.060
zag+0.059
uzz+0.053
 sometime+0.052
Neg logit contributions
 pans-0.048
 ding-0.045
 forward-0.043
 y-0.043
nam-0.043
Token delicious
Token ID12625
Feature activation+3.32e+00

Pos logit contributions
zag+0.018
oot+0.016
uzz+0.016
 sometime+0.015
seek+0.015
Neg logit contributions
nam-0.013
 pans-0.013
 ding-0.013
 counters-0.013
 forward-0.013
Token,
Token ID11
Feature activation-2.82e-01

Pos logit contributions
nam+0.184
 pans+0.184
 ding+0.183
 counters+0.179
 forward+0.176
Neg logit contributions
zag-0.162
oot-0.150
uzz-0.144
seek-0.140
 sometime-0.134
Token but
Token ID475
Feature activation+1.49e+00

Pos logit contributions
zag+0.013
oot+0.012
uzz+0.012
 sometime+0.012
seek+0.011
Neg logit contributions
nam-0.016
 pans-0.016
 ding-0.015
 counters-0.015
 forward-0.015
Token because
Token ID780
Feature activation-3.01e+00

Pos logit contributions
 pans+0.076
 counters+0.075
nam+0.075
 ding+0.075
 forward+0.069
Neg logit contributions
zag-0.080
oot-0.074
uzz-0.074
 sometime-0.070
seek-0.069
Token the
Token ID262
Feature activation+5.92e-01

Pos logit contributions
zag+0.171
oot+0.158
uzz+0.155
seek+0.148
 sometime+0.148
Neg logit contributions
nam-0.143
 ding-0.143
 pans-0.143
 counters-0.141
 forward-0.134
Token monster
Token ID9234
Feature activation-2.27e+00

Pos logit contributions
nam+0.036
 pans+0.036
 ding+0.035
 counters+0.035
 forward+0.034
Neg logit contributions
zag-0.026
oot-0.024
uzz-0.023
seek-0.022
 sometime-0.021
Token wasn
Token ID2492
Feature activation+1.16e+00

Pos logit contributions
zag+0.129
oot+0.123
uzz+0.119
seek+0.116
 sometime+0.110
Neg logit contributions
 pans-0.105
 ding-0.105
nam-0.104
 counters-0.102
 y-0.100
Token't
Token ID470
Feature activation-4.61e+00

Pos logit contributions
 forward+0.069
 ding+0.068
 y+0.065
nam+0.065
 pans+0.064
Neg logit contributions
zag-0.053
oot-0.049
uzz-0.048
seek-0.048
gy-0.045
Token scary
Token ID14343
Feature activation-7.66e-01

Pos logit contributions
zag+0.289
oot+0.274
uzz+0.267
seek+0.259
 sometime+0.253
Neg logit contributions
 pans-0.189
 ding-0.188
nam-0.188
 counters-0.185
 forward-0.178
Token after
Token ID706
Feature activation+6.65e-03

Pos logit contributions
zag+0.026
oot+0.024
uzz+0.022
seek+0.021
 sometime+0.020
Neg logit contributions
nam-0.054
 pans-0.054
 ding-0.053
 counters-0.052
 forward-0.051
Token all
Token ID477
Feature activation-3.91e+00

Pos logit contributions
nam+0.000
 ding+0.000
 pans+0.000
 y+0.000
 forward+0.000
Neg logit contributions
zag-0.000
oot-0.000
seek-0.000
gy-0.000
uzz-0.000
Token little
Token ID1310
Feature activation+3.22e+00

Pos logit contributions
 counters+0.013
nam+0.013
sc+0.013
 forward+0.013
 pans+0.012
Neg logit contributions
zag-0.022
oot-0.020
uzz-0.020
gy-0.019
 sometime-0.019
Token boy
Token ID2933
Feature activation+4.52e-01

Pos logit contributions
 counters+0.135
nam+0.134
 ding+0.128
 forward+0.127
 pans+0.126
Neg logit contributions
zag-0.193
oot-0.185
uzz-0.180
gy-0.175
ippy-0.168
Token.
Token ID13
Feature activation-8.09e-01

Pos logit contributions
nam+0.025
 pans+0.025
 ding+0.025
 counters+0.024
 forward+0.024
Neg logit contributions
zag-0.022
oot-0.020
uzz-0.019
seek-0.019
 sometime-0.018
Token He
Token ID679
Feature activation-6.60e-01

Pos logit contributions
zag+0.050
oot+0.047
uzz+0.045
seek+0.044
 sometime+0.043
Neg logit contributions
 ding-0.035
nam-0.035
 pans-0.035
 counters-0.034
 forward-0.033
Token was
Token ID373
Feature activation-6.37e-01

Pos logit contributions
zag+0.049
oot+0.047
uzz+0.046
seek+0.044
 sometime+0.043
Neg logit contributions
 pans-0.020
nam-0.020
 y-0.020
 ding-0.020
 counters-0.019
Token three
Token ID1115
Feature activation-1.68e+00

Pos logit contributions
zag+0.038
uzz+0.037
gy+0.036
oot+0.035
seek+0.033
Neg logit contributions
 counters-0.028
 pans-0.028
sc-0.027
 ding-0.025
 spec-0.025
Token years
Token ID812
Feature activation+1.85e+00

Pos logit contributions
zag+0.088
oot+0.083
uzz+0.081
seek+0.076
 sometime+0.076
Neg logit contributions
 ding-0.084
nam-0.084
 pans-0.081
 forward-0.081
 counters-0.079
Token old
Token ID1468
Feature activation+5.28e-01

Pos logit contributions
nam+0.077
 ding+0.075
 forward+0.072
 pans+0.071
sc+0.071
Neg logit contributions
zag-0.115
oot-0.113
uzz-0.108
seek-0.100
ippy-0.099
Token and
Token ID290
Feature activation-3.51e-01

Pos logit contributions
nam+0.025
 pans+0.025
 ding+0.024
 counters+0.024
 y+0.024
Neg logit contributions
zag-0.032
oot-0.029
uzz-0.028
seek-0.027
ogo-0.026
Token had
Token ID550
Feature activation-1.53e+00

Pos logit contributions
zag+0.017
uzz+0.016
gy+0.016
oot+0.016
seek+0.015
Neg logit contributions
 counters-0.018
sc-0.018
 spec-0.018
 ding-0.018
 forward-0.018
Token lots
Token ID6041
Feature activation-5.42e-02

Pos logit contributions
zag+0.059
seek+0.057
uzz+0.055
 sometime+0.052
gy+0.052
Neg logit contributions
 forward-0.092
 pans-0.092
sc-0.092
 ding-0.092
 counters-0.090
Token had
Token ID550
Feature activation-1.51e+00

Pos logit contributions
 pans+0.046
nam+0.044
 ding+0.044
 y+0.043
 counters+0.043
Neg logit contributions
zag-0.074
oot-0.071
uzz-0.069
seek-0.067
ippy-0.063
Token an
Token ID281
Feature activation-1.13e+00

Pos logit contributions
zag+0.119
oot+0.113
uzz+0.102
ebra+0.102
ippy+0.102
Neg logit contributions
 y-0.061
 ju-0.051
 flour-0.049
nam-0.046
 fres-0.045
Token idea
Token ID2126
Feature activation-2.17e+00

Pos logit contributions
zag+0.080
seek+0.073
uzz+0.073
oot+0.072
gy+0.069
Neg logit contributions
 y-0.041
 forward-0.039
 ding-0.039
 pans-0.039
nam-0.039
Token.
Token ID13
Feature activation-6.06e-01

Pos logit contributions
zag+0.137
oot+0.124
uzz+0.123
seek+0.120
gy+0.119
Neg logit contributions
 y-0.088
 forward-0.088
 pans-0.087
nam-0.084
 ding-0.083
Token
Token ID198
Feature activation-5.45e-01

Pos logit contributions
zag+0.034
oot+0.031
uzz+0.030
seek+0.030
 sometime+0.029
Neg logit contributions
nam-0.030
 ding-0.030
 pans-0.030
 counters-0.029
 forward-0.028
Token
Token ID198
Feature activation-4.57e-01

Pos logit contributions
zag+0.035
oot+0.033
uzz+0.032
seek+0.032
gy+0.031
Neg logit contributions
 pans-0.020
 ding-0.020
 forward-0.020
 y-0.019
 counters-0.019
TokenR
Token ID49
Feature activation-1.40e+00

Pos logit contributions
zag+0.027
oot+0.026
uzz+0.025
seek+0.024
 sometime+0.023
Neg logit contributions
 pans-0.021
 ding-0.020
nam-0.020
 counters-0.020
 forward-0.020
Tokenemy
Token ID3065
Feature activation-3.65e+00

Pos logit contributions
zag+0.045
uzz+0.042
oot+0.040
seek+0.040
 sometime+0.034
Neg logit contributions
 pans-0.095
 y-0.093
 counters-0.092
 forward-0.092
 ding-0.091
Token went
Token ID1816
Feature activation+1.78e+00

Pos logit contributions
zag+0.225
oot+0.216
uzz+0.211
seek+0.202
ippy+0.195
Neg logit contributions
 pans-0.153
 counters-0.149
 ding-0.147
 y-0.145
nam-0.143
Token to
Token ID284
Feature activation-1.14e+00

Pos logit contributions
 forward+0.080
 pans+0.078
 counters+0.074
 ding+0.073
 y+0.071
Neg logit contributions
zag-0.105
oot-0.103
uzz-0.100
 sometime-0.095
seek-0.093
Token the
Token ID262
Feature activation+3.66e-01

Pos logit contributions
zag+0.072
oot+0.071
uzz+0.066
seek+0.065
 sometime+0.060
Neg logit contributions
 pans-0.049
 y-0.048
nam-0.048
 ding-0.047
 counters-0.045
Token brave
Token ID14802
Feature activation+7.08e-01

Pos logit contributions
nam+0.019
 pans+0.018
 counters+0.018
 ding+0.018
 forward+0.017
Neg logit contributions
zag-0.020
oot-0.018
seek-0.018
uzz-0.017
 sometime-0.017
Token Princess
Token ID8449
Feature activation+1.60e+00

Pos logit contributions
nam+0.031
 pans+0.031
 ding+0.030
 counters+0.030
 forward+0.029
Neg logit contributions
zag-0.043
oot-0.041
uzz-0.040
seek-0.039
 sometime-0.037
Token for
Token ID329
Feature activation-1.33e+00

Pos logit contributions
nam+0.074
 ding+0.073
 pans+0.073
 forward+0.073
 counters+0.071
Neg logit contributions
zag-0.091
oot-0.084
uzz-0.082
seek-0.080
 sometime-0.077
Token protecting
Token ID10192
Feature activation+1.48e+00

Pos logit contributions
zag+0.076
oot+0.070
uzz+0.067
seek+0.066
gy+0.063
Neg logit contributions
nam-0.066
 ding-0.064
 pans-0.063
 forward-0.062
 counters-0.061
Token the
Token ID262
Feature activation+3.50e-01

Pos logit contributions
 pans+0.078
 ding+0.078
nam+0.078
 counters+0.076
 forward+0.073
Neg logit contributions
zag-0.076
oot-0.072
uzz-0.070
seek-0.067
gy-0.065
Token castle
Token ID16669
Feature activation-3.19e+00

Pos logit contributions
nam+0.021
 pans+0.020
 counters+0.020
 ding+0.020
sc+0.019
Neg logit contributions
zag-0.015
seek-0.013
oot-0.013
 sometime-0.013
gy-0.013
Token and
Token ID290
Feature activation-2.08e-01

Pos logit contributions
zag+0.153
oot+0.138
seek+0.128
uzz+0.128
gy+0.124
Neg logit contributions
 pans-0.186
nam-0.186
 ding-0.182
 counters-0.179
 spec-0.175
Token saving
Token ID8914
Feature activation+1.66e+00

Pos logit contributions
zag+0.011
oot+0.010
uzz+0.010
seek+0.010
 sometime+0.009
Neg logit contributions
 pans-0.011
 counters-0.011
 ding-0.011
nam-0.010
 forward-0.010
Token the
Token ID262
Feature activation+3.25e-01

Pos logit contributions
 pans+0.099
 ding+0.097
 counters+0.097
nam+0.095
 ju+0.093
Neg logit contributions
oot-0.067
uzz-0.067
zag-0.065
gy-0.062
 sometime-0.061
Token day
Token ID1110
Feature activation-1.06e-02

Pos logit contributions
 pans+0.018
nam+0.018
 counters+0.018
 ding+0.017
sc+0.016
Neg logit contributions
zag-0.015
 sometime-0.013
seek-0.013
oot-0.013
gy-0.013
Token.
Token ID13
Feature activation-1.93e-01

Pos logit contributions
zag+0.000
oot+0.000
seek+0.000
 sometime+0.000
uzz+0.000
Neg logit contributions
 pans-0.001
nam-0.001
 counters-0.001
 ding-0.001
 spec-0.001
Token special
Token ID2041
Feature activation-3.46e-01

Pos logit contributions
zag+0.039
uzz+0.037
oot+0.037
 sometime+0.037
emo+0.035
Neg logit contributions
 counters-0.030
 ding-0.030
nam-0.029
 pans-0.028
sc-0.028
Token as
Token ID355
Feature activation-7.25e-01

Pos logit contributions
zag+0.019
oot+0.017
uzz+0.017
seek+0.016
gy+0.016
Neg logit contributions
 pans-0.017
nam-0.017
 ding-0.017
 forward-0.017
 counters-0.017
Token the
Token ID262
Feature activation+1.92e-02

Pos logit contributions
zag+0.037
oot+0.035
uzz+0.034
 sometime+0.033
seek+0.032
Neg logit contributions
 ding-0.038
nam-0.038
 counters-0.037
 pans-0.037
 forward-0.035
Token butter
Token ID9215
Feature activation+2.50e+00

Pos logit contributions
 ding+0.001
nam+0.001
 counters+0.001
 forward+0.001
sc+0.001
Neg logit contributions
zag-0.001
 sometime-0.001
seek-0.001
oot-0.001
 seek-0.001
Token he
Token ID339
Feature activation+8.30e-01

Pos logit contributions
 pans+0.118
nam+0.117
 ding+0.117
 counters+0.114
 forward+0.112
Neg logit contributions
zag-0.141
oot-0.133
uzz-0.129
seek-0.126
 sometime-0.121
Token found
Token ID1043
Feature activation-1.93e+00

Pos logit contributions
 pans+0.031
nam+0.031
 ding+0.031
 counters+0.030
 forward+0.029
Neg logit contributions
zag-0.055
oot-0.053
uzz-0.051
seek-0.050
 sometime-0.048
Token when
Token ID618
Feature activation+4.02e+00

Pos logit contributions
zag+0.087
oot+0.081
uzz+0.078
 sometime+0.074
seek+0.074
Neg logit contributions
nam-0.115
 pans-0.115
 ding-0.114
 counters-0.111
 forward-0.104
Token he
Token ID339
Feature activation+8.09e-01

Pos logit contributions
nam+0.193
 pans+0.192
 ding+0.191
 counters+0.186
 forward+0.184
Neg logit contributions
zag-0.227
oot-0.214
uzz-0.207
seek-0.200
gy-0.192
Token climbed
Token ID19952
Feature activation-2.18e-01

Pos logit contributions
 y+0.031
 ding+0.030
 forward+0.029
 pans+0.029
 counters+0.029
Neg logit contributions
zag-0.052
oot-0.051
uzz-0.050
seek-0.046
ippy-0.045
Token the
Token ID262
Feature activation-4.18e-02

Pos logit contributions
zag+0.014
oot+0.013
uzz+0.013
seek+0.013
 sometime+0.012
Neg logit contributions
 pans-0.009
nam-0.009
 ding-0.009
 forward-0.009
 counters-0.008
Token wall
Token ID3355
Feature activation+9.50e-01

Pos logit contributions
zag+0.002
oot+0.002
seek+0.002
uzz+0.002
 sometime+0.002
Neg logit contributions
nam-0.002
 pans-0.002
 ding-0.002
 counters-0.002
 forward-0.002
Token.
Token ID13
Feature activation-2.64e-01

Pos logit contributions
zag+0.119
oot+0.111
uzz+0.107
seek+0.104
 sometime+0.100
Neg logit contributions
nam-0.113
 pans-0.113
 ding-0.112
 counters-0.109
 forward-0.107
Token He
Token ID679
Feature activation-2.18e-01

Pos logit contributions
zag+0.012
uzz+0.011
oot+0.011
seek+0.011
 sometime+0.011
Neg logit contributions
nam-0.015
 pans-0.015
 ding-0.015
 forward-0.014
 counters-0.014
Token wanted
Token ID2227
Feature activation+1.04e+00

Pos logit contributions
zag+0.014
oot+0.013
uzz+0.013
seek+0.012
gy+0.012
Neg logit contributions
nam-0.009
 pans-0.009
 ding-0.009
 counters-0.009
 y-0.009
Token it
Token ID340
Feature activation+1.78e-01

Pos logit contributions
nam+0.052
 pans+0.051
 ding+0.051
 forward+0.051
 y+0.050
Neg logit contributions
zag-0.058
oot-0.053
uzz-0.052
seek-0.050
gy-0.049
Token so
Token ID523
Feature activation+7.64e-01

Pos logit contributions
 forward+0.006
 y+0.005
nam+0.005
 ding+0.005
 brightest+0.005
Neg logit contributions
zag-0.013
uzz-0.012
oot-0.012
seek-0.012
gy-0.012
Token badly
Token ID11234
Feature activation-6.37e+00

Pos logit contributions
 y+0.035
nam+0.034
 forward+0.033
 ding+0.033
 de+0.032
Neg logit contributions
zag-0.047
oot-0.043
seek-0.042
uzz-0.041
istle-0.040
Token!
Token ID0
Feature activation-1.25e+00

Pos logit contributions
zag+0.413
uzz+0.400
isk+0.384
ogo+0.374
oot+0.374
Neg logit contributions
 forward-0.238
 y-0.225
 de-0.220
 ready-0.214
 spec-0.204
Token
Token ID220
Feature activation+3.40e+00

Pos logit contributions
zag+0.064
oot+0.060
uzz+0.059
seek+0.058
 sometime+0.057
Neg logit contributions
nam-0.065
 pans-0.064
 ding-0.064
 counters-0.060
 forward-0.059
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
nam+0.162
 pans+0.161
 ding+0.161
 counters+0.158
 forward+0.155
Neg logit contributions
zag-0.191
oot-0.179
uzz-0.173
seek-0.169
 sometime-0.163
Token
Token ID198
Feature activation-9.73e-02

Pos logit contributions
zag+0.007
oot+0.006
uzz+0.006
seek+0.006
 sometime+0.006
Neg logit contributions
nam-0.007
 pans-0.007
 ding-0.007
 counters-0.007
 spec-0.007
Token"
Token ID1
Feature activation-6.82e-01

Pos logit contributions
zag+0.004
 sometime+0.004
oot+0.004
uzz+0.004
seek+0.004
Neg logit contributions
nam-0.006
 spec-0.006
 ding-0.006
 de-0.006
 pans-0.006
Token wanted
Token ID2227
Feature activation+9.08e-01

Pos logit contributions
 pans+0.084
 ding+0.084
 counters+0.082
nam+0.082
 forward+0.081
Neg logit contributions
zag-0.137
oot-0.132
uzz-0.129
seek-0.125
 sometime-0.119
Token to
Token ID284
Feature activation-1.13e+00

Pos logit contributions
 y+0.039
 pans+0.038
nam+0.038
 flour+0.038
 counters+0.035
Neg logit contributions
zag-0.060
oot-0.056
uzz-0.052
ogo-0.052
ippy-0.052
Token play
Token ID711
Feature activation-4.17e+00

Pos logit contributions
zag+0.073
oot+0.071
uzz+0.070
ogo+0.067
seek+0.065
Neg logit contributions
 y-0.045
 counters-0.042
 pans-0.041
nam-0.041
 ding-0.041
Token hide
Token ID7808
Feature activation-8.52e-01

Pos logit contributions
zag+0.319
uzz+0.304
oot+0.301
ogo+0.300
ert+0.290
Neg logit contributions
 y-0.151
 forward-0.127
 soft-0.121
 low-0.120
sc-0.114
Token and
Token ID290
Feature activation+1.18e-02

Pos logit contributions
zag+0.051
oot+0.047
seek+0.045
uzz+0.044
ogo+0.042
Neg logit contributions
 pans-0.041
nam-0.039
 forward-0.039
 y-0.039
 counters-0.039
Token seek
Token ID5380
Feature activation-7.46e+00

Pos logit contributions
 ding+0.001
 forward+0.001
 counters+0.001
 pans+0.001
nam+0.001
Neg logit contributions
zag-0.000
oot-0.000
seek-0.000
uzz-0.000
 sometime-0.000
Token with
Token ID351
Feature activation-9.01e-02

Pos logit contributions
zag+0.489
oot+0.466
uzz+0.438
ogo+0.420
seek+0.420
Neg logit contributions
nam-0.306
 forward-0.298
 y-0.296
 pans-0.291
 counters-0.287
Token the
Token ID262
Feature activation+3.92e-01

Pos logit contributions
zag+0.005
oot+0.004
uzz+0.004
seek+0.004
 sometime+0.004
Neg logit contributions
 pans-0.005
 ding-0.005
nam-0.005
 counters-0.005
 forward-0.004
Token sun
Token ID4252
Feature activation+3.58e+00

Pos logit contributions
 ding+0.020
sc+0.019
 counters+0.019
 forward+0.019
nam+0.019
Neg logit contributions
zag-0.019
 fault-0.016
oot-0.016
uzz-0.016
gy-0.015
Token.
Token ID13
Feature activation-4.32e-01

Pos logit contributions
nam+0.202
 ding+0.200
 pans+0.200
 counters+0.196
 forward+0.190
Neg logit contributions
zag-0.175
oot-0.159
uzz-0.153
seek-0.147
gy-0.146
Token The
Token ID383
Feature activation-1.38e+00

Pos logit contributions
zag+0.023
oot+0.021
seek+0.021
uzz+0.021
gy+0.020
Neg logit contributions
nam-0.022
 pans-0.022
 forward-0.021
 ding-0.021
 counters-0.021
Token something
Token ID1223
Feature activation+1.25e+00

Pos logit contributions
zag+0.029
oot+0.028
uzz+0.027
ogo+0.026
seek+0.026
Neg logit contributions
 y-0.013
nam-0.013
 spec-0.012
 forward-0.012
 low-0.012
Token so
Token ID523
Feature activation+6.52e-01

Pos logit contributions
 pans+0.047
nam+0.047
 ding+0.047
 counters+0.046
 forward+0.042
Neg logit contributions
zag-0.084
oot-0.080
uzz-0.076
 sometime-0.076
seek-0.075
Token hard
Token ID1327
Feature activation+2.50e-01

Pos logit contributions
 pans+0.029
 counters+0.029
 ding+0.028
nam+0.028
 spec+0.025
Neg logit contributions
zag-0.039
oot-0.038
uzz-0.036
 sometime-0.035
seek-0.034
Token!
Token ID0
Feature activation-1.02e+00

Pos logit contributions
 forward+0.011
 ding+0.011
 pans+0.011
 counters+0.011
 y+0.011
Neg logit contributions
zag-0.014
uzz-0.014
oot-0.013
seek-0.013
ippy-0.012
Token<|endoftext|>
Token ID50256
Feature activation-1.69e-01

Pos logit contributions
zag+0.063
oot+0.059
uzz+0.057
seek+0.056
 sometime+0.054
Neg logit contributions
nam-0.044
 pans-0.044
 ding-0.043
 counters-0.042
 forward-0.041
TokenOne
Token ID3198
Feature activation-5.10e+00

Pos logit contributions
zag+0.010
oot+0.009
uzz+0.009
seek+0.009
 sometime+0.009
Neg logit contributions
 pans-0.008
 ding-0.007
nam-0.007
 counters-0.007
 forward-0.007
Token day
Token ID1110
Feature activation-8.31e-02

Pos logit contributions
zag+0.341
oot+0.332
uzz+0.319
seek+0.315
gy+0.304
Neg logit contributions
 ding-0.188
 y-0.184
 pans-0.183
 forward-0.182
nam-0.180
Token,
Token ID11
Feature activation-4.88e-01

Pos logit contributions
zag+0.004
oot+0.004
uzz+0.003
seek+0.003
 sometime+0.003
Neg logit contributions
nam-0.005
 pans-0.005
 ding-0.005
 counters-0.005
 forward-0.005
Token a
Token ID257
Feature activation+4.95e-01

Pos logit contributions
zag+0.027
oot+0.025
uzz+0.024
seek+0.024
 sometime+0.023
Neg logit contributions
nam-0.024
 pans-0.024
 ding-0.024
 counters-0.023
 forward-0.023
Token little
Token ID1310
Feature activation+3.44e+00

Pos logit contributions
 counters+0.022
nam+0.021
sc+0.019
 forward+0.019
 pans+0.019
Neg logit contributions
zag-0.030
oot-0.027
uzz-0.026
gy-0.026
ah-0.026
Token boy
Token ID2933
Feature activation+5.65e-01

Pos logit contributions
 counters+0.152
nam+0.149
 pans+0.142
 ding+0.139
 forward+0.133
Neg logit contributions
zag-0.206
oot-0.199
uzz-0.191
gy-0.188
ippy-0.180
Token he
Token ID339
Feature activation+8.60e-01

Pos logit contributions
zag+0.006
oot+0.005
uzz+0.005
 sometime+0.004
gy+0.004
Neg logit contributions
 counters-0.016
 pans-0.016
nam-0.016
 ju-0.015
 ding-0.015
Token wanted
Token ID2227
Feature activation+6.24e-01

Pos logit contributions
 pans+0.027
 y+0.026
nam+0.025
 ding+0.025
sc+0.025
Neg logit contributions
oot-0.062
zag-0.061
uzz-0.059
seek-0.057
ippy-0.056
Token to
Token ID284
Feature activation-1.32e+00

Pos logit contributions
nam+0.030
 pans+0.030
 ding+0.029
 y+0.029
 counters+0.029
Neg logit contributions
zag-0.036
oot-0.034
uzz-0.032
gy-0.031
ippy-0.030
Token try
Token ID1949
Feature activation-4.93e-01

Pos logit contributions
oot+0.081
zag+0.081
uzz+0.080
ogo+0.074
gy+0.072
Neg logit contributions
 y-0.056
nam-0.054
 pans-0.053
 ding-0.053
 counters-0.053
Token to
Token ID284
Feature activation-1.33e+00

Pos logit contributions
zag+0.032
oot+0.032
uzz+0.032
seek+0.030
gy+0.030
Neg logit contributions
nam-0.019
 pans-0.019
 ding-0.019
 y-0.018
 forward-0.018
Token win
Token ID1592
Feature activation-7.22e+00

Pos logit contributions
zag+0.076
oot+0.076
uzz+0.075
gy+0.068
ogo+0.068
Neg logit contributions
nam-0.062
 y-0.060
 ding-0.060
 pans-0.059
 counters-0.058
Token.
Token ID13
Feature activation-8.86e-01

Pos logit contributions
zag+0.466
oot+0.445
uzz+0.430
gy+0.413
ippy+0.412
Neg logit contributions
nam-0.315
 forward-0.292
 y-0.286
 pans-0.284
 ding-0.280
Token He
Token ID679
Feature activation-7.08e-01

Pos logit contributions
zag+0.046
oot+0.043
uzz+0.042
seek+0.041
 sometime+0.039
Neg logit contributions
 pans-0.047
nam-0.047
 ding-0.046
 counters-0.045
 forward-0.044
Token kept
Token ID4030
Feature activation-8.38e-01

Pos logit contributions
oot+0.053
zag+0.051
uzz+0.049
seek+0.048
ogo+0.047
Neg logit contributions
 y-0.021
 pans-0.020
nam-0.020
sc-0.019
 forward-0.018
Token trying
Token ID2111
Feature activation+8.64e-01

Pos logit contributions
zag+0.049
oot+0.046
uzz+0.045
seek+0.043
gy+0.042
Neg logit contributions
nam-0.040
 ding-0.040
 pans-0.039
 forward-0.039
 counters-0.037
Token and
Token ID290
Feature activation-4.54e-01

Pos logit contributions
nam+0.043
 ding+0.043
 pans+0.042
 forward+0.042
 counters+0.041
Neg logit contributions
zag-0.047
oot-0.044
uzz-0.043
seek-0.041
gy-0.040
Token the
Token ID262
Feature activation+7.50e-01

Pos logit contributions
 pans+0.107
nam+0.107
 ding+0.106
 counters+0.105
 forward+0.102
Neg logit contributions
zag-0.122
oot-0.114
uzz-0.110
seek-0.107
 sometime-0.103
Token bridge
Token ID7696
Feature activation-1.53e+00

Pos logit contributions
 pans+0.040
nam+0.040
 ding+0.040
 counters+0.039
 forward+0.038
Neg logit contributions
zag-0.039
oot-0.036
uzz-0.035
seek-0.034
 sometime-0.033
Token shakes
Token ID29959
Feature activation-2.54e-01

Pos logit contributions
zag+0.088
oot+0.082
uzz+0.079
seek+0.077
 sometime+0.074
Neg logit contributions
nam-0.073
 pans-0.072
 ding-0.070
 counters-0.070
 forward-0.068
Token.
Token ID13
Feature activation+7.44e-01

Pos logit contributions
zag+0.012
oot+0.011
uzz+0.011
seek+0.010
 sometime+0.010
Neg logit contributions
nam-0.015
 pans-0.015
 ding-0.014
 counters-0.014
 forward-0.014
Token Sara
Token ID24799
Feature activation-8.05e-01

Pos logit contributions
nam+0.036
 pans+0.036
 ding+0.035
 counters+0.035
 forward+0.033
Neg logit contributions
zag-0.041
oot-0.039
uzz-0.039
seek-0.037
 sometime-0.036
Token loses
Token ID14754
Feature activation-5.06e+00

Pos logit contributions
zag+0.050
oot+0.047
uzz+0.046
seek+0.045
 sometime+0.043
Neg logit contributions
 pans-0.034
nam-0.034
 ding-0.034
 counters-0.033
 forward-0.032
Token her
Token ID607
Feature activation+2.41e-01

Pos logit contributions
zag+0.359
oot+0.327
seek+0.311
 sometime+0.299
ogo+0.297
Neg logit contributions
 pans-0.196
nam-0.195
 ding-0.190
 counters-0.185
 spec-0.182
Token balance
Token ID5236
Feature activation-2.08e+00

Pos logit contributions
nam+0.015
 ding+0.015
 pans+0.014
 forward+0.014
 y+0.014
Neg logit contributions
zag-0.010
oot-0.009
uzz-0.009
seek-0.009
 sometime-0.008
Token and
Token ID290
Feature activation+9.10e-01

Pos logit contributions
zag+0.097
oot+0.090
uzz+0.085
seek+0.081
 sometime+0.079
Neg logit contributions
nam-0.121
 pans-0.120
 ding-0.118
 counters-0.117
 ju-0.112
Token drops
Token ID10532
Feature activation+1.42e+00

Pos logit contributions
nam+0.046
 pans+0.046
 counters+0.046
 ding+0.043
 ju+0.043
Neg logit contributions
zag-0.048
oot-0.044
uzz-0.042
seek-0.041
 sometime-0.040
Token the
Token ID262
Feature activation+7.28e-01

Pos logit contributions
nam+0.082
 counters+0.080
 pans+0.080
 ding+0.077
 brightest+0.075
Neg logit contributions
uzz-0.063
zag-0.063
oot-0.062
seek-0.055
ippy-0.053