TOP ACTIVATIONS
MAX = 6.071

to the NFL Championship in 1949 a game in which
and Walter White . In 1949 she became the first woman
1800 at a performance of Loc atell i 's C major
Tub man of Liberia in 1949 . She also has had
antagonist of the 2008 film Kung Fu Panda , is an
honor .[ 53 ] In 1989 Eb ony Magazine listed her
's speech on the EU looks set to be a heated
F ifty / F ifty Plan The council
this out of control e gom ani ac , secret police
this meant a depression in 1949 , or if the entity
AA FC Championships . In 1950 , the NFL finally took
City Council F ifty / F ifty Plan
- year deal with the Demons is reportedly worth $ 750
Russia has accused Ukraine of stealing gas meant for Europe Russian
buildup . Between 1946 and 1949 , the Rams and their
30 , 1964 f ifty years ago last week .
nearly 70 % of South Koreans who were awarded PhD s
, Mi Coc ina , PK 's Blue Water Grill
spores over Tokyo . In 1998 , terrorism experts warn about
the hands of the North Koreans ensured that no other outcome

MIN ACTIVATIONS
MIN = -6.153

C elt ics coach Brad Stevens isn 't sure if any
a heated exchange , Chris Wallace , the Texas Association of
, attorney general candidate Josh Stein and state Senate candidate Jeff
ed with Mos aic and Amar illo hops , it smells
following pioneering authors such as Hansen ( 1984 ), assume that
: [ Chuck Todd :] What
th anniversary ) of Sultan Hassan al Bol k iah acc
, about Dw y ane Wade , Chris Bosh , Kevin
year was last year ," Stevens said . " I don
s office later stressed that there were no immediate
can listen to the clar inet quint et without fearing that
just isn t Wallace s game ;
s play with Blake Wheeler and Mark Sche ife le
L all ana and Jordan Henderson . Despite a damaging run
. With Paul Ryan , there is a sense
helpful in the development of Hassan Whites ide .
l ashing criticism of Paul Ryan , the House speaker whose
Det Sgt Ronnie Payne asked anyone with information to
the fresh citrus aroma from Amar illo hops ; something lic
- Fle ury , Sidney Crosby , Ev gen i Malk

INTERVAL 3.015 - 6.071
CONTAINS 0.481%

could shuffle things around for Hong Kong , though these outcomes
its government has a good reputation , the instruments that it
Then he developed graft - vers us - host
The Hill . <|endoftext|> K UAL A L UMP UR --
be the first in the Philippines to enforce an outright ban

INTERVAL -0.041 - 3.015
CONTAINS 51.144%

created on the basis of the original M oom in works
for determining environmental racism . Advoc ates and recipient agencies alike
her travel agent earlier in the week to a different flight
World Trade Center towers has been injected into a single 46
legs open . I found it painful . When he finished

INTERVAL -3.097 - -0.041
CONTAINS 47.884%

objectives feeling tired by the time that you reach the final
United are set to bring supporters back into the board room
from above the seven heavens . 6
adding that she is p roud of our work
the First s Cors airs are the guardians of values and

INTERVAL -6.153 - -3.097
CONTAINS 0.490%

1 , 425 voters in Wisconsin . <|endoftext|> John Sm id
hold on until this whole Trump thing blows over .
Yet even these monuments can reinforce myths about slavery . The
) 20 . Chris F us aro ( 117
of people who are just steak . And , there
Token to
Token ID284
Feature activation+9.87e-01

Pos logit contributions
phis+1.247
eatures+1.097
 adolesc+1.079
utonium+1.053
inatory+1.039
Neg logit contributions
ICLE-0.813
cil-0.789
lich-0.788
eting-0.767
wic-0.706
Token the
Token ID262
Feature activation+5.52e-01

Pos logit contributions
phis+0.959
eatures+0.846
 adolesc+0.829
utonium+0.807
inatory+0.793
Neg logit contributions
ICLE-0.691
cil-0.675
lich-0.671
eting-0.657
wic-0.606
Token NFL
Token ID5134
Feature activation-9.63e-01

Pos logit contributions
phis+0.501
eatures+0.439
 adolesc+0.429
utonium+0.417
inatory+0.409
Neg logit contributions
ICLE-0.421
cil-0.412
lich-0.410
eting-0.402
wic-0.374
Token Championship
Token ID10749
Feature activation+1.12e+00

Pos logit contributions
ICLE+0.529
cil+0.514
lich+0.507
eting+0.497
wic+0.445
Neg logit contributions
phis-1.080
eatures-0.974
 adolesc-0.957
utonium-0.935
eries-0.917
Token in
Token ID287
Feature activation+8.48e-01

Pos logit contributions
phis+1.041
eatures+0.912
 adolesc+0.893
utonium+0.868
inatory+0.853
Neg logit contributions
ICLE-0.838
cil-0.820
lich-0.816
eting-0.799
wic-0.742
Token 1949
Token ID24977
Feature activation+6.07e+00

Pos logit contributions
phis+0.455
eatures+0.359
 adolesc+0.344
utonium+0.325
inatory+0.312
Neg logit contributions
ICLE-0.964
cil-0.950
lich-0.949
eting-0.935
wic-0.890
Token
Token ID960
Feature activation+1.70e+00

Pos logit contributions
phis+6.634
eatures+5.810
 adolesc+5.744
utonium+5.626
inatory+5.590
Neg logit contributions
ICLE-3.404
cil-3.288
lich-3.251
eting-3.123
wic-2.862
Tokena
Token ID64
Feature activation+4.72e-01

Pos logit contributions
phis+1.651
eatures+1.452
 adolesc+1.421
utonium+1.387
inatory+1.366
Neg logit contributions
ICLE-1.180
cil-1.149
lich-1.143
eting-1.119
wic-1.033
Token game
Token ID983
Feature activation+6.69e-01

Pos logit contributions
phis+0.411
eatures+0.360
 adolesc+0.351
utonium+0.340
inatory+0.333
Neg logit contributions
ICLE-0.377
cil-0.369
lich-0.367
eting-0.361
wic-0.336
Token in
Token ID287
Feature activation+1.01e+00

Pos logit contributions
phis+0.697
eatures+0.621
 adolesc+0.608
utonium+0.595
inatory+0.585
Neg logit contributions
ICLE-0.420
cil-0.408
lich-0.407
eting-0.397
wic-0.363
Token which
Token ID543
Feature activation+1.79e+00

Pos logit contributions
phis+0.967
eatures+0.855
 adolesc+0.836
utonium+0.816
inatory+0.803
Neg logit contributions
ICLE-0.709
cil-0.689
lich-0.686
eting-0.671
wic-0.625
Token and
Token ID290
Feature activation+5.89e-01

Pos logit contributions
phis+1.393
eatures+1.245
 adolesc+1.227
utonium+1.194
eries+1.182
Neg logit contributions
ICLE-0.721
cil-0.693
lich-0.688
eting-0.664
Acknowled-0.604
Token Walter
Token ID15819
Feature activation-6.74e-01

Pos logit contributions
phis+0.579
eatures+0.512
 adolesc+0.502
utonium+0.487
inatory+0.481
Neg logit contributions
ICLE-0.403
cil-0.392
lich-0.390
eting-0.379
wic-0.353
Token White
Token ID2635
Feature activation-1.43e+00

Pos logit contributions
ICLE+0.477
cil+0.465
lich+0.462
eting+0.452
wic+0.418
Neg logit contributions
phis-0.650
eatures-0.571
 adolesc-0.561
utonium-0.547
inatory-0.538
Token.
Token ID13
Feature activation+2.67e-01

Pos logit contributions
ICLE+0.789
cil+0.764
lich+0.758
eting+0.735
wic+0.663
Neg logit contributions
phis-1.610
eatures-1.445
 adolesc-1.422
utonium-1.389
inatory-1.370
Token In
Token ID554
Feature activation+4.61e-01

Pos logit contributions
phis+0.266
eatures+0.234
 adolesc+0.230
utonium+0.225
inatory+0.221
Neg logit contributions
ICLE-0.179
cil-0.175
lich-0.174
eting-0.169
wic-0.156
Token 1949
Token ID24977
Feature activation+5.95e+00

Pos logit contributions
phis+0.357
eatures+0.304
 adolesc+0.297
utonium+0.286
inatory+0.280
Neg logit contributions
ICLE-0.414
cil-0.406
lich-0.405
eting-0.397
wic-0.375
Token she
Token ID673
Feature activation+1.72e+00

Pos logit contributions
phis+6.674
eatures+5.992
 adolesc+5.856
utonium+5.745
eries+5.687
Neg logit contributions
ICLE-3.131
cil-3.008
lich-2.926
eting-2.813
wic-2.548
Token became
Token ID2627
Feature activation+9.76e-01

Pos logit contributions
phis+1.623
eatures+1.418
 adolesc+1.387
utonium+1.358
inatory+1.334
Neg logit contributions
ICLE-1.260
cil-1.223
lich-1.216
eting-1.188
wic-1.104
Token the
Token ID262
Feature activation+1.45e-01

Pos logit contributions
phis+1.013
eatures+0.903
 adolesc+0.886
utonium+0.864
inatory+0.850
Neg logit contributions
ICLE-0.615
cil-0.599
lich-0.595
eting-0.581
wic-0.532
Token first
Token ID717
Feature activation-1.09e-01

Pos logit contributions
phis+0.123
eatures+0.106
 adolesc+0.104
utonium+0.101
inatory+0.099
Neg logit contributions
ICLE-0.119
cil-0.116
lich-0.116
eting-0.114
wic-0.106
Token woman
Token ID2415
Feature activation+1.64e+00

Pos logit contributions
ICLE+0.072
cil+0.070
lich+0.070
eting+0.068
wic+0.063
Neg logit contributions
phis-0.109
eatures-0.097
 adolesc-0.095
utonium-0.092
inatory-0.091
Token 1800
Token ID21431
Feature activation+1.82e+00

Pos logit contributions
phis+1.708
eatures+1.451
 adolesc+1.431
utonium+1.381
inatory+1.354
Neg logit contributions
ICLE-1.821
cil-1.775
lich-1.763
eting-1.735
Acknowled-1.634
Token at
Token ID379
Feature activation-3.42e-01

Pos logit contributions
phis+2.002
eatures+1.779
 adolesc+1.752
utonium+1.717
inatory+1.693
Neg logit contributions
ICLE-1.045
cil-1.005
lich-1.003
eting-0.974
Acknowled-0.882
Token a
Token ID257
Feature activation+1.28e-01

Pos logit contributions
ICLE+0.219
cil+0.213
lich+0.212
eting+0.206
wic+0.189
Neg logit contributions
phis-0.354
eatures-0.314
 adolesc-0.309
utonium-0.301
inatory-0.296
Token performance
Token ID2854
Feature activation-4.92e-01

Pos logit contributions
phis+0.127
eatures+0.112
 adolesc+0.110
utonium+0.107
inatory+0.105
Neg logit contributions
ICLE-0.088
cil-0.085
lich-0.085
eting-0.083
wic-0.077
Token of
Token ID286
Feature activation-7.36e-01

Pos logit contributions
ICLE+0.307
cil+0.299
lich+0.297
eting+0.290
wic+0.265
Neg logit contributions
phis-0.516
eatures-0.459
 adolesc-0.451
utonium-0.440
inatory-0.433
Token Loc
Token ID15181
Feature activation+5.86e+00

Pos logit contributions
ICLE+0.471
cil+0.459
lich+0.456
eting+0.445
wic+0.408
Neg logit contributions
phis-0.760
eatures-0.676
 adolesc-0.663
utonium-0.646
inatory-0.636
Tokenatell
Token ID7528
Feature activation+2.88e+00

Pos logit contributions
phis+5.560
eatures+4.722
utonium+4.595
 adolesc+4.587
inatory+4.537
Neg logit contributions
ICLE-4.247
lich-4.129
cil-4.107
eting-3.942
Acknowled-3.762
Tokeni
Token ID72
Feature activation+6.49e-01

Pos logit contributions
phis+2.794
eatures+2.439
 adolesc+2.373
utonium+2.327
eries+2.308
Neg logit contributions
ICLE-2.022
lich-1.961
cil-1.960
eting-1.896
Acknowled-1.768
Token's
Token ID338
Feature activation+1.77e+00

Pos logit contributions
phis+0.659
eatures+0.584
 adolesc+0.573
utonium+0.558
inatory+0.549
Neg logit contributions
ICLE-0.426
cil-0.415
lich-0.413
eting-0.403
wic-0.370
Token C
Token ID327
Feature activation+5.71e-01

Pos logit contributions
phis+1.740
eatures+1.534
 adolesc+1.506
utonium+1.466
inatory+1.447
Neg logit contributions
ICLE-1.209
cil-1.174
lich-1.167
eting-1.145
wic-1.056
Token major
Token ID1688
Feature activation-1.66e+00

Pos logit contributions
phis+0.549
eatures+0.482
 adolesc+0.472
utonium+0.461
inatory+0.454
Neg logit contributions
ICLE-0.405
cil-0.395
lich-0.393
eting-0.385
wic-0.356
Token Tub
Token ID42850
Feature activation-1.21e+00

Pos logit contributions
phis+0.220
eatures+0.193
 adolesc+0.190
utonium+0.186
inatory+0.183
Neg logit contributions
ICLE-0.156
cil-0.152
lich-0.151
eting-0.147
wic-0.136
Tokenman
Token ID805
Feature activation+9.59e-02

Pos logit contributions
ICLE+0.793
cil+0.774
lich+0.770
eting+0.752
wic+0.691
Neg logit contributions
phis-1.224
eatures-1.086
 adolesc-1.067
utonium-1.038
inatory-1.022
Token of
Token ID286
Feature activation-2.85e-01

Pos logit contributions
phis+0.102
eatures+0.091
 adolesc+0.089
utonium+0.087
inatory+0.086
Neg logit contributions
ICLE-0.059
cil-0.057
lich-0.057
eting-0.055
wic-0.050
Token Liberia
Token ID33208
Feature activation+2.65e+00

Pos logit contributions
ICLE+0.205
cil+0.201
lich+0.200
eting+0.196
wic+0.181
Neg logit contributions
phis-0.270
eatures-0.238
 adolesc-0.233
utonium-0.227
inatory-0.223
Token in
Token ID287
Feature activation+7.01e-01

Pos logit contributions
phis+2.816
eatures+2.489
 adolesc+2.448
utonium+2.403
inatory+2.366
Neg logit contributions
ICLE-1.614
cil-1.559
lich-1.550
eting-1.510
wic-1.380
Token 1949
Token ID24977
Feature activation+5.75e+00

Pos logit contributions
phis+0.399
eatures+0.318
 adolesc+0.307
utonium+0.291
inatory+0.282
Neg logit contributions
ICLE-0.773
cil-0.761
lich-0.759
eting-0.748
wic-0.713
Token.
Token ID13
Feature activation+9.69e-01

Pos logit contributions
phis+6.180
eatures+5.468
 adolesc+5.390
utonium+5.308
inatory+5.254
Neg logit contributions
ICLE-3.256
cil-3.133
lich-3.097
eting-2.978
wic-2.751
Token She
Token ID1375
Feature activation+1.08e+00

Pos logit contributions
phis+0.972
eatures+0.859
 adolesc+0.843
utonium+0.824
inatory+0.811
Neg logit contributions
ICLE-0.644
cil-0.628
lich-0.624
eting-0.608
wic-0.559
Token also
Token ID635
Feature activation+4.31e-01

Pos logit contributions
phis+1.013
eatures+0.888
 adolesc+0.869
utonium+0.847
inatory+0.832
Neg logit contributions
ICLE-0.795
cil-0.775
lich-0.771
eting-0.755
wic-0.701
Token has
Token ID468
Feature activation+1.12e+00

Pos logit contributions
phis+0.430
eatures+0.380
 adolesc+0.373
utonium+0.363
inatory+0.358
Neg logit contributions
ICLE-0.291
cil-0.283
lich-0.282
eting-0.276
wic-0.254
Token had
Token ID550
Feature activation-1.77e-01

Pos logit contributions
phis+1.066
eatures+0.942
 adolesc+0.925
utonium+0.898
inatory+0.886
Neg logit contributions
ICLE-0.792
cil-0.769
lich-0.765
eting-0.749
wic-0.696
Token antagonist
Token ID34667
Feature activation+3.03e-01

Pos logit contributions
ICLE+0.745
cil+0.727
lich+0.724
eting+0.707
wic+0.650
Neg logit contributions
phis-1.106
eatures-0.980
 adolesc-0.962
utonium-0.936
inatory-0.920
Token of
Token ID286
Feature activation-3.01e-01

Pos logit contributions
phis+0.327
eatures+0.293
 adolesc+0.287
utonium+0.280
inatory+0.277
Neg logit contributions
ICLE-0.179
cil-0.174
lich-0.173
eting-0.168
wic-0.153
Token the
Token ID262
Feature activation+4.74e-01

Pos logit contributions
ICLE+0.201
cil+0.196
lich+0.195
eting+0.191
wic+0.175
Neg logit contributions
phis-0.303
eatures-0.268
 adolesc-0.263
utonium-0.256
inatory-0.252
Token 2008
Token ID3648
Feature activation+3.19e+00

Pos logit contributions
phis+0.407
eatures+0.353
 adolesc+0.345
utonium+0.334
inatory+0.328
Neg logit contributions
ICLE-0.385
cil-0.378
lich-0.376
eting-0.369
wic-0.345
Token film
Token ID2646
Feature activation-6.23e-03

Pos logit contributions
phis+2.920
eatures+2.558
 adolesc+2.498
utonium+2.428
eries+2.404
Neg logit contributions
ICLE-2.369
cil-2.315
lich-2.294
eting-2.258
wic-2.108
Token Kung
Token ID44753
Feature activation+5.53e+00

Pos logit contributions
ICLE+0.004
cil+0.004
lich+0.004
eting+0.004
wic+0.004
Neg logit contributions
phis-0.006
eatures-0.005
 adolesc-0.005
utonium-0.005
inatory-0.005
Token Fu
Token ID13333
Feature activation+1.42e+00

Pos logit contributions
phis+3.506
eatures+2.891
 adolesc+2.840
utonium+2.751
eries+2.654
Neg logit contributions
ICLE-5.602
cil-5.496
lich-5.458
eting-5.405
Acknowled-5.159
Token Panda
Token ID41112
Feature activation+1.67e+00

Pos logit contributions
phis+1.153
eatures+0.993
 adolesc+0.975
utonium+0.946
inatory+0.927
Neg logit contributions
ICLE-1.204
cil-1.178
lich-1.171
eting-1.155
wic-1.085
Token,
Token ID11
Feature activation+1.72e-01

Pos logit contributions
phis+1.810
eatures+1.623
 adolesc+1.595
utonium+1.559
inatory+1.536
Neg logit contributions
ICLE-0.973
cil-0.946
lich-0.936
eting-0.909
Acknowled-0.827
Token is
Token ID318
Feature activation+1.28e+00

Pos logit contributions
phis+0.157
eatures+0.137
 adolesc+0.134
utonium+0.130
inatory+0.128
Neg logit contributions
ICLE-0.130
cil-0.128
lich-0.127
eting-0.125
wic-0.116
Token an
Token ID281
Feature activation-8.86e-02

Pos logit contributions
phis+1.321
eatures+1.176
 adolesc+1.153
utonium+1.125
inatory+1.108
Neg logit contributions
ICLE-0.807
cil-0.784
lich-0.776
eting-0.763
wic-0.698
Token honor
Token ID7522
Feature activation-6.78e-01

Pos logit contributions
phis+0.911
eatures+0.773
 adolesc+0.754
utonium+0.726
inatory+0.710
Neg logit contributions
ICLE-1.088
cil-1.068
lich-1.064
eting-1.046
wic-0.986
Token.[
Token ID3693
Feature activation-1.03e+00

Pos logit contributions
ICLE+0.420
cil+0.408
lich+0.406
eting+0.396
wic+0.361
Neg logit contributions
phis-0.714
eatures-0.636
 adolesc-0.625
utonium-0.609
inatory-0.600
Token53
Token ID4310
Feature activation+2.74e+00

Pos logit contributions
ICLE+0.624
cil+0.608
lich+0.604
eting+0.587
Acknowled+0.534
Neg logit contributions
phis-1.101
eatures-0.984
 adolesc-0.967
utonium-0.943
inatory-0.927
Token]
Token ID60
Feature activation+1.77e-01

Pos logit contributions
phis+2.644
eatures+2.332
 adolesc+2.288
utonium+2.232
inatory+2.198
Neg logit contributions
ICLE-1.911
cil-1.870
lich-1.862
eting-1.813
wic-1.680
Token In
Token ID554
Feature activation+1.43e-02

Pos logit contributions
phis+0.179
eatures+0.159
 adolesc+0.157
utonium+0.152
inatory+0.150
Neg logit contributions
ICLE-0.117
cil-0.114
lich-0.113
eting-0.111
wic-0.102
Token 1989
Token ID11104
Feature activation+5.45e+00

Pos logit contributions
phis+0.008
eatures+0.007
 adolesc+0.007
utonium+0.006
inatory+0.006
Neg logit contributions
ICLE-0.015
cil-0.015
lich-0.015
eting-0.015
wic-0.014
Token Eb
Token ID12119
Feature activation-3.64e-02

Pos logit contributions
phis+5.952
eatures+5.315
 adolesc+5.169
utonium+5.081
eries+5.058
Neg logit contributions
ICLE-3.059
cil-2.948
lich-2.908
eting-2.821
wic-2.559
Tokenony
Token ID1647
Feature activation+5.29e-01

Pos logit contributions
ICLE+0.029
cil+0.028
lich+0.028
eting+0.028
Acknowled+0.026
Neg logit contributions
phis-0.032
eatures-0.027
 adolesc-0.027
utonium-0.026
inatory-0.026
Token Magazine
Token ID11175
Feature activation+2.20e+00

Pos logit contributions
phis+0.512
eatures+0.450
 adolesc+0.441
utonium+0.430
eries+0.423
Neg logit contributions
ICLE-0.372
cil-0.362
lich-0.360
eting-0.352
wic-0.325
Token listed
Token ID5610
Feature activation+1.50e+00

Pos logit contributions
phis+2.169
eatures+1.926
 adolesc+1.871
utonium+1.828
eries+1.811
Neg logit contributions
ICLE-1.492
lich-1.447
cil-1.445
eting-1.417
wic-1.308
Token her
Token ID607
Feature activation+1.63e+00

Pos logit contributions
phis+1.655
eatures+1.480
 adolesc+1.454
utonium+1.419
inatory+1.400
Neg logit contributions
ICLE-0.861
cil-0.835
lich-0.830
eting-0.804
wic-0.731
Token's
Token ID338
Feature activation+1.21e+00

Pos logit contributions
ICLE+1.505
lich+1.468
cil+1.466
eting+1.437
wic+1.295
Neg logit contributions
phis-2.830
eatures-2.536
 adolesc-2.471
utonium-2.423
inatory-2.385
Token speech
Token ID4046
Feature activation-8.95e-01

Pos logit contributions
phis+1.158
eatures+1.018
 adolesc+1.000
utonium+0.972
inatory+0.961
Neg logit contributions
ICLE-0.855
cil-0.836
lich-0.828
eting-0.808
wic-0.748
Token on
Token ID319
Feature activation-2.00e-01

Pos logit contributions
ICLE+0.639
cil+0.624
lich+0.621
eting+0.608
wic+0.562
Neg logit contributions
phis-0.858
eatures-0.755
 adolesc-0.740
utonium-0.720
inatory-0.708
Token the
Token ID262
Feature activation+5.03e-01

Pos logit contributions
ICLE+0.132
cil+0.129
lich+0.128
eting+0.125
wic+0.115
Neg logit contributions
phis-0.202
eatures-0.179
 adolesc-0.176
utonium-0.171
inatory-0.169
Token EU
Token ID4576
Feature activation-5.85e-01

Pos logit contributions
phis+0.491
eatures+0.433
 adolesc+0.424
utonium+0.413
inatory+0.406
Neg logit contributions
ICLE-0.351
cil-0.343
lich-0.341
eting-0.334
wic-0.308
Token looks
Token ID3073
Feature activation+5.45e+00

Pos logit contributions
ICLE+0.440
cil+0.431
lich+0.429
eting+0.420
wic+0.390
Neg logit contributions
phis-0.538
eatures-0.471
 adolesc-0.462
utonium-0.448
inatory-0.440
Token set
Token ID900
Feature activation-4.16e-01

Pos logit contributions
phis+5.125
 adolesc+4.426
eatures+4.357
utonium+4.292
eries+4.253
Neg logit contributions
ICLE-3.831
cil-3.694
lich-3.616
eting-3.560
wic-3.421
Token to
Token ID284
Feature activation+5.21e-01

Pos logit contributions
ICLE+0.272
cil+0.265
lich+0.264
eting+0.258
wic+0.236
Neg logit contributions
phis-0.424
eatures-0.378
 adolesc-0.369
utonium-0.360
inatory-0.354
Token be
Token ID307
Feature activation-1.00e-01

Pos logit contributions
phis+0.426
eatures+0.368
 adolesc+0.359
utonium+0.346
inatory+0.338
Neg logit contributions
ICLE-0.444
cil-0.437
lich-0.434
eting-0.428
wic-0.401
Token a
Token ID257
Feature activation-4.29e-02

Pos logit contributions
ICLE+0.068
cil+0.065
lich+0.065
eting+0.064
wic+0.059
Neg logit contributions
phis-0.100
eatures-0.088
 adolesc-0.087
utonium-0.084
inatory-0.083
Token heated
Token ID16968
Feature activation-2.27e+00

Pos logit contributions
ICLE+0.031
cil+0.031
lich+0.030
eting+0.030
wic+0.028
Neg logit contributions
phis-0.040
eatures-0.035
 adolesc-0.035
utonium-0.034
inatory-0.033
Token
Token ID960
Feature activation+5.83e-01

Pos logit contributions
phis+0.247
eatures+0.219
 adolesc+0.215
utonium+0.210
inatory+0.207
Neg logit contributions
ICLE-0.154
cil-0.150
lich-0.150
eting-0.146
wic-0.134
TokenF
Token ID37
Feature activation+6.48e-01

Pos logit contributions
phis+0.594
eatures+0.526
 adolesc+0.516
utonium+0.504
inatory+0.497
Neg logit contributions
ICLE-0.379
cil-0.368
lich-0.367
eting-0.358
wic-0.329
Tokenifty
Token ID24905
Feature activation+5.34e+00

Pos logit contributions
phis+0.648
eatures+0.575
 adolesc+0.557
utonium+0.550
eries+0.542
Neg logit contributions
ICLE-0.435
lich-0.418
cil-0.418
eting-0.404
wic-0.378
Token/
Token ID14
Feature activation+6.71e-01

Pos logit contributions
phis+5.190
eatures+4.518
utonium+4.394
eries+4.392
 adolesc+4.389
Neg logit contributions
ICLE-3.585
lich-3.470
cil-3.359
eting-3.283
rez-3.101
TokenF
Token ID37
Feature activation+1.19e+00

Pos logit contributions
phis+0.731
eatures+0.650
 adolesc+0.639
utonium+0.627
inatory+0.618
Neg logit contributions
ICLE-0.388
cil-0.377
lich-0.374
eting-0.365
wic-0.333
Tokenifty
Token ID24905
Feature activation+5.42e+00

Pos logit contributions
phis+1.052
eatures+0.919
 adolesc+0.886
utonium+0.879
inatory+0.861
Neg logit contributions
ICLE-0.931
cil-0.902
lich-0.899
eting-0.878
wic-0.826
Token Plan
Token ID5224
Feature activation+5.08e-01

Pos logit contributions
phis+5.205
eatures+4.569
 adolesc+4.426
utonium+4.406
inatory+4.405
Neg logit contributions
ICLE-3.678
lich-3.554
cil-3.431
eting-3.383
ctica-3.176
Token
Token ID198
Feature activation+5.74e-03

Pos logit contributions
phis+0.514
eatures+0.455
 adolesc+0.446
utonium+0.436
inatory+0.429
Neg logit contributions
ICLE-0.335
cil-0.325
lich-0.325
eting-0.316
wic-0.291
Token
Token ID198
Feature activation-2.20e-02

Pos logit contributions
phis+0.006
eatures+0.005
 adolesc+0.005
utonium+0.005
eries+0.005
Neg logit contributions
ICLE-0.004
cil-0.004
lich-0.004
eting-0.004
wic-0.003
TokenThe
Token ID464
Feature activation+6.43e-02

Pos logit contributions
ICLE+0.013
cil+0.013
lich+0.013
eting+0.013
wic+0.012
Neg logit contributions
phis-0.023
eatures-0.021
 adolesc-0.020
utonium-0.020
inatory-0.019
Token council
Token ID6745
Feature activation+1.09e+00

Pos logit contributions
phis+0.061
eatures+0.054
 adolesc+0.053
utonium+0.051
inatory+0.050
Neg logit contributions
ICLE-0.047
cil-0.046
lich-0.045
eting-0.044
wic-0.041
Token this
Token ID428
Feature activation+4.80e-01

Pos logit contributions
phis+1.362
eatures+1.201
 adolesc+1.184
utonium+1.152
inatory+1.132
Neg logit contributions
ICLE-0.927
cil-0.903
lich-0.898
eting-0.874
wic-0.810
Token out
Token ID503
Feature activation-3.84e-01

Pos logit contributions
phis+0.444
eatures+0.389
 adolesc+0.381
utonium+0.370
inatory+0.363
Neg logit contributions
ICLE-0.359
cil-0.352
lich-0.350
eting-0.343
wic-0.318
Token of
Token ID286
Feature activation+2.37e-02

Pos logit contributions
ICLE+0.226
cil+0.220
lich+0.218
eting+0.213
Acknowled+0.193
Neg logit contributions
phis-0.416
eatures-0.372
 adolesc-0.365
utonium-0.356
inatory-0.351
Token control
Token ID1630
Feature activation+1.04e+00

Pos logit contributions
phis+0.023
eatures+0.021
 adolesc+0.020
utonium+0.020
inatory+0.019
Neg logit contributions
ICLE-0.016
cil-0.016
lich-0.016
eting-0.016
wic-0.014
Token e
Token ID304
Feature activation+7.62e-01

Pos logit contributions
phis+1.024
eatures+0.898
 adolesc+0.893
utonium+0.862
inatory+0.847
Neg logit contributions
ICLE-0.722
cil-0.702
lich-0.697
eting-0.684
wic-0.632
Tokengom
Token ID19120
Feature activation+5.38e+00

Pos logit contributions
phis+0.727
eatures+0.635
 adolesc+0.623
utonium+0.608
eries+0.599
Neg logit contributions
ICLE-0.550
cil-0.535
lich-0.532
eting-0.519
Acknowled-0.482
Tokenani
Token ID3216
Feature activation+6.28e-01

Pos logit contributions
phis+3.613
eatures+2.949
 adolesc+2.786
utonium+2.786
inatory+2.769
Neg logit contributions
ICLE-5.344
cil-5.242
lich-5.124
eting-5.098
Acknowled-4.882
Tokenac
Token ID330
Feature activation-1.08e+00

Pos logit contributions
phis+0.683
eatures+0.605
 adolesc+0.593
utonium+0.587
inatory+0.577
Neg logit contributions
ICLE-0.369
cil-0.357
lich-0.353
eting-0.343
Acknowled-0.316
Token,
Token ID11
Feature activation-4.47e-02

Pos logit contributions
ICLE+0.621
cil+0.604
lich+0.601
eting+0.585
wic+0.529
Neg logit contributions
phis-1.179
eatures-1.058
 adolesc-1.038
utonium-1.012
inatory-0.998
Token secret
Token ID3200
Feature activation+7.62e-01

Pos logit contributions
ICLE+0.028
cil+0.027
lich+0.027
eting+0.027
wic+0.024
Neg logit contributions
phis-0.047
eatures-0.042
 adolesc-0.041
utonium-0.040
inatory-0.039
Token police
Token ID1644
Feature activation+3.42e-01

Pos logit contributions
phis+0.734
eatures+0.640
 adolesc+0.633
utonium+0.613
inatory+0.604
Neg logit contributions
ICLE-0.542
cil-0.527
lich-0.524
eting-0.513
Acknowled-0.475
Token this
Token ID428
Feature activation-9.25e-02

Pos logit contributions
ICLE+0.279
cil+0.271
lich+0.269
eting+0.262
wic+0.238
Neg logit contributions
phis-0.519
eatures-0.465
 adolesc-0.457
utonium-0.446
inatory-0.439
Token meant
Token ID4001
Feature activation+6.17e-01

Pos logit contributions
ICLE+0.068
cil+0.067
lich+0.066
eting+0.065
Acknowled+0.060
Neg logit contributions
phis-0.087
eatures-0.076
 adolesc-0.074
utonium-0.073
inatory-0.071
Token a
Token ID257
Feature activation-1.85e-01

Pos logit contributions
phis+0.629
eatures+0.559
 adolesc+0.550
utonium+0.534
inatory+0.527
Neg logit contributions
ICLE-0.401
cil-0.391
lich-0.388
eting-0.379
wic-0.348
Token depression
Token ID8862
Feature activation+7.29e-01

Pos logit contributions
ICLE+0.136
cil+0.134
lich+0.133
eting+0.130
wic+0.121
Neg logit contributions
phis-0.173
eatures-0.152
 adolesc-0.148
utonium-0.145
inatory-0.142
Token in
Token ID287
Feature activation+1.73e-01

Pos logit contributions
phis+0.775
eatures+0.691
 adolesc+0.680
utonium+0.661
inatory+0.657
Neg logit contributions
ICLE-0.442
cil-0.430
lich-0.426
eting-0.414
wic-0.380
Token 1949
Token ID24977
Feature activation+5.34e+00

Pos logit contributions
phis+0.168
eatures+0.148
 adolesc+0.145
utonium+0.142
inatory+0.139
Neg logit contributions
ICLE-0.122
cil-0.119
lich-0.118
eting-0.116
wic-0.107
Token,
Token ID11
Feature activation+5.97e-01

Pos logit contributions
phis+5.569
eatures+4.895
 adolesc+4.849
utonium+4.720
inatory+4.717
Neg logit contributions
ICLE-3.253
cil-3.146
lich-3.108
eting-2.991
wic-2.785
Token or
Token ID393
Feature activation+7.41e-02

Pos logit contributions
phis+0.623
eatures+0.555
 adolesc+0.545
utonium+0.531
inatory+0.523
Neg logit contributions
ICLE-0.374
cil-0.365
lich-0.363
eting-0.354
wic-0.323
Token if
Token ID611
Feature activation-7.98e-02

Pos logit contributions
phis+0.077
eatures+0.068
 adolesc+0.067
utonium+0.066
inatory+0.064
Neg logit contributions
ICLE-0.047
cil-0.046
lich-0.046
eting-0.044
wic-0.041
Token the
Token ID262
Feature activation+2.64e-01

Pos logit contributions
ICLE+0.050
cil+0.048
lich+0.048
eting+0.047
wic+0.043
Neg logit contributions
phis-0.084
eatures-0.075
 adolesc-0.073
utonium-0.072
inatory-0.070
Token entity
Token ID9312
Feature activation+9.10e-01

Pos logit contributions
phis+0.252
eatures+0.222
 adolesc+0.217
utonium+0.212
inatory+0.208
Neg logit contributions
ICLE-0.190
cil-0.186
lich-0.185
eting-0.181
wic-0.167
Token AA
Token ID15923
Feature activation-1.40e+00

Pos logit contributions
phis+1.145
eatures+1.004
 adolesc+0.983
utonium+0.955
inatory+0.939
Neg logit contributions
ICLE-0.918
cil-0.898
lich-0.894
eting-0.875
wic-0.813
TokenFC
Token ID4851
Feature activation+1.11e+00

Pos logit contributions
ICLE+0.683
cil+0.658
lich+0.649
eting+0.630
wic+0.560
Neg logit contributions
phis-1.666
eatures-1.510
 adolesc-1.486
utonium-1.450
inatory-1.430
Token Championships
Token ID24782
Feature activation+2.42e+00

Pos logit contributions
phis+0.843
eatures+0.716
 adolesc+0.699
utonium+0.673
inatory+0.657
Neg logit contributions
ICLE-1.006
cil-0.988
lich-0.983
eting-0.968
wic-0.911
Token.
Token ID13
Feature activation+6.81e-01

Pos logit contributions
phis+2.650
eatures+2.368
 adolesc+2.320
utonium+2.274
eries+2.244
Neg logit contributions
ICLE-1.376
cil-1.337
lich-1.335
eting-1.284
wic-1.177
Token In
Token ID554
Feature activation+5.18e-01

Pos logit contributions
phis+0.675
eatures+0.597
 adolesc+0.585
utonium+0.570
inatory+0.561
Neg logit contributions
ICLE-0.464
cil-0.453
lich-0.450
eting-0.440
wic-0.406
Token 1950
Token ID11445
Feature activation+5.34e+00

Pos logit contributions
phis+0.450
eatures+0.391
 adolesc+0.382
utonium+0.370
inatory+0.363
Neg logit contributions
ICLE-0.417
cil-0.409
lich-0.407
eting-0.399
wic-0.373
Token,
Token ID11
Feature activation+1.50e+00

Pos logit contributions
phis+6.267
eatures+5.641
 adolesc+5.559
utonium+5.438
inatory+5.384
Neg logit contributions
ICLE-2.575
lich-2.477
cil-2.458
eting-2.357
Acknowled-2.129
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
phis+1.544
eatures+1.372
 adolesc+1.347
utonium+1.315
inatory+1.294
Neg logit contributions
ICLE-0.952
cil-0.926
lich-0.923
eting-0.902
wic-0.825
Token NFL
Token ID5134
Feature activation-9.39e-01

Pos logit contributions
phis+1.117
eatures+0.974
 adolesc+0.953
utonium+0.924
inatory+0.907
Neg logit contributions
ICLE-0.974
cil-0.953
lich-0.949
eting-0.931
wic-0.867
Token finally
Token ID3443
Feature activation+1.15e+00

Pos logit contributions
ICLE+0.691
cil+0.677
lich+0.668
eting+0.659
wic+0.609
Neg logit contributions
phis-0.880
eatures-0.774
 adolesc-0.762
utonium-0.735
inatory-0.719
Token took
Token ID1718
Feature activation+1.48e+00

Pos logit contributions
phis+1.102
eatures+0.968
 adolesc+0.947
utonium+0.925
inatory+0.909
Neg logit contributions
ICLE-0.815
cil-0.792
lich-0.790
eting-0.772
wic-0.713
Token
Token ID198
Feature activation-5.37e-01

Pos logit contributions
ICLE+0.428
cil+0.416
lich+0.413
eting+0.403
wic+0.373
Neg logit contributions
phis-0.620
eatures-0.534
 adolesc-0.530
utonium-0.523
eries-0.518
TokenCity
Token ID14941
Feature activation-5.48e-01

Pos logit contributions
ICLE+0.331
cil+0.322
lich+0.321
eting+0.313
wic+0.286
Neg logit contributions
phis-0.565
eatures-0.502
 adolesc-0.493
utonium-0.482
inatory-0.476
Token Council
Token ID4281
Feature activation+2.40e-01

Pos logit contributions
ICLE+0.373
cil+0.364
lich+0.361
eting+0.354
wic+0.326
Neg logit contributions
phis-0.544
eatures-0.482
 adolesc-0.474
utonium-0.461
inatory-0.452
Token
Token ID960
Feature activation+5.83e-01

Pos logit contributions
phis+0.247
eatures+0.219
 adolesc+0.215
utonium+0.210
inatory+0.207
Neg logit contributions
ICLE-0.154
cil-0.150
lich-0.150
eting-0.146
wic-0.134
TokenF
Token ID37
Feature activation+6.48e-01

Pos logit contributions
phis+0.594
eatures+0.526
 adolesc+0.516
utonium+0.504
inatory+0.497
Neg logit contributions
ICLE-0.379
cil-0.368
lich-0.367
eting-0.358
wic-0.329
Tokenifty
Token ID24905
Feature activation+5.34e+00

Pos logit contributions
phis+0.648
eatures+0.575
 adolesc+0.557
utonium+0.550
eries+0.542
Neg logit contributions
ICLE-0.435
lich-0.418
cil-0.418
eting-0.404
wic-0.378
Token/
Token ID14
Feature activation+6.71e-01

Pos logit contributions
phis+5.190
eatures+4.518
utonium+4.394
eries+4.392
 adolesc+4.389
Neg logit contributions
ICLE-3.585
lich-3.470
cil-3.359
eting-3.283
rez-3.101
TokenF
Token ID37
Feature activation+1.19e+00

Pos logit contributions
phis+0.731
eatures+0.650
 adolesc+0.639
utonium+0.627
inatory+0.618
Neg logit contributions
ICLE-0.388
cil-0.377
lich-0.374
eting-0.365
wic-0.333
Tokenifty
Token ID24905
Feature activation+5.42e+00

Pos logit contributions
phis+1.052
eatures+0.919
 adolesc+0.886
utonium+0.879
inatory+0.861
Neg logit contributions
ICLE-0.931
cil-0.902
lich-0.899
eting-0.878
wic-0.826
Token Plan
Token ID5224
Feature activation+5.08e-01

Pos logit contributions
phis+5.205
eatures+4.569
 adolesc+4.426
utonium+4.406
inatory+4.405
Neg logit contributions
ICLE-3.678
lich-3.554
cil-3.431
eting-3.383
ctica-3.176
Token
Token ID198
Feature activation+5.74e-03

Pos logit contributions
phis+0.514
eatures+0.455
 adolesc+0.446
utonium+0.436
inatory+0.429
Neg logit contributions
ICLE-0.335
cil-0.325
lich-0.325
eting-0.316
wic-0.291
Token-
Token ID12
Feature activation-1.80e-01

Pos logit contributions
ICLE+0.310
cil+0.300
lich+0.298
eting+0.290
wic+0.260
Neg logit contributions
phis-0.675
eatures-0.608
 adolesc-0.598
utonium-0.584
inatory-0.576
Tokenyear
Token ID1941
Feature activation+1.16e+00

Pos logit contributions
ICLE+0.170
cil+0.167
lich+0.166
eting+0.164
wic+0.155
Neg logit contributions
phis-0.131
eatures-0.109
 adolesc-0.106
utonium-0.103
inatory-0.101
Token deal
Token ID1730
Feature activation+6.37e-01

Pos logit contributions
phis+0.991
eatures+0.860
 adolesc+0.843
utonium+0.816
eries+0.804
Neg logit contributions
ICLE-0.937
cil-0.918
lich-0.913
eting-0.896
wic-0.839
Token with
Token ID351
Feature activation+3.66e-01

Pos logit contributions
phis+0.613
eatures+0.540
 adolesc+0.529
utonium+0.515
inatory+0.507
Neg logit contributions
ICLE-0.451
cil-0.440
lich-0.438
eting-0.429
wic-0.396
Token the
Token ID262
Feature activation+5.10e-01

Pos logit contributions
phis+0.370
eatures+0.329
 adolesc+0.322
utonium+0.314
inatory+0.309
Neg logit contributions
ICLE-0.241
cil-0.235
lich-0.234
eting-0.228
wic-0.210
Token Demons
Token ID38539
Feature activation+5.20e+00

Pos logit contributions
phis+0.444
eatures+0.387
 adolesc+0.378
utonium+0.366
inatory+0.359
Neg logit contributions
ICLE-0.407
cil-0.399
lich-0.397
eting-0.390
wic-0.364
Token is
Token ID318
Feature activation+1.44e+00

Pos logit contributions
phis+4.743
eatures+4.087
 adolesc+3.992
utonium+3.944
eries+3.919
Neg logit contributions
ICLE-3.833
cil-3.693
lich-3.646
eting-3.626
ctica-3.375
Token reportedly
Token ID7478
Feature activation+1.04e+00

Pos logit contributions
phis+1.388
eatures+1.228
 adolesc+1.204
utonium+1.169
inatory+1.156
Neg logit contributions
ICLE-1.008
cil-0.981
lich-0.970
eting-0.956
wic-0.885
Token worth
Token ID2861
Feature activation+1.04e+00

Pos logit contributions
phis+0.970
eatures+0.852
 adolesc+0.836
utonium+0.811
inatory+0.799
Neg logit contributions
ICLE-0.765
cil-0.746
lich-0.739
eting-0.727
wic-0.675
Token $
Token ID720
Feature activation+5.07e-01

Pos logit contributions
phis+1.051
eatures+0.930
 adolesc+0.916
utonium+0.890
inatory+0.878
Neg logit contributions
ICLE-0.686
cil-0.667
lich-0.662
eting-0.649
wic-0.597
Token750
Token ID15426
Feature activation+7.49e-01

Pos logit contributions
phis+0.561
eatures+0.495
 adolesc+0.488
utonium+0.483
eries+0.478
Neg logit contributions
ICLE-0.281
cil-0.273
lich-0.270
eting-0.265
wic-0.238
TokenRussia
Token ID16347
Feature activation+5.51e-01

Pos logit contributions
ICLE+0.251
cil+0.244
lich+0.243
eting+0.238
wic+0.218
Neg logit contributions
phis-0.380
eatures-0.336
 adolesc-0.330
utonium-0.321
inatory-0.316
Token has
Token ID468
Feature activation+1.64e+00

Pos logit contributions
phis+0.546
eatures+0.483
 adolesc+0.474
utonium+0.461
inatory+0.453
Neg logit contributions
ICLE-0.375
cil-0.367
lich-0.365
eting-0.357
wic-0.329
Token accused
Token ID5371
Feature activation+1.02e-01

Pos logit contributions
phis+1.613
eatures+1.425
 adolesc+1.397
utonium+1.366
inatory+1.342
Neg logit contributions
ICLE-1.118
cil-1.089
lich-1.083
eting-1.061
wic-0.978
Token Ukraine
Token ID7049
Feature activation-5.21e-02

Pos logit contributions
phis+0.100
eatures+0.088
 adolesc+0.087
utonium+0.084
inatory+0.083
Neg logit contributions
ICLE-0.071
cil-0.069
lich-0.069
eting-0.067
wic-0.062
Token of
Token ID286
Feature activation-9.74e-01

Pos logit contributions
ICLE+0.030
cil+0.029
lich+0.029
eting+0.028
wic+0.026
Neg logit contributions
phis-0.057
eatures-0.051
 adolesc-0.050
utonium-0.049
inatory-0.048
Token stealing
Token ID16568
Feature activation+5.18e+00

Pos logit contributions
ICLE+0.666
cil+0.654
lich+0.648
eting+0.638
Acknowled+0.587
Neg logit contributions
phis-0.960
eatures-0.853
 adolesc-0.834
utonium-0.805
inatory-0.790
Token gas
Token ID3623
Feature activation+2.61e-01

Pos logit contributions
phis+4.881
eatures+4.306
 adolesc+4.228
utonium+4.171
inatory+4.087
Neg logit contributions
ICLE-3.634
lich-3.526
cil-3.522
eting-3.385
wic-3.232
Token meant
Token ID4001
Feature activation+1.65e+00

Pos logit contributions
phis+0.264
eatures+0.234
 adolesc+0.229
utonium+0.224
inatory+0.220
Neg logit contributions
ICLE-0.172
cil-0.168
lich-0.167
eting-0.163
wic-0.150
Token for
Token ID329
Feature activation+3.06e-01

Pos logit contributions
phis+1.743
eatures+1.550
 adolesc+1.526
utonium+1.490
inatory+1.466
Neg logit contributions
ICLE-1.020
cil-0.990
lich-0.985
eting-0.960
wic-0.876
Token Europe
Token ID2031
Feature activation-1.08e+00

Pos logit contributions
phis+0.298
eatures+0.263
 adolesc+0.258
utonium+0.251
inatory+0.246
Neg logit contributions
ICLE-0.213
cil-0.208
lich-0.207
eting-0.203
wic-0.187
Token Russian
Token ID3394
Feature activation-3.81e-01

Pos logit contributions
ICLE+0.633
cil+0.615
lich+0.611
eting+0.596
wic+0.541
Neg logit contributions
phis-1.165
eatures-1.043
 adolesc-1.024
utonium-0.999
inatory-0.985
Token buildup
Token ID40502
Feature activation-9.93e-01

Pos logit contributions
ICLE+0.817
cil+0.803
lich+0.801
eting+0.787
Acknowled+0.731
Neg logit contributions
phis-0.982
eatures-0.867
 adolesc-0.842
utonium-0.820
inatory-0.804
Token.
Token ID13
Feature activation+1.68e-01

Pos logit contributions
ICLE+0.620
cil+0.604
lich+0.600
eting+0.586
wic+0.535
Neg logit contributions
phis-1.040
eatures-0.927
 adolesc-0.910
utonium-0.887
inatory-0.873
Token Between
Token ID14307
Feature activation+7.22e-01

Pos logit contributions
phis+0.166
eatures+0.147
 adolesc+0.144
utonium+0.140
inatory+0.138
Neg logit contributions
ICLE-0.115
cil-0.112
lich-0.111
eting-0.109
wic-0.100
Token 1946
Token ID22717
Feature activation+9.05e-01

Pos logit contributions
phis+0.713
eatures+0.630
 adolesc+0.618
utonium+0.602
inatory+0.592
Neg logit contributions
ICLE-0.494
cil-0.482
lich-0.479
eting-0.468
wic-0.432
Token and
Token ID290
Feature activation+1.36e+00

Pos logit contributions
phis+1.000
eatures+0.900
 adolesc+0.884
utonium+0.863
inatory+0.848
Neg logit contributions
ICLE-0.511
cil-0.496
lich-0.495
eting-0.483
wic-0.434
Token 1949
Token ID24977
Feature activation+5.17e+00

Pos logit contributions
phis+0.700
eatures+0.539
 adolesc+0.520
utonium+0.488
inatory+0.472
Neg logit contributions
ICLE-1.578
cil-1.554
lich-1.545
eting-1.527
wic-1.463
Token,
Token ID11
Feature activation+6.95e-01

Pos logit contributions
phis+5.959
eatures+5.386
 adolesc+5.275
utonium+5.138
inatory+5.121
Neg logit contributions
ICLE-2.574
lich-2.463
cil-2.453
eting-2.354
Acknowled-2.156
Token the
Token ID262
Feature activation+5.00e-01

Pos logit contributions
phis+0.727
eatures+0.648
 adolesc+0.636
utonium+0.620
inatory+0.611
Neg logit contributions
ICLE-0.433
cil-0.422
lich-0.420
eting-0.410
wic-0.375
Token Rams
Token ID16077
Feature activation+3.65e-01

Pos logit contributions
phis+0.458
eatures+0.401
 adolesc+0.392
utonium+0.381
inatory+0.373
Neg logit contributions
ICLE-0.380
cil-0.371
lich-0.369
eting-0.363
wic-0.336
Token and
Token ID290
Feature activation+8.15e-01

Pos logit contributions
phis+0.365
eatures+0.324
 adolesc+0.317
utonium+0.309
inatory+0.304
Neg logit contributions
ICLE-0.245
cil-0.239
lich-0.238
eting-0.232
wic-0.214
Token their
Token ID511
Feature activation+1.08e+00

Pos logit contributions
phis+0.795
eatures+0.701
 adolesc+0.687
utonium+0.668
inatory+0.658
Neg logit contributions
ICLE-0.565
cil-0.552
lich-0.549
eting-0.536
wic-0.496
Token 30
Token ID1542
Feature activation+6.65e-02

Pos logit contributions
phis+0.551
eatures+0.480
 adolesc+0.473
utonium+0.460
inatory+0.453
Neg logit contributions
ICLE-0.440
cil-0.430
lich-0.427
eting-0.417
wic-0.390
Token,
Token ID11
Feature activation+4.03e-01

Pos logit contributions
phis+0.081
eatures+0.074
 adolesc+0.072
utonium+0.071
inatory+0.070
Neg logit contributions
ICLE-0.030
cil-0.029
lich-0.029
eting-0.028
wic-0.024
Token 1964
Token ID17575
Feature activation+2.31e+00

Pos logit contributions
phis+0.169
eatures+0.123
 adolesc+0.116
utonium+0.107
inatory+0.101
Neg logit contributions
ICLE-0.504
cil-0.498
lich-0.497
eting-0.491
wic-0.470
Token
Token ID960
Feature activation+8.09e-01

Pos logit contributions
phis+2.636
eatures+2.357
 adolesc+2.331
utonium+2.279
inatory+2.248
Neg logit contributions
ICLE-1.220
cil-1.177
lich-1.159
eting-1.124
wic-1.022
Tokenf
Token ID69
Feature activation+4.67e-01

Pos logit contributions
phis+0.806
eatures+0.712
 adolesc+0.698
utonium+0.681
inatory+0.670
Neg logit contributions
ICLE-0.545
cil-0.530
lich-0.527
eting-0.516
wic-0.476
Tokenifty
Token ID24905
Feature activation+5.15e+00

Pos logit contributions
phis+0.352
eatures+0.300
 adolesc+0.288
utonium+0.283
inatory+0.275
Neg logit contributions
ICLE-0.429
cil-0.419
lich-0.417
eting-0.409
wic-0.387
Token years
Token ID812
Feature activation+1.27e+00

Pos logit contributions
phis+5.092
eatures+4.484
 adolesc+4.430
utonium+4.334
inatory+4.324
Neg logit contributions
ICLE-3.362
lich-3.274
cil-3.249
eting-3.123
wic-2.955
Token ago
Token ID2084
Feature activation+2.08e+00

Pos logit contributions
phis+1.267
eatures+1.122
 adolesc+1.103
utonium+1.074
inatory+1.058
Neg logit contributions
ICLE-0.844
cil-0.823
lich-0.819
eting-0.796
wic-0.738
Token last
Token ID938
Feature activation+1.62e+00

Pos logit contributions
phis+2.293
eatures+2.042
 adolesc+2.017
utonium+1.968
inatory+1.946
Neg logit contributions
ICLE-1.181
cil-1.148
lich-1.129
eting-1.097
wic-1.005
Token week
Token ID1285
Feature activation+1.67e+00

Pos logit contributions
phis+1.380
eatures+1.197
 adolesc+1.173
utonium+1.136
inatory+1.117
Neg logit contributions
ICLE-1.323
cil-1.297
lich-1.283
eting-1.255
wic-1.178
Token.
Token ID13
Feature activation+7.59e-01

Pos logit contributions
phis+1.884
eatures+1.685
 adolesc+1.659
utonium+1.625
inatory+1.603
Neg logit contributions
ICLE-0.898
cil-0.868
lich-0.855
eting-0.827
wic-0.755
Token nearly
Token ID3016
Feature activation-4.48e-01

Pos logit contributions
phis+0.178
eatures+0.158
 adolesc+0.155
utonium+0.151
inatory+0.148
Neg logit contributions
ICLE-0.119
cil-0.116
lich-0.115
eting-0.113
wic-0.104
Token 70
Token ID4317
Feature activation+1.45e+00

Pos logit contributions
ICLE+0.300
cil+0.292
lich+0.290
eting+0.284
wic+0.262
Neg logit contributions
phis-0.448
eatures-0.396
 adolesc-0.390
utonium-0.379
inatory-0.373
Token%
Token ID4
Feature activation+8.19e-01

Pos logit contributions
phis+1.574
eatures+1.411
 adolesc+1.396
utonium+1.363
inatory+1.343
Neg logit contributions
ICLE-0.836
cil-0.805
lich-0.798
eting-0.778
wic-0.718
Token of
Token ID286
Feature activation-1.39e-01

Pos logit contributions
phis+0.900
eatures+0.806
 adolesc+0.791
utonium+0.773
inatory+0.762
Neg logit contributions
ICLE-0.468
cil-0.456
lich-0.452
eting-0.440
Acknowled-0.397
Token South
Token ID2520
Feature activation+2.68e+00

Pos logit contributions
ICLE+0.093
cil+0.090
lich+0.090
eting+0.088
wic+0.081
Neg logit contributions
phis-0.139
eatures-0.123
 adolesc-0.121
utonium-0.118
inatory-0.116
Token Koreans
Token ID25999
Feature activation+5.14e+00

Pos logit contributions
phis+2.186
eatures+1.881
 adolesc+1.843
utonium+1.778
inatory+1.746
Neg logit contributions
ICLE-2.283
cil-2.228
lich-2.222
eting-2.181
wic-2.048
Token who
Token ID508
Feature activation+1.18e+00

Pos logit contributions
phis+4.645
 adolesc+4.022
eatures+4.019
utonium+3.904
eries+3.874
Neg logit contributions
ICLE-3.816
lich-3.666
cil-3.627
eting-3.584
wic-3.410
Token were
Token ID547
Feature activation+5.55e-01

Pos logit contributions
phis+1.098
eatures+0.958
 adolesc+0.940
utonium+0.917
eries+0.900
Neg logit contributions
ICLE-0.877
cil-0.850
lich-0.848
eting-0.832
wic-0.774
Token awarded
Token ID11343
Feature activation+1.48e+00

Pos logit contributions
phis+0.541
eatures+0.477
 adolesc+0.468
utonium+0.455
inatory+0.448
Neg logit contributions
ICLE-0.387
cil-0.378
lich-0.376
eting-0.368
wic-0.339
Token PhD
Token ID16394
Feature activation+9.31e-01

Pos logit contributions
phis+1.506
eatures+1.339
 adolesc+1.323
utonium+1.288
inatory+1.267
Neg logit contributions
ICLE-0.956
cil-0.929
lich-0.922
eting-0.905
wic-0.832
Tokens
Token ID82
Feature activation+2.20e-01

Pos logit contributions
phis+0.730
eatures+0.623
 adolesc+0.608
utonium+0.586
inatory+0.573
Neg logit contributions
ICLE-0.827
cil-0.812
lich-0.808
eting-0.795
wic-0.747
Token,
Token ID11
Feature activation-1.73e-01

Pos logit contributions
phis+1.115
eatures+0.983
 adolesc+0.964
utonium+0.941
eries+0.928
Neg logit contributions
ICLE-0.746
cil-0.725
lich-0.720
eting-0.706
Acknowled-0.647
Token Mi
Token ID13756
Feature activation-1.36e-01

Pos logit contributions
ICLE+0.124
cil+0.121
lich+0.121
eting+0.118
wic+0.110
Neg logit contributions
phis-0.166
eatures-0.146
 adolesc-0.143
utonium-0.139
inatory-0.137
Token Coc
Token ID18490
Feature activation+2.49e+00

Pos logit contributions
ICLE+0.094
cil+0.092
lich+0.091
eting+0.089
wic+0.082
Neg logit contributions
phis-0.134
eatures-0.118
 adolesc-0.115
utonium-0.113
inatory-0.111
Tokenina
Token ID1437
Feature activation+2.93e-01

Pos logit contributions
phis+2.361
eatures+2.056
 adolesc+2.006
utonium+1.975
eries+1.947
Neg logit contributions
ICLE-1.795
lich-1.746
cil-1.737
eting-1.712
Acknowled-1.598
Token,
Token ID11
Feature activation-1.20e-01

Pos logit contributions
phis+0.313
eatures+0.279
 adolesc+0.274
utonium+0.268
inatory+0.264
Neg logit contributions
ICLE-0.176
cil-0.171
lich-0.170
eting-0.166
Acknowled-0.150
Token PK
Token ID29673
Feature activation+5.10e+00

Pos logit contributions
ICLE+0.085
cil+0.083
lich+0.083
eting+0.081
wic+0.075
Neg logit contributions
phis-0.114
eatures-0.101
 adolesc-0.099
utonium-0.096
inatory-0.094
Token's
Token ID338
Feature activation+1.97e+00

Pos logit contributions
phis+4.998
eatures+4.296
 adolesc+4.233
eries+4.177
utonium+4.175
Neg logit contributions
ICLE-3.391
cil-3.301
lich-3.287
eting-3.227
Acknowled-2.993
Token Blue
Token ID4518
Feature activation-7.62e-01

Pos logit contributions
phis+2.000
eatures+1.758
 adolesc+1.729
utonium+1.692
eries+1.670
Neg logit contributions
ICLE-1.289
cil-1.248
lich-1.247
eting-1.219
Acknowled-1.119
Token Water
Token ID5638
Feature activation+1.81e-01

Pos logit contributions
ICLE+0.525
cil+0.513
lich+0.510
eting+0.499
wic+0.460
Neg logit contributions
phis-0.748
eatures-0.661
 adolesc-0.648
utonium-0.631
inatory-0.620
Token Grill
Token ID34814
Feature activation-3.19e-01

Pos logit contributions
phis+0.183
eatures+0.161
 adolesc+0.158
utonium+0.155
eries+0.153
Neg logit contributions
ICLE-0.120
cil-0.117
lich-0.116
eting-0.114
Acknowled-0.104
Token
Token ID198
Feature activation-4.07e-02

Pos logit contributions
ICLE+0.198
cil+0.193
lich+0.192
eting+0.187
wic+0.171
Neg logit contributions
phis-0.334
eatures-0.298
 adolesc-0.293
utonium-0.285
inatory-0.281
Token spores
Token ID47306
Feature activation+1.53e+00

Pos logit contributions
ICLE+0.973
cil+0.949
lich+0.944
eting+0.922
wic+0.847
Neg logit contributions
phis-1.502
eatures-1.333
 adolesc-1.308
utonium-1.274
inatory-1.254
Token over
Token ID625
Feature activation+1.15e+00

Pos logit contributions
phis+1.527
eatures+1.345
 adolesc+1.324
utonium+1.297
inatory+1.273
Neg logit contributions
ICLE-1.025
cil-0.994
lich-0.989
eting-0.961
wic-0.887
Token Tokyo
Token ID11790
Feature activation+1.17e+00

Pos logit contributions
phis+1.082
eatures+0.948
 adolesc+0.931
utonium+0.905
inatory+0.889
Neg logit contributions
ICLE-0.841
cil-0.825
lich-0.819
eting-0.795
wic-0.744
Token.
Token ID13
Feature activation+6.08e-01

Pos logit contributions
phis+1.201
eatures+1.065
 adolesc+1.049
utonium+1.021
inatory+1.006
Neg logit contributions
ICLE-0.741
cil-0.723
lich-0.719
eting-0.698
wic-0.643
Token In
Token ID554
Feature activation+3.92e-01

Pos logit contributions
phis+0.607
eatures+0.536
 adolesc+0.527
utonium+0.515
inatory+0.505
Neg logit contributions
ICLE-0.409
cil-0.399
lich-0.396
eting-0.387
wic-0.357
Token 1998
Token ID7795
Feature activation+5.07e+00

Pos logit contributions
phis+0.310
eatures+0.266
 adolesc+0.259
utonium+0.250
inatory+0.245
Neg logit contributions
ICLE-0.345
cil-0.339
lich-0.338
eting-0.332
wic-0.312
Token,
Token ID11
Feature activation+1.14e+00

Pos logit contributions
phis+5.681
eatures+5.013
 adolesc+4.979
utonium+4.928
eries+4.815
Neg logit contributions
ICLE-2.728
cil-2.632
lich-2.554
eting-2.487
wic-2.269
Token terrorism
Token ID8649
Feature activation-9.70e-02

Pos logit contributions
phis+1.172
eatures+1.038
 adolesc+1.021
utonium+1.000
inatory+0.979
Neg logit contributions
ICLE-0.739
cil-0.719
lich-0.712
eting-0.697
wic-0.641
Token experts
Token ID6154
Feature activation-1.07e-01

Pos logit contributions
ICLE+0.067
cil+0.065
lich+0.065
eting+0.064
wic+0.059
Neg logit contributions
phis-0.095
eatures-0.084
 adolesc-0.082
utonium-0.080
inatory-0.079
Token warn
Token ID9828
Feature activation-6.62e-01

Pos logit contributions
ICLE+0.073
cil+0.071
lich+0.071
eting+0.070
wic+0.064
Neg logit contributions
phis-0.105
eatures-0.093
 adolesc-0.092
utonium-0.089
inatory-0.088
Token about
Token ID546
Feature activation-3.48e-01

Pos logit contributions
ICLE+0.408
cil+0.397
lich+0.394
eting+0.385
wic+0.351
Neg logit contributions
phis-0.699
eatures-0.623
 adolesc-0.612
utonium-0.597
inatory-0.588
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
ICLE+0.554
cil+0.540
lich+0.537
eting+0.525
wic+0.483
Neg logit contributions
phis-0.817
eatures-0.723
 adolesc-0.710
utonium-0.692
inatory-0.680
Token hands
Token ID2832
Feature activation+1.82e+00

Pos logit contributions
phis+0.223
eatures+0.201
 adolesc+0.198
utonium+0.193
inatory+0.191
Neg logit contributions
ICLE-0.103
cil-0.100
lich-0.099
eting-0.096
wic-0.086
Token of
Token ID286
Feature activation+6.12e-02

Pos logit contributions
phis+1.883
eatures+1.626
 adolesc+1.612
eries+1.604
utonium+1.604
Neg logit contributions
ICLE-1.134
cil-1.091
lich-1.080
eting-1.052
wic-0.974
Token the
Token ID262
Feature activation+6.80e-01

Pos logit contributions
phis+0.060
eatures+0.053
 adolesc+0.052
utonium+0.051
inatory+0.050
Neg logit contributions
ICLE-0.042
cil-0.041
lich-0.041
eting-0.040
wic-0.037
Token North
Token ID2258
Feature activation+3.00e-01

Pos logit contributions
phis+0.570
eatures+0.491
 adolesc+0.481
utonium+0.466
inatory+0.457
Neg logit contributions
ICLE-0.567
cil-0.555
lich-0.552
eting-0.543
wic-0.509
Token Koreans
Token ID25999
Feature activation+5.05e+00

Pos logit contributions
phis+0.260
eatures+0.226
 adolesc+0.221
utonium+0.215
inatory+0.210
Neg logit contributions
ICLE-0.242
cil-0.236
lich-0.235
eting-0.231
wic-0.216
Token ensured
Token ID30169
Feature activation+8.28e-01

Pos logit contributions
phis+4.734
eatures+4.109
 adolesc+4.030
utonium+3.978
eries+3.906
Neg logit contributions
ICLE-3.606
lich-3.489
cil-3.476
eting-3.410
wic-3.145
Token that
Token ID326
Feature activation+1.22e-01

Pos logit contributions
phis+0.874
eatures+0.778
 adolesc+0.769
utonium+0.749
eries+0.736
Neg logit contributions
ICLE-0.508
cil-0.491
lich-0.489
eting-0.479
wic-0.435
Token no
Token ID645
Feature activation-4.61e-01

Pos logit contributions
phis+0.135
eatures+0.121
 adolesc+0.120
utonium+0.117
eries+0.115
Neg logit contributions
ICLE-0.069
cil-0.067
lich-0.066
eting-0.065
wic-0.059
Token other
Token ID584
Feature activation-8.09e-01

Pos logit contributions
ICLE+0.316
cil+0.309
lich+0.307
eting+0.300
wic+0.277
Neg logit contributions
phis-0.454
eatures-0.401
 adolesc-0.393
utonium-0.383
inatory-0.377
Token outcome
Token ID8055
Feature activation-6.62e-01

Pos logit contributions
ICLE+0.559
cil+0.547
lich+0.544
eting+0.532
wic+0.490
Neg logit contributions
phis-0.792
eatures-0.700
 adolesc-0.685
utonium-0.668
inatory-0.657
TokenC
Token ID34
Feature activation+3.04e-01

Pos logit contributions
ICLE+0.417
cil+0.407
lich+0.404
eting+0.396
wic+0.362
Neg logit contributions
phis-0.664
eatures-0.582
 adolesc-0.571
utonium-0.561
eries-0.555
Tokenelt
Token ID2120
Feature activation-3.63e-01

Pos logit contributions
phis+0.345
eatures+0.305
utonium+0.302
eries+0.297
inatory+0.297
Neg logit contributions
ICLE-0.157
lich-0.153
cil-0.152
eting-0.146
Acknowled-0.139
Tokenics
Token ID873
Feature activation-2.24e+00

Pos logit contributions
ICLE+0.196
cil+0.192
lich+0.189
eting+0.186
Acknowled+0.169
Neg logit contributions
phis-0.408
eatures-0.366
 adolesc-0.356
utonium-0.350
eries-0.350
Token coach
Token ID3985
Feature activation-4.02e-01

Pos logit contributions
ICLE+1.605
cil+1.568
lich+1.564
eting+1.529
wic+1.413
Neg logit contributions
phis-2.140
eatures-1.886
 adolesc-1.850
utonium-1.802
inatory-1.769
Token Brad
Token ID8114
Feature activation-2.53e+00

Pos logit contributions
ICLE+0.301
lich+0.296
cil+0.295
eting+0.288
wic+0.268
Neg logit contributions
phis-0.364
eatures-0.318
 adolesc-0.311
utonium-0.303
eries-0.300
Token Stevens
Token ID20019
Feature activation-6.15e+00

Pos logit contributions
ICLE+0.442
cil+0.420
lich+0.406
eting+0.369
wic+0.227
Neg logit contributions
phis-3.789
eatures-3.502
 adolesc-3.475
utonium-3.382
inatory-3.366
Token isn
Token ID2125
Feature activation+1.14e+00

Pos logit contributions
lich+3.655
ICLE+3.624
cil+3.617
eting+3.529
wic+3.207
Neg logit contributions
phis-6.452
eatures-5.888
 adolesc-5.772
utonium-5.538
inatory-5.477
Token't
Token ID470
Feature activation+2.85e-01

Pos logit contributions
phis+0.827
eatures+0.652
utonium+0.652
eries+0.649
 adolesc+0.646
Neg logit contributions
ICLE-1.062
cil-1.033
lich-1.025
eting-1.012
wic-0.961
Token sure
Token ID1654
Feature activation-2.12e+00

Pos logit contributions
phis+0.282
eatures+0.248
 adolesc+0.244
utonium+0.237
eries+0.233
Neg logit contributions
ICLE-0.195
cil-0.189
lich-0.188
eting-0.184
wic-0.170
Token if
Token ID611
Feature activation-1.38e+00

Pos logit contributions
ICLE+1.250
cil+1.215
lich+1.208
eting+1.177
wic+1.068
Neg logit contributions
phis-2.302
eatures-2.058
 adolesc-2.023
utonium-1.974
inatory-1.945
Token any
Token ID597
Feature activation-1.33e+00

Pos logit contributions
ICLE+0.926
cil+0.903
lich+0.898
eting+0.878
wic+0.807
Neg logit contributions
phis-1.380
eatures-1.221
 adolesc-1.198
utonium-1.166
inatory-1.148
Token a
Token ID257
Feature activation+3.19e-01

Pos logit contributions
ICLE+0.516
cil+0.502
lich+0.499
eting+0.486
wic+0.444
Neg logit contributions
phis-0.890
eatures-0.793
 adolesc-0.779
utonium-0.760
inatory-0.749
Token heated
Token ID16968
Feature activation-1.88e+00

Pos logit contributions
phis+0.309
eatures+0.271
 adolesc+0.266
utonium+0.259
inatory+0.255
Neg logit contributions
ICLE-0.225
cil-0.220
lich-0.218
eting-0.213
wic-0.197
Token exchange
Token ID5163
Feature activation+3.41e-01

Pos logit contributions
ICLE+1.293
cil+1.263
lich+1.259
eting+1.236
wic+1.133
Neg logit contributions
phis-1.845
eatures-1.636
 adolesc-1.597
utonium-1.561
inatory-1.530
Token,
Token ID11
Feature activation-1.42e-01

Pos logit contributions
phis+0.352
eatures+0.311
 adolesc+0.307
utonium+0.300
eries+0.297
Neg logit contributions
ICLE-0.218
cil-0.212
lich-0.210
eting-0.202
wic-0.187
Token Chris
Token ID5180
Feature activation-4.02e+00

Pos logit contributions
ICLE+0.100
cil+0.098
lich+0.097
eting+0.095
wic+0.088
Neg logit contributions
phis-0.137
eatures-0.121
 adolesc-0.119
utonium-0.116
inatory-0.114
Token Wallace
Token ID17161
Feature activation-5.97e+00

Pos logit contributions
ICLE+2.800
cil+2.758
lich+2.739
eting+2.711
wic+2.487
Neg logit contributions
phis-3.875
eatures-3.464
 adolesc-3.369
utonium-3.263
inatory-3.206
Token,
Token ID11
Feature activation-6.77e-01

Pos logit contributions
ICLE+2.940
lich+2.902
cil+2.879
eting+2.845
Acknowled+2.501
Neg logit contributions
phis-6.959
eatures-6.289
 adolesc-6.158
utonium-5.981
inatory-5.918
Token the
Token ID262
Feature activation-6.81e-01

Pos logit contributions
ICLE+0.413
cil+0.402
lich+0.399
eting+0.389
wic+0.356
Neg logit contributions
phis-0.717
eatures-0.640
 adolesc-0.629
utonium-0.613
inatory-0.604
Token Texas
Token ID3936
Feature activation-3.74e+00

Pos logit contributions
ICLE+0.467
cil+0.456
lich+0.454
eting+0.445
wic+0.409
Neg logit contributions
phis-0.671
eatures-0.594
 adolesc-0.582
utonium-0.566
inatory-0.557
Token Association
Token ID5396
Feature activation+5.00e-01

Pos logit contributions
ICLE+2.656
cil+2.600
lich+2.584
eting+2.539
wic+2.347
Neg logit contributions
phis-3.590
eatures-3.174
 adolesc-3.101
utonium-3.028
inatory-2.955
Token of
Token ID286
Feature activation-8.20e-01

Pos logit contributions
phis+0.547
eatures+0.489
 adolesc+0.481
utonium+0.470
inatory+0.463
Neg logit contributions
ICLE-0.289
cil-0.281
lich-0.279
eting-0.272
wic-0.246
Token,
Token ID11
Feature activation-7.21e-01

Pos logit contributions
lich+1.771
ICLE+1.769
cil+1.761
eting+1.730
wic+1.566
Neg logit contributions
phis-3.291
eatures-2.966
 adolesc-2.899
utonium-2.814
inatory-2.767
Token attorney
Token ID6136
Feature activation-3.52e-01

Pos logit contributions
ICLE+0.443
cil+0.431
lich+0.429
eting+0.418
wic+0.381
Neg logit contributions
phis-0.762
eatures-0.679
 adolesc-0.667
utonium-0.651
inatory-0.641
Token general
Token ID2276
Feature activation-7.38e-01

Pos logit contributions
ICLE+0.251
cil+0.246
lich+0.245
eting+0.240
wic+0.221
Neg logit contributions
phis-0.338
eatures-0.298
 adolesc-0.291
utonium-0.284
inatory-0.278
Token candidate
Token ID4540
Feature activation-8.34e-01

Pos logit contributions
ICLE+0.479
cil+0.467
lich+0.464
eting+0.453
wic+0.416
Neg logit contributions
phis-0.755
eatures-0.670
 adolesc-0.659
utonium-0.642
inatory-0.632
Token Josh
Token ID8518
Feature activation+1.83e+00

Pos logit contributions
ICLE+0.577
cil+0.566
lich+0.561
eting+0.552
wic+0.506
Neg logit contributions
phis-0.816
eatures-0.724
 adolesc-0.708
utonium-0.687
inatory-0.677
Token Stein
Token ID15215
Feature activation-5.96e+00

Pos logit contributions
phis+1.763
eatures+1.563
 adolesc+1.526
utonium+1.460
inatory+1.434
Neg logit contributions
ICLE-1.297
lich-1.292
cil-1.282
eting-1.256
wic-1.159
Token and
Token ID290
Feature activation-2.90e-01

Pos logit contributions
lich+3.324
cil+3.258
ICLE+3.160
eting+3.107
wic+2.810
Neg logit contributions
phis-6.627
eatures-6.042
 adolesc-5.900
utonium-5.678
orea-5.572
Token state
Token ID1181
Feature activation-1.85e+00

Pos logit contributions
ICLE+0.209
cil+0.205
lich+0.203
eting+0.199
wic+0.185
Neg logit contributions
phis-0.275
eatures-0.242
 adolesc-0.237
utonium-0.230
inatory-0.226
Token Senate
Token ID3845
Feature activation-2.15e+00

Pos logit contributions
ICLE+1.338
cil+1.308
lich+1.302
eting+1.276
wic+1.180
Neg logit contributions
phis-1.757
eatures-1.554
 adolesc-1.511
utonium-1.475
inatory-1.448
Token candidate
Token ID4540
Feature activation-1.07e+00

Pos logit contributions
ICLE+1.471
cil+1.438
lich+1.422
eting+1.397
Acknowled+1.283
Neg logit contributions
phis-2.111
eatures-1.872
 adolesc-1.838
utonium-1.789
inatory-1.751
Token Jeff
Token ID5502
Feature activation-1.03e+00

Pos logit contributions
ICLE+0.751
cil+0.737
lich+0.731
eting+0.720
wic+0.660
Neg logit contributions
phis-1.035
eatures-0.918
 adolesc-0.895
utonium-0.871
inatory-0.857
Tokened
Token ID276
Feature activation+5.34e-01

Pos logit contributions
ICLE+0.055
cil+0.052
lich+0.052
eting+0.050
wic+0.042
Neg logit contributions
phis-0.182
eatures-0.166
 adolesc-0.163
utonium-0.160
eries-0.158
Token with
Token ID351
Feature activation+5.34e-01

Pos logit contributions
phis+0.564
eatures+0.503
 adolesc+0.494
utonium+0.482
inatory+0.475
Neg logit contributions
ICLE-0.329
cil-0.320
lich-0.318
eting-0.310
wic-0.283
Token Mos
Token ID5826
Feature activation-8.66e-01

Pos logit contributions
phis+0.519
eatures+0.456
 adolesc+0.449
utonium+0.435
inatory+0.429
Neg logit contributions
ICLE-0.374
cil-0.362
lich-0.361
eting-0.354
Acknowled-0.327
Tokenaic
Token ID18452
Feature activation-2.89e+00

Pos logit contributions
ICLE+0.543
cil+0.534
lich+0.528
eting+0.516
wic+0.474
Neg logit contributions
phis-0.900
eatures-0.804
 adolesc-0.790
utonium-0.769
inatory-0.755
Token and
Token ID290
Feature activation+1.06e+00

Pos logit contributions
ICLE+1.788
cil+1.761
lich+1.744
eting+1.690
wic+1.558
Neg logit contributions
phis-3.030
eatures-2.717
 adolesc-2.659
utonium-2.587
inatory-2.547
Token Amar
Token ID44291
Feature activation-5.83e+00

Pos logit contributions
phis+1.011
eatures+0.884
 adolesc+0.873
utonium+0.846
eries+0.832
Neg logit contributions
ICLE-0.757
lich-0.730
cil-0.729
eting-0.719
wic-0.664
Tokenillo
Token ID16111
Feature activation-2.55e+00

Pos logit contributions
ICLE+3.354
cil+3.319
lich+3.254
eting+3.158
wic+2.864
Neg logit contributions
phis-6.345
eatures-5.742
 adolesc-5.630
utonium-5.470
inatory-5.390
Token hops
Token ID29438
Feature activation-2.19e+00

Pos logit contributions
ICLE+1.637
cil+1.604
lich+1.589
eting+1.550
wic+1.425
Neg logit contributions
phis-2.623
eatures-2.335
 adolesc-2.287
utonium-2.230
inatory-2.196
Token,
Token ID11
Feature activation+6.56e-02

Pos logit contributions
ICLE+1.042
cil+1.020
lich+1.002
eting+0.976
wic+0.867
Neg logit contributions
phis-2.615
eatures-2.364
 adolesc-2.326
utonium-2.274
inatory-2.247
Token it
Token ID340
Feature activation+8.40e-01

Pos logit contributions
phis+0.067
eatures+0.059
 adolesc+0.058
utonium+0.057
inatory+0.056
Neg logit contributions
ICLE-0.043
cil-0.042
lich-0.042
eting-0.041
wic-0.037
Token smells
Token ID25760
Feature activation+2.46e+00

Pos logit contributions
phis+0.826
eatures+0.730
 adolesc+0.716
utonium+0.696
inatory+0.685
Neg logit contributions
ICLE-0.579
cil-0.566
lich-0.563
eting-0.550
wic-0.508
Token following
Token ID1708
Feature activation-3.35e-01

Pos logit contributions
ICLE+0.047
cil+0.046
lich+0.046
eting+0.045
wic+0.041
Neg logit contributions
phis-0.075
eatures-0.067
 adolesc-0.065
utonium-0.064
inatory-0.063
Token pioneering
Token ID36304
Feature activation-7.74e-01

Pos logit contributions
ICLE+0.210
cil+0.205
lich+0.203
eting+0.199
wic+0.181
Neg logit contributions
phis-0.349
eatures-0.311
 adolesc-0.305
utonium-0.298
inatory-0.293
Token authors
Token ID7035
Feature activation+4.88e-01

Pos logit contributions
ICLE+0.566
cil+0.554
lich+0.551
eting+0.540
wic+0.500
Neg logit contributions
phis-0.728
eatures-0.639
 adolesc-0.626
utonium-0.608
inatory-0.598
Token such
Token ID884
Feature activation-1.02e+00

Pos logit contributions
phis+0.504
eatures+0.448
 adolesc+0.440
utonium+0.429
inatory+0.423
Neg logit contributions
ICLE-0.311
cil-0.303
lich-0.301
eting-0.294
wic-0.269
Token as
Token ID355
Feature activation-9.92e-01

Pos logit contributions
ICLE+0.562
cil+0.546
lich+0.543
eting+0.527
wic+0.475
Neg logit contributions
phis-1.150
eatures-1.034
 adolesc-1.016
utonium-0.992
inatory-0.978
Token Hansen
Token ID27667
Feature activation-5.70e+00

Pos logit contributions
ICLE+0.691
cil+0.677
lich+0.675
eting+0.661
Acknowled+0.608
Neg logit contributions
phis-0.966
eatures-0.856
 adolesc-0.836
utonium-0.812
inatory-0.802
Token (
Token ID357
Feature activation-1.61e-01

Pos logit contributions
ICLE+3.315
lich+3.301
cil+3.254
eting+3.212
wic+2.905
Neg logit contributions
phis-6.059
eatures-5.484
 adolesc-5.361
utonium-5.183
inatory-5.107
Token1984
Token ID28296
Feature activation+1.60e+00

Pos logit contributions
ICLE+0.157
cil+0.155
lich+0.154
eting+0.152
wic+0.144
Neg logit contributions
phis-0.112
eatures-0.094
 adolesc-0.091
utonium-0.087
inatory-0.085
Token),
Token ID828
Feature activation-8.34e-02

Pos logit contributions
phis+1.740
eatures+1.552
 adolesc+1.523
utonium+1.492
inatory+1.474
Neg logit contributions
ICLE-0.929
cil-0.893
lich-0.888
eting-0.867
wic-0.786
Token assume
Token ID7048
Feature activation-9.99e-01

Pos logit contributions
ICLE+0.059
cil+0.058
lich+0.058
eting+0.056
wic+0.052
Neg logit contributions
phis-0.080
eatures-0.071
 adolesc-0.070
utonium-0.068
inatory-0.066
Token that
Token ID326
Feature activation-6.29e-01

Pos logit contributions
ICLE+0.611
cil+0.598
lich+0.594
eting+0.579
wic+0.527
Neg logit contributions
phis-1.056
eatures-0.943
 adolesc-0.925
utonium-0.903
inatory-0.888
Token:
Token ID25
Feature activation-3.15e-01

Pos logit contributions
ICLE+1.417
cil+1.367
lich+1.367
eting+1.332
wic+1.187
Neg logit contributions
phis-2.963
eatures-2.668
 adolesc-2.623
utonium-2.559
inatory-2.526
Token
Token ID198
Feature activation-7.44e-01

Pos logit contributions
ICLE+0.203
cil+0.197
lich+0.197
eting+0.192
wic+0.176
Neg logit contributions
phis-0.324
eatures-0.288
 adolesc-0.283
utonium-0.275
inatory-0.271
Token
Token ID198
Feature activation-5.69e-01

Pos logit contributions
ICLE+0.506
cil+0.493
lich+0.489
eting+0.477
wic+0.442
Neg logit contributions
phis-0.734
eatures-0.631
 adolesc-0.626
utonium-0.619
eries-0.612
Token[
Token ID58
Feature activation-1.40e+00

Pos logit contributions
ICLE+0.358
cil+0.349
lich+0.346
eting+0.338
wic+0.309
Neg logit contributions
phis-0.593
eatures-0.528
 adolesc-0.518
utonium-0.505
inatory-0.498
TokenChuck
Token ID44324
Feature activation-2.63e-01

Pos logit contributions
ICLE+0.948
cil+0.925
lich+0.921
eting+0.900
wic+0.829
Neg logit contributions
phis-1.386
eatures-1.227
 adolesc-1.204
utonium-1.171
inatory-1.151
Token Todd
Token ID14377
Feature activation-5.68e+00

Pos logit contributions
ICLE+0.177
cil+0.173
lich+0.173
eting+0.168
wic+0.155
Neg logit contributions
phis-0.263
eatures-0.233
 adolesc-0.229
utonium-0.222
inatory-0.219
Token:]
Token ID47715
Feature activation-4.87e-01

Pos logit contributions
ICLE+3.393
lich+3.392
cil+3.343
eting+3.292
wic+2.959
Neg logit contributions
phis-6.054
eatures-5.354
 adolesc-5.213
utonium-5.095
inatory-5.027
Token
Token ID564
Feature activation+1.39e-01

Pos logit contributions
ICLE+0.313
cil+0.305
lich+0.303
eting+0.296
wic+0.271
Neg logit contributions
phis-0.501
eatures-0.446
 adolesc-0.437
utonium-0.426
inatory-0.419
Token
Token ID250
Feature activation-1.39e+00

Pos logit contributions
phis+0.124
eatures+0.108
 adolesc+0.106
utonium+0.102
inatory+0.100
Neg logit contributions
ICLE-0.109
cil-0.107
lich-0.106
eting-0.104
wic-0.097
TokenWhat
Token ID2061
Feature activation-3.12e-01

Pos logit contributions
ICLE+0.867
cil+0.844
lich+0.840
eting+0.819
Acknowled+0.748
Neg logit contributions
phis-1.452
eatures-1.295
 adolesc-1.273
utonium-1.238
inatory-1.219
Token
Token ID447
Feature activation-9.56e-02

Pos logit contributions
ICLE+0.206
cil+0.201
lich+0.200
eting+0.195
wic+0.179
Neg logit contributions
phis-0.316
eatures-0.280
 adolesc-0.275
utonium-0.268
inatory-0.264
Tokenth
Token ID400
Feature activation+4.20e-01

Pos logit contributions
ICLE+0.263
cil+0.257
lich+0.255
eting+0.250
wic+0.230
Neg logit contributions
phis-0.382
eatures-0.338
 adolesc-0.332
utonium-0.322
inatory-0.317
Token anniversary
Token ID11162
Feature activation+4.59e-01

Pos logit contributions
phis+0.361
eatures+0.313
 adolesc+0.306
utonium+0.296
inatory+0.290
Neg logit contributions
ICLE-0.342
cil-0.336
lich-0.334
eting-0.328
wic-0.306
Token)
Token ID8
Feature activation+1.04e-01

Pos logit contributions
phis+0.487
eatures+0.433
 adolesc+0.426
utonium+0.416
inatory+0.409
Neg logit contributions
ICLE-0.282
cil-0.275
lich-0.273
eting-0.266
wic-0.242
Token of
Token ID286
Feature activation-2.63e-01

Pos logit contributions
phis+0.113
eatures+0.101
 adolesc+0.099
utonium+0.097
inatory+0.095
Neg logit contributions
ICLE-0.061
cil-0.060
lich-0.059
eting-0.058
wic-0.053
Token Sultan
Token ID37399
Feature activation+1.11e+00

Pos logit contributions
ICLE+0.171
cil+0.167
lich+0.166
eting+0.162
wic+0.148
Neg logit contributions
phis-0.269
eatures-0.239
 adolesc-0.235
utonium-0.229
inatory-0.225
Token Hassan
Token ID24485
Feature activation-5.53e+00

Pos logit contributions
phis+1.068
eatures+0.940
 adolesc+0.921
utonium+0.896
inatory+0.881
Neg logit contributions
ICLE-0.795
cil-0.776
lich-0.771
eting-0.754
wic-0.698
Tokenal
Token ID282
Feature activation-2.66e-01

Pos logit contributions
ICLE+2.424
cil+2.394
lich+2.347
eting+2.295
Bay+1.986
Neg logit contributions
phis-6.761
eatures-6.204
 adolesc-6.094
utonium-5.919
inatory-5.812
Token Bol
Token ID10797
Feature activation-2.74e-01

Pos logit contributions
ICLE+0.198
cil+0.194
lich+0.193
eting+0.189
wic+0.175
Neg logit contributions
phis-0.247
eatures-0.217
 adolesc-0.212
utonium-0.206
inatory-0.202
Tokenk
Token ID74
Feature activation+2.12e+00

Pos logit contributions
ICLE+0.146
cil+0.138
lich+0.137
eting+0.134
Acknowled+0.121
Neg logit contributions
phis-0.314
eatures-0.279
 adolesc-0.274
utonium-0.271
inatory-0.267
Tokeniah
Token ID9520
Feature activation+1.03e+00

Pos logit contributions
phis+1.147
eatures+0.846
utonium+0.811
inatory+0.808
 adolesc+0.796
Neg logit contributions
ICLE-2.390
cil-2.318
lich-2.310
eting-2.283
Acknowled-2.196
Token acc
Token ID697
Feature activation-8.37e-01

Pos logit contributions
phis+1.162
eatures+1.045
 adolesc+1.026
utonium+1.004
inatory+0.990
Neg logit contributions
ICLE-0.562
cil-0.544
lich-0.540
eting-0.524
wic-0.472
Token,
Token ID11
Feature activation-9.51e-01

Pos logit contributions
phis+0.673
eatures+0.601
 adolesc+0.592
utonium+0.579
inatory+0.572
Neg logit contributions
ICLE-0.335
cil-0.326
lich-0.321
eting-0.311
wic-0.282
Token about
Token ID546
Feature activation-1.52e-01

Pos logit contributions
ICLE+0.596
cil+0.580
lich+0.577
eting+0.563
wic+0.514
Neg logit contributions
phis-0.994
eatures-0.886
 adolesc-0.870
utonium-0.848
inatory-0.835
Token Dw
Token ID19113
Feature activation-2.85e+00

Pos logit contributions
ICLE+0.098
cil+0.096
lich+0.095
eting+0.093
wic+0.085
Neg logit contributions
phis-0.156
eatures-0.138
 adolesc-0.136
utonium-0.132
inatory-0.130
Tokeny
Token ID88
Feature activation+1.41e-01

Pos logit contributions
ICLE+1.559
cil+1.495
lich+1.490
eting+1.445
Acknowled+1.319
Neg logit contributions
phis-3.211
eatures-2.836
 adolesc-2.799
utonium-2.768
orea-2.737
Tokenane
Token ID1531
Feature activation-2.60e+00

Pos logit contributions
phis+0.145
eatures+0.126
utonium+0.125
 adolesc+0.124
orea+0.122
Neg logit contributions
ICLE-0.091
cil-0.085
lich-0.083
eting-0.082
ograp-0.078
Token Wade
Token ID19136
Feature activation-5.51e+00

Pos logit contributions
ICLE+1.050
cil+1.006
lich+1.004
eting+0.966
wic+0.840
Neg logit contributions
phis-3.281
eatures-2.992
 adolesc-2.943
utonium-2.883
inatory-2.846
Token,
Token ID11
Feature activation-9.70e-01

Pos logit contributions
ICLE+2.846
lich+2.792
cil+2.762
eting+2.729
wic+2.450
Neg logit contributions
phis-6.260
eatures-5.696
 adolesc-5.515
utonium-5.428
inatory-5.350
Token Chris
Token ID5180
Feature activation-4.69e+00

Pos logit contributions
ICLE+0.650
cil+0.634
lich+0.632
eting+0.617
wic+0.567
Neg logit contributions
phis-0.970
eatures-0.861
 adolesc-0.844
utonium-0.823
inatory-0.809
Token Bosh
Token ID42776
Feature activation-4.66e+00

Pos logit contributions
ICLE+2.880
cil+2.856
lich+2.814
eting+2.730
wic+2.510
Neg logit contributions
phis-4.909
eatures-4.421
 adolesc-4.310
utonium-4.208
inatory-4.138
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
ICLE+2.095
lich+2.049
cil+2.031
eting+1.983
wic+1.731
Neg logit contributions
phis-5.616
eatures-5.134
 adolesc-4.972
utonium-4.917
inatory-4.846
Token Kevin
Token ID7939
Feature activation+5.29e-01

Pos logit contributions
ICLE+0.872
cil+0.853
lich+0.850
eting+0.833
wic+0.766
Neg logit contributions
phis-1.224
eatures-1.086
 adolesc-1.062
utonium-1.036
inatory-1.019
Token year
Token ID614
Feature activation+1.36e+00

Pos logit contributions
phis+1.197
eatures+0.975
 adolesc+0.944
utonium+0.899
inatory+0.883
Neg logit contributions
ICLE-1.883
cil-1.860
lich-1.845
eting-1.812
wic-1.725
Token was
Token ID373
Feature activation+1.29e+00

Pos logit contributions
phis+1.475
eatures+1.300
 adolesc+1.287
utonium+1.256
eries+1.241
Neg logit contributions
ICLE-0.803
cil-0.777
lich-0.768
eting-0.750
Acknowled-0.683
Token last
Token ID938
Feature activation+1.08e+00

Pos logit contributions
phis+1.260
eatures+1.105
 adolesc+1.092
utonium+1.058
eries+1.043
Neg logit contributions
ICLE-0.891
cil-0.867
lich-0.862
eting-0.846
wic-0.785
Token year
Token ID614
Feature activation+1.16e+00

Pos logit contributions
phis+0.752
eatures+0.625
 adolesc+0.610
utonium+0.583
inatory+0.571
Neg logit contributions
ICLE-1.051
cil-1.035
lich-1.029
eting-1.013
wic-0.959
Token,"
Token ID553
Feature activation-1.60e-01

Pos logit contributions
phis+1.244
eatures+1.096
 adolesc+1.089
utonium+1.060
eries+1.048
Neg logit contributions
ICLE-0.690
cil-0.670
lich-0.659
eting-0.646
wic-0.591
Token Stevens
Token ID20019
Feature activation-5.45e+00

Pos logit contributions
ICLE+0.040
cil+0.037
lich+0.037
eting+0.034
wic+0.026
Neg logit contributions
phis-0.227
eatures-0.209
 adolesc-0.206
utonium-0.203
inatory-0.201
Token said
Token ID531
Feature activation-8.57e-01

Pos logit contributions
ICLE+2.524
lich+2.459
cil+2.419
eting+2.378
Acknowled+2.081
Neg logit contributions
phis-6.519
eatures-5.968
 adolesc-5.823
utonium-5.680
inatory-5.606
Token.
Token ID13
Feature activation-6.32e-01

Pos logit contributions
ICLE+0.453
cil+0.439
lich+0.436
eting+0.423
wic+0.379
Neg logit contributions
phis-0.981
eatures-0.883
 adolesc-0.868
utonium-0.849
inatory-0.837
Token "
Token ID366
Feature activation-1.25e+00

Pos logit contributions
ICLE+0.389
cil+0.379
lich+0.377
eting+0.368
wic+0.335
Neg logit contributions
phis-0.665
eatures-0.594
 adolesc-0.585
utonium-0.568
inatory-0.560
TokenI
Token ID40
Feature activation-6.58e-01

Pos logit contributions
ICLE+0.762
cil+0.740
lich+0.735
eting+0.717
Acknowled+0.654
Neg logit contributions
phis-1.329
eatures-1.191
 adolesc-1.168
utonium-1.137
inatory-1.120
Token don
Token ID836
Feature activation-6.26e-01

Pos logit contributions
ICLE+0.471
cil+0.458
lich+0.456
eting+0.447
wic+0.412
Neg logit contributions
phis-0.631
eatures-0.551
 adolesc-0.539
utonium-0.528
inatory-0.519
Token
Token ID447
Feature activation+1.94e-01

Pos logit contributions
phis+1.086
eatures+0.961
 adolesc+0.942
utonium+0.922
inatory+0.911
Neg logit contributions
ICLE-0.690
cil-0.669
lich-0.661
eting-0.643
wic-0.595
Token
Token ID247
Feature activation+1.12e+00

Pos logit contributions
phis+0.156
eatures+0.133
 adolesc+0.130
utonium+0.126
inatory+0.123
Neg logit contributions
ICLE-0.169
cil-0.166
lich-0.166
eting-0.163
wic-0.153
Tokens
Token ID82
Feature activation-7.12e-01

Pos logit contributions
phis+0.879
eatures+0.746
 adolesc+0.718
utonium+0.702
inatory+0.692
Neg logit contributions
ICLE-0.993
cil-0.968
lich-0.961
eting-0.946
Acknowled-0.892
Token office
Token ID2607
Feature activation-5.11e-01

Pos logit contributions
ICLE+0.486
cil+0.474
lich+0.473
eting+0.463
wic+0.425
Neg logit contributions
phis-0.704
eatures-0.624
 adolesc-0.611
utonium-0.596
inatory-0.584
Token later
Token ID1568
Feature activation-6.08e-01

Pos logit contributions
ICLE+0.328
cil+0.320
lich+0.318
eting+0.310
wic+0.284
Neg logit contributions
phis-0.526
eatures-0.467
 adolesc-0.458
utonium-0.447
inatory-0.440
Token stressed
Token ID15033
Feature activation-5.44e+00

Pos logit contributions
ICLE+0.359
cil+0.350
lich+0.348
eting+0.339
wic+0.308
Neg logit contributions
phis-0.658
eatures-0.588
 adolesc-0.579
utonium-0.564
inatory-0.556
Token that
Token ID326
Feature activation-2.71e+00

Pos logit contributions
ICLE+2.999
cil+2.916
lich+2.889
eting+2.858
Acknowled+2.570
Neg logit contributions
phis-6.001
eatures-5.379
 adolesc-5.309
utonium-5.236
eries-5.087
Token there
Token ID612
Feature activation-1.45e+00

Pos logit contributions
ICLE+1.624
cil+1.580
lich+1.571
eting+1.534
wic+1.389
Neg logit contributions
phis-2.891
eatures-2.580
 adolesc-2.546
utonium-2.488
inatory-2.441
Token were
Token ID547
Feature activation-1.04e+00

Pos logit contributions
ICLE+1.030
cil+1.007
lich+1.002
eting+0.983
wic+0.907
Neg logit contributions
phis-1.398
eatures-1.233
 adolesc-1.210
utonium-1.175
inatory-1.151
Token no
Token ID645
Feature activation-1.75e+00

Pos logit contributions
ICLE+0.622
cil+0.604
lich+0.600
eting+0.584
wic+0.533
Neg logit contributions
phis-1.115
eatures-0.996
 adolesc-0.978
utonium-0.954
inatory-0.943
Token immediate
Token ID7103
Feature activation-1.54e+00

Pos logit contributions
ICLE+1.132
cil+1.111
lich+1.103
eting+1.082
Acknowled+0.986
Neg logit contributions
phis-1.784
eatures-1.591
 adolesc-1.560
utonium-1.520
eries-1.485
Token can
Token ID460
Feature activation+1.28e+00

Pos logit contributions
phis+0.821
eatures+0.719
 adolesc+0.707
utonium+0.691
eries+0.679
Neg logit contributions
ICLE-0.601
cil-0.583
lich-0.578
eting-0.568
wic-0.525
Token listen
Token ID6004
Feature activation-1.72e+00

Pos logit contributions
phis+1.117
eatures+0.963
 adolesc+0.940
utonium+0.916
inatory+0.900
Neg logit contributions
ICLE-1.032
cil-1.004
lich-1.002
eting-0.983
wic-0.919
Token to
Token ID284
Feature activation-3.14e-01

Pos logit contributions
ICLE+1.073
lich+1.047
cil+1.046
eting+1.018
Acknowled+0.929
Neg logit contributions
phis-1.798
eatures-1.619
 adolesc-1.581
utonium-1.540
inatory-1.512
Token the
Token ID262
Feature activation-3.33e-01

Pos logit contributions
ICLE+0.197
cil+0.192
lich+0.190
eting+0.186
wic+0.170
Neg logit contributions
phis-0.328
eatures-0.292
 adolesc-0.287
utonium-0.279
inatory-0.276
Token clar
Token ID10212
Feature activation-2.17e+00

Pos logit contributions
ICLE+0.241
cil+0.236
lich+0.235
eting+0.230
wic+0.213
Neg logit contributions
phis-0.314
eatures-0.277
 adolesc-0.271
utonium-0.263
inatory-0.258
Tokeninet
Token ID42504
Feature activation-5.42e+00

Pos logit contributions
ICLE+1.318
cil+1.291
lich+1.286
eting+1.255
wic+1.138
Neg logit contributions
phis-2.294
eatures-2.049
 adolesc-2.027
utonium-1.958
inatory-1.918
Token quint
Token ID28533
Feature activation-1.99e+00

Pos logit contributions
ICLE+3.621
cil+3.594
lich+3.546
eting+3.461
Acknowled+3.178
Neg logit contributions
phis-5.325
eatures-4.786
 adolesc-4.663
utonium-4.527
inatory-4.420
Tokenet
Token ID316
Feature activation-1.69e+00

Pos logit contributions
ICLE+0.925
cil+0.894
lich+0.886
eting+0.858
wic+0.755
Neg logit contributions
phis-2.403
eatures-2.175
 adolesc-2.144
utonium-2.095
inatory-2.069
Token without
Token ID1231
Feature activation-4.49e-02

Pos logit contributions
ICLE+1.058
cil+1.034
lich+1.030
eting+1.004
wic+0.917
Neg logit contributions
phis-1.767
eatures-1.581
 adolesc-1.550
utonium-1.508
inatory-1.484
Token fearing
Token ID33188
Feature activation-8.00e-01

Pos logit contributions
ICLE+0.029
cil+0.028
lich+0.028
eting+0.027
wic+0.025
Neg logit contributions
phis-0.046
eatures-0.041
 adolesc-0.040
utonium-0.039
inatory-0.039
Token that
Token ID326
Feature activation-7.96e-01

Pos logit contributions
ICLE+0.512
cil+0.498
lich+0.494
eting+0.483
wic+0.443
Neg logit contributions
phis-0.826
eatures-0.734
 adolesc-0.722
utonium-0.703
inatory-0.693
Token just
Token ID655
Feature activation+3.32e-01

Pos logit contributions
phis+2.164
eatures+1.908
 adolesc+1.877
utonium+1.827
eries+1.800
Neg logit contributions
ICLE-1.438
cil-1.398
lich-1.394
eting-1.355
wic-1.248
Token isn
Token ID2125
Feature activation+1.61e+00

Pos logit contributions
phis+0.314
eatures+0.277
 adolesc+0.272
utonium+0.263
inatory+0.259
Neg logit contributions
ICLE-0.240
cil-0.235
lich-0.234
eting-0.229
wic-0.212
Token
Token ID447
Feature activation-7.94e-02

Pos logit contributions
phis+1.569
 adolesc+1.330
utonium+1.330
eatures+1.325
eries+1.321
Neg logit contributions
ICLE-1.084
cil-1.056
lich-1.042
eting-1.020
wic-0.953
Token
Token ID247
Feature activation+9.15e-01

Pos logit contributions
ICLE+0.068
cil+0.067
lich+0.067
eting+0.066
wic+0.062
Neg logit contributions
phis-0.064
eatures-0.055
 adolesc-0.054
utonium-0.052
inatory-0.051
Tokent
Token ID83
Feature activation-1.50e+00

Pos logit contributions
phis+0.838
eatures+0.731
 adolesc+0.714
utonium+0.695
inatory+0.684
Neg logit contributions
ICLE-0.693
cil-0.675
lich-0.671
eting-0.658
Acknowled-0.612
Token Wallace
Token ID17161
Feature activation-5.41e+00

Pos logit contributions
ICLE+0.861
cil+0.833
lich+0.829
eting+0.806
wic+0.731
Neg logit contributions
phis-1.642
eatures-1.470
 adolesc-1.445
utonium-1.409
inatory-1.390
Token
Token ID447
Feature activation-1.53e-01

Pos logit contributions
ICLE+3.242
lich+3.181
eting+3.135
cil+3.129
Bay+2.832
Neg logit contributions
phis-5.641
eatures-5.081
 adolesc-4.944
utonium-4.838
eries-4.748
Token
Token ID247
Feature activation+8.69e-01

Pos logit contributions
ICLE+0.138
cil+0.135
lich+0.135
eting+0.132
wic+0.124
Neg logit contributions
phis-0.118
eatures-0.101
 adolesc-0.098
utonium-0.095
inatory-0.093
Tokens
Token ID82
Feature activation-2.33e-01

Pos logit contributions
phis+0.673
eatures+0.572
 adolesc+0.556
utonium+0.538
inatory+0.528
Neg logit contributions
ICLE-0.781
cil-0.764
lich-0.759
eting-0.748
Acknowled-0.704
Token game
Token ID983
Feature activation-6.71e-01

Pos logit contributions
ICLE+0.183
cil+0.179
lich+0.178
eting+0.175
wic+0.163
Neg logit contributions
phis-0.206
eatures-0.179
 adolesc-0.175
utonium-0.170
inatory-0.167
Token;
Token ID26
Feature activation-1.49e+00

Pos logit contributions
ICLE+0.378
cil+0.365
lich+0.363
eting+0.352
wic+0.320
Neg logit contributions
phis-0.746
eatures-0.665
 adolesc-0.655
utonium-0.639
inatory-0.631
Token
Token ID247
Feature activation+2.11e+00

Pos logit contributions
phis+0.451
eatures+0.380
 adolesc+0.371
utonium+0.360
inatory+0.350
Neg logit contributions
ICLE-0.552
cil-0.542
lich-0.539
eting-0.532
wic-0.503
Tokens
Token ID82
Feature activation-3.13e-01

Pos logit contributions
phis+1.688
eatures+1.440
 adolesc+1.389
utonium+1.353
eries+1.340
Neg logit contributions
ICLE-1.826
cil-1.774
lich-1.768
eting-1.742
Acknowled-1.645
Token play
Token ID711
Feature activation-1.79e+00

Pos logit contributions
ICLE+0.237
cil+0.232
lich+0.231
eting+0.226
wic+0.210
Neg logit contributions
phis-0.286
eatures-0.250
 adolesc-0.245
utonium-0.238
inatory-0.233
Token with
Token ID351
Feature activation-3.97e-01

Pos logit contributions
ICLE+1.273
cil+1.246
lich+1.240
eting+1.214
wic+1.123
Neg logit contributions
phis-1.723
eatures-1.517
 adolesc-1.490
utonium-1.447
inatory-1.421
Token Blake
Token ID13307
Feature activation+2.10e-01

Pos logit contributions
ICLE+0.265
cil+0.258
lich+0.256
eting+0.251
wic+0.231
Neg logit contributions
phis-0.398
eatures-0.353
 adolesc-0.346
utonium-0.337
inatory-0.332
Token Wheeler
Token ID27512
Feature activation-5.41e+00

Pos logit contributions
phis+0.238
eatures+0.213
 adolesc+0.210
utonium+0.206
inatory+0.203
Neg logit contributions
ICLE-0.114
cil-0.110
lich-0.109
eting-0.106
wic-0.095
Token and
Token ID290
Feature activation+3.39e-01

Pos logit contributions
ICLE+3.127
lich+3.101
cil+3.095
eting+3.019
wic+2.745
Neg logit contributions
phis-5.750
eatures-5.242
 adolesc-5.081
utonium-4.953
inatory-4.895
Token Mark
Token ID2940
Feature activation-1.27e+00

Pos logit contributions
phis+0.324
eatures+0.285
 adolesc+0.280
utonium+0.272
inatory+0.267
Neg logit contributions
ICLE-0.242
cil-0.236
lich-0.235
eting-0.230
wic-0.213
Token Sche
Token ID10011
Feature activation-2.64e+00

Pos logit contributions
ICLE+0.799
cil+0.784
lich+0.777
eting+0.762
wic+0.697
Neg logit contributions
phis-1.315
eatures-1.172
 adolesc-1.150
utonium-1.118
inatory-1.101
Tokenife
Token ID901
Feature activation+5.19e-01

Pos logit contributions
ICLE+2.410
cil+2.377
lich+2.377
eting+2.323
wic+2.190
Neg logit contributions
phis-1.999
eatures-1.714
 adolesc-1.668
utonium-1.587
inatory-1.558
Tokenle
Token ID293
Feature activation-9.18e-01

Pos logit contributions
phis+0.580
eries+0.497
utonium+0.494
eatures+0.493
orea+0.489
Neg logit contributions
ICLE-0.293
cil-0.269
eting-0.263
lich-0.259
ctica-0.244
Token L
Token ID406
Feature activation+1.41e+00

Pos logit contributions
ICLE+0.196
cil+0.192
lich+0.191
eting+0.187
wic+0.174
Neg logit contributions
phis-0.236
eatures-0.207
 adolesc-0.203
utonium-0.197
inatory-0.193
Tokenall
Token ID439
Feature activation-5.38e-01

Pos logit contributions
phis+1.367
eatures+1.162
utonium+1.144
eries+1.127
 adolesc+1.120
Neg logit contributions
ICLE-1.035
eting-0.971
cil-0.960
lich-0.924
Acknowled-0.895
Tokenana
Token ID2271
Feature activation+4.55e-01

Pos logit contributions
ICLE+0.280
cil+0.275
lich+0.274
eting+0.263
wic+0.238
Neg logit contributions
phis-0.615
eatures-0.560
 adolesc-0.553
utonium-0.534
eries-0.526
Token and
Token ID290
Feature activation+9.16e-01

Pos logit contributions
phis+0.518
eatures+0.466
 adolesc+0.459
utonium+0.448
inatory+0.442
Neg logit contributions
ICLE-0.243
cil-0.235
lich-0.234
eting-0.227
wic-0.204
Token Jordan
Token ID8078
Feature activation-1.34e+00

Pos logit contributions
phis+0.900
eatures+0.779
 adolesc+0.774
utonium+0.751
eries+0.742
Neg logit contributions
ICLE-0.640
cil-0.613
lich-0.607
eting-0.600
wic-0.556
Token Henderson
Token ID22016
Feature activation-5.38e+00

Pos logit contributions
ICLE+0.493
cil+0.461
lich+0.447
eting+0.435
wic+0.364
Neg logit contributions
phis-1.779
 adolesc-1.586
eatures-1.585
utonium-1.555
inatory-1.553
Token.
Token ID13
Feature activation+3.04e-01

Pos logit contributions
cil+2.732
lich+2.717
ICLE+2.668
eting+2.655
wic+2.352
Neg logit contributions
phis-6.078
eatures-5.630
 adolesc-5.415
utonium-5.278
inatory-5.246
Token Despite
Token ID7945
Feature activation+2.07e-01

Pos logit contributions
phis+0.306
eatures+0.269
 adolesc+0.265
utonium+0.259
inatory+0.255
Neg logit contributions
ICLE-0.203
cil-0.197
lich-0.196
eting-0.192
wic-0.177
Token a
Token ID257
Feature activation+4.75e-01

Pos logit contributions
phis+0.214
eatures+0.189
 adolesc+0.186
utonium+0.181
eries+0.179
Neg logit contributions
ICLE-0.133
cil-0.128
lich-0.127
eting-0.125
wic-0.115
Token damaging
Token ID14790
Feature activation+9.89e-01

Pos logit contributions
phis+0.436
eatures+0.383
 adolesc+0.375
utonium+0.364
inatory+0.357
Neg logit contributions
ICLE-0.357
cil-0.349
lich-0.347
eting-0.340
wic-0.316
Token run
Token ID1057
Feature activation+7.49e-01

Pos logit contributions
phis+0.839
eatures+0.725
 adolesc+0.709
utonium+0.686
inatory+0.673
Neg logit contributions
ICLE-0.814
cil-0.798
lich-0.794
eting-0.779
wic-0.729
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
phis+0.895
eatures+0.785
 adolesc+0.781
utonium+0.762
inatory+0.754
Neg logit contributions
ICLE-0.500
cil-0.486
lich-0.478
eting-0.463
wic-0.430
Token
Token ID198
Feature activation-2.84e-01

Pos logit contributions
ICLE+0.124
cil+0.121
lich+0.120
eting+0.117
wic+0.108
Neg logit contributions
phis-0.185
eatures-0.163
 adolesc-0.160
utonium-0.156
inatory-0.154
Token
Token ID198
Feature activation-1.96e-01

Pos logit contributions
ICLE+0.194
cil+0.190
lich+0.188
eting+0.184
wic+0.170
Neg logit contributions
phis-0.277
eatures-0.237
 adolesc-0.236
utonium-0.233
eries-0.231
TokenWith
Token ID3152
Feature activation+3.20e-01

Pos logit contributions
ICLE+0.127
cil+0.124
lich+0.123
eting+0.121
wic+0.111
Neg logit contributions
phis-0.199
eatures-0.175
 adolesc-0.172
utonium-0.169
eries-0.167
Token Paul
Token ID3362
Feature activation+1.49e-01

Pos logit contributions
phis+0.333
eatures+0.296
 adolesc+0.291
utonium+0.283
inatory+0.279
Neg logit contributions
ICLE-0.202
cil-0.196
lich-0.195
eting-0.190
wic-0.175
Token Ryan
Token ID6047
Feature activation-5.35e+00

Pos logit contributions
phis+0.154
eatures+0.137
 adolesc+0.134
utonium+0.131
inatory+0.129
Neg logit contributions
ICLE-0.095
cil-0.093
lich-0.092
eting-0.090
wic-0.083
Token,
Token ID11
Feature activation+1.27e-01

Pos logit contributions
ICLE+3.297
lich+3.280
cil+3.255
eting+3.229
wic+2.893
Neg logit contributions
phis-5.547
eatures-5.018
 adolesc-4.844
utonium-4.737
inatory-4.673
Token there
Token ID612
Feature activation-2.24e-01

Pos logit contributions
phis+0.134
eatures+0.119
 adolesc+0.117
utonium+0.115
inatory+0.113
Neg logit contributions
ICLE-0.079
cil-0.077
lich-0.076
eting-0.074
wic-0.068
Token is
Token ID318
Feature activation+7.60e-01

Pos logit contributions
ICLE+0.170
cil+0.166
lich+0.165
eting+0.162
wic+0.151
Neg logit contributions
phis-0.205
eatures-0.179
 adolesc-0.175
utonium-0.170
inatory-0.167
Token a
Token ID257
Feature activation-5.95e-01

Pos logit contributions
phis+0.783
eatures+0.693
 adolesc+0.682
utonium+0.666
inatory+0.655
Neg logit contributions
ICLE-0.488
cil-0.474
lich-0.469
eting-0.461
wic-0.424
Token sense
Token ID2565
Feature activation-1.60e-01

Pos logit contributions
ICLE+0.426
cil+0.417
lich+0.415
eting+0.406
wic+0.376
Neg logit contributions
phis-0.567
eatures-0.500
 adolesc-0.490
utonium-0.476
inatory-0.468
Token helpful
Token ID7613
Feature activation-7.89e-02

Pos logit contributions
ICLE+1.052
cil+1.028
lich+1.022
eting+1.000
wic+0.923
Neg logit contributions
phis-1.471
eatures-1.299
 adolesc-1.273
utonium-1.239
inatory-1.218
Token in
Token ID287
Feature activation-1.98e-01

Pos logit contributions
ICLE+0.048
cil+0.047
lich+0.046
eting+0.045
wic+0.041
Neg logit contributions
phis-0.084
eatures-0.074
 adolesc-0.073
utonium-0.071
inatory-0.071
Token the
Token ID262
Feature activation+4.59e-01

Pos logit contributions
ICLE+0.126
cil+0.122
lich+0.121
eting+0.119
wic+0.109
Neg logit contributions
phis-0.205
eatures-0.182
 adolesc-0.179
utonium-0.173
inatory-0.171
Token development
Token ID2478
Feature activation+7.21e-01

Pos logit contributions
phis+0.429
eatures+0.375
 adolesc+0.368
utonium+0.355
eries+0.350
Neg logit contributions
ICLE-0.339
cil-0.331
lich-0.330
eting-0.323
wic-0.300
Token of
Token ID286
Feature activation-3.33e-01

Pos logit contributions
phis+0.766
eatures+0.686
 adolesc+0.673
utonium+0.653
inatory+0.647
Neg logit contributions
ICLE-0.439
cil-0.424
lich-0.422
eting-0.410
wic-0.375
Token Hassan
Token ID24485
Feature activation-5.34e+00

Pos logit contributions
ICLE+0.215
cil+0.209
lich+0.208
eting+0.203
wic+0.186
Neg logit contributions
phis-0.342
eatures-0.303
 adolesc-0.298
utonium-0.290
inatory-0.285
Token Whites
Token ID29290
Feature activation-1.99e+00

Pos logit contributions
ICLE+2.722
cil+2.636
lich+2.609
eting+2.538
wic+2.257
Neg logit contributions
phis-6.199
eatures-5.601
 adolesc-5.499
utonium-5.397
inatory-5.308
Tokenide
Token ID485
Feature activation-8.18e-01

Pos logit contributions
ICLE+1.099
lich+1.079
cil+1.076
eting+1.041
wic+0.948
Neg logit contributions
phis-2.210
eatures-2.008
 adolesc-1.977
utonium-1.915
inatory-1.882
Token.
Token ID13
Feature activation-1.56e-01

Pos logit contributions
ICLE+0.430
cil+0.417
lich+0.414
eting+0.402
wic+0.361
Neg logit contributions
phis-0.937
eatures-0.844
 adolesc-0.830
utonium-0.811
inatory-0.800
Token
Token ID198
Feature activation-3.74e-01

Pos logit contributions
ICLE+0.102
cil+0.099
lich+0.099
eting+0.096
wic+0.088
Neg logit contributions
phis-0.159
eatures-0.141
 adolesc-0.139
utonium-0.135
inatory-0.133
Token
Token ID198
Feature activation-2.74e-01

Pos logit contributions
ICLE+0.255
cil+0.248
lich+0.246
eting+0.240
wic+0.222
Neg logit contributions
phis-0.369
eatures-0.317
 adolesc-0.315
utonium-0.311
eries-0.308
Token l
Token ID300
Feature activation+8.24e-01

Pos logit contributions
phis+0.550
eatures+0.485
 adolesc+0.476
utonium+0.462
inatory+0.456
Neg logit contributions
ICLE-0.401
cil-0.391
lich-0.388
eting-0.380
wic-0.352
Tokenashing
Token ID2140
Feature activation+1.08e+00

Pos logit contributions
phis+0.872
eatures+0.778
 adolesc+0.764
utonium+0.746
inatory+0.734
Neg logit contributions
ICLE-0.506
cil-0.492
lich-0.489
eting-0.477
wic-0.435
Token criticism
Token ID7734
Feature activation-3.20e-01

Pos logit contributions
phis+1.157
eatures+1.036
 adolesc+1.017
utonium+0.994
inatory+0.980
Neg logit contributions
ICLE-0.641
cil-0.620
lich-0.616
eting-0.600
wic-0.548
Token of
Token ID286
Feature activation-1.50e+00

Pos logit contributions
ICLE+0.199
cil+0.194
lich+0.193
eting+0.189
wic+0.172
Neg logit contributions
phis-0.335
eatures-0.299
 adolesc-0.294
utonium-0.286
inatory-0.281
Token Paul
Token ID3362
Feature activation+1.02e-01

Pos logit contributions
ICLE+0.939
cil+0.915
lich+0.911
eting+0.889
wic+0.811
Neg logit contributions
phis-1.567
eatures-1.395
 adolesc-1.371
utonium-1.336
inatory-1.314
Token Ryan
Token ID6047
Feature activation-5.33e+00

Pos logit contributions
phis+0.105
eatures+0.094
 adolesc+0.092
utonium+0.090
inatory+0.088
Neg logit contributions
ICLE-0.065
cil-0.063
lich-0.063
eting-0.062
wic-0.056
Token,
Token ID11
Feature activation-1.10e+00

Pos logit contributions
ICLE+2.647
lich+2.636
cil+2.606
eting+2.551
wic+2.272
Neg logit contributions
phis-6.175
eatures-5.629
 adolesc-5.474
utonium-5.348
inatory-5.261
Token the
Token ID262
Feature activation-6.53e-01

Pos logit contributions
ICLE+0.666
cil+0.648
lich+0.644
eting+0.628
wic+0.572
Neg logit contributions
phis-1.173
eatures-1.047
 adolesc-1.029
utonium-1.003
inatory-0.988
Token House
Token ID2097
Feature activation-1.48e+00

Pos logit contributions
ICLE+0.410
cil+0.400
lich+0.397
eting+0.389
wic+0.354
Neg logit contributions
phis-0.683
eatures-0.609
 adolesc-0.597
utonium-0.581
inatory-0.572
Token speaker
Token ID10834
Feature activation-4.94e+00

Pos logit contributions
ICLE+0.916
cil+0.891
lich+0.886
eting+0.865
wic+0.789
Neg logit contributions
phis-1.563
eatures-1.393
 adolesc-1.369
utonium-1.335
inatory-1.315
Token whose
Token ID3025
Feature activation-4.44e-01

Pos logit contributions
ICLE+2.528
cil+2.447
lich+2.441
eting+2.393
Acknowled+2.111
Neg logit contributions
phis-5.711
eatures-5.175
 adolesc-5.062
utonium-4.955
eries-4.859
Token
Token ID198
Feature activation-4.91e-01

Pos logit contributions
ICLE+0.161
cil+0.157
lich+0.156
eting+0.152
wic+0.140
Neg logit contributions
phis-0.253
eatures-0.225
 adolesc-0.221
utonium-0.215
inatory-0.212
Token
Token ID198
Feature activation-4.00e-01

Pos logit contributions
ICLE+0.336
cil+0.327
lich+0.324
eting+0.316
wic+0.294
Neg logit contributions
phis-0.481
eatures-0.411
 adolesc-0.409
utonium-0.405
eries-0.402
TokenDet
Token ID11242
Feature activation-1.18e+00

Pos logit contributions
ICLE+0.259
cil+0.252
lich+0.251
eting+0.246
wic+0.226
Neg logit contributions
phis-0.406
eatures-0.355
 adolesc-0.351
utonium-0.344
eries-0.341
Token Sgt
Token ID22925
Feature activation-4.77e-01

Pos logit contributions
cil+0.935
ICLE+0.933
lich+0.910
eting+0.903
wic+0.848
Neg logit contributions
phis-1.029
eatures-0.910
 adolesc-0.887
utonium-0.852
inatory-0.831
Token Ronnie
Token ID40892
Feature activation+2.21e+00

Pos logit contributions
ICLE+0.337
cil+0.330
lich+0.327
eting+0.321
wic+0.297
Neg logit contributions
phis-0.460
eatures-0.407
 adolesc-0.398
utonium-0.387
inatory-0.380
Token Payne
Token ID32788
Feature activation-5.33e+00

Pos logit contributions
phis+2.116
eatures+1.842
 adolesc+1.817
utonium+1.772
eries+1.762
Neg logit contributions
ICLE-1.562
cil-1.518
lich-1.510
eting-1.471
Acknowled-1.369
Token asked
Token ID1965
Feature activation-8.59e-01

Pos logit contributions
cil+2.652
lich+2.647
ICLE+2.642
eting+2.560
wic+2.318
Neg logit contributions
phis-6.164
eatures-5.591
 adolesc-5.463
utonium-5.335
inatory-5.268
Token anyone
Token ID2687
Feature activation-1.87e-01

Pos logit contributions
ICLE+0.515
cil+0.499
lich+0.496
eting+0.483
wic+0.441
Neg logit contributions
phis-0.920
eatures-0.820
 adolesc-0.808
utonium-0.785
inatory-0.776
Token with
Token ID351
Feature activation-1.04e+00

Pos logit contributions
ICLE+0.108
cil+0.103
lich+0.102
eting+0.100
wic+0.091
Neg logit contributions
phis-0.206
eatures-0.183
 adolesc-0.181
utonium-0.177
eries-0.175
Token information
Token ID1321
Feature activation-1.01e+00

Pos logit contributions
ICLE+0.697
cil+0.678
lich+0.675
eting+0.660
wic+0.608
Neg logit contributions
phis-1.039
eatures-0.921
 adolesc-0.903
utonium-0.879
inatory-0.865
Token to
Token ID284
Feature activation+6.14e-02

Pos logit contributions
ICLE+0.583
cil+0.567
lich+0.564
eting+0.550
wic+0.497
Neg logit contributions
phis-1.107
eatures-0.995
 adolesc-0.976
utonium-0.952
inatory-0.938
Token the
Token ID262
Feature activation+4.73e-01

Pos logit contributions
ICLE+0.433
cil+0.423
lich+0.419
eting+0.409
wic+0.369
Neg logit contributions
phis-0.846
eatures-0.757
 adolesc-0.746
utonium-0.728
inatory-0.718
Token fresh
Token ID4713
Feature activation+1.11e+00

Pos logit contributions
phis+0.421
eatures+0.367
 adolesc+0.360
utonium+0.349
inatory+0.342
Neg logit contributions
ICLE-0.369
cil-0.360
lich-0.359
eting-0.352
wic-0.328
Token citrus
Token ID35405
Feature activation-1.19e+00

Pos logit contributions
phis+1.102
eatures+0.969
 adolesc+0.956
utonium+0.928
eries+0.917
Neg logit contributions
ICLE-0.758
lich-0.729
cil-0.729
eting-0.715
wic-0.656
Token aroma
Token ID31242
Feature activation+6.80e-01

Pos logit contributions
ICLE+0.717
cil+0.694
lich+0.691
eting+0.673
wic+0.614
Neg logit contributions
phis-1.271
eatures-1.132
 adolesc-1.115
utonium-1.087
inatory-1.073
Token from
Token ID422
Feature activation+1.43e+00

Pos logit contributions
phis+0.752
eatures+0.670
 adolesc+0.661
utonium+0.644
inatory+0.637
Neg logit contributions
ICLE-0.387
cil-0.372
lich-0.371
eting-0.357
wic-0.325
Token Amar
Token ID44291
Feature activation-5.33e+00

Pos logit contributions
phis+1.456
eatures+1.290
 adolesc+1.270
utonium+1.233
inatory+1.215
Neg logit contributions
ICLE-0.941
cil-0.913
lich-0.910
eting-0.889
wic-0.817
Tokenillo
Token ID16111
Feature activation-2.17e+00

Pos logit contributions
ICLE+3.122
cil+3.062
lich+3.023
eting+2.943
wic+2.674
Neg logit contributions
phis-5.770
eatures-5.174
 adolesc-5.084
utonium-4.958
inatory-4.884
Token hops
Token ID29438
Feature activation-1.66e+00

Pos logit contributions
ICLE+1.238
cil+1.212
lich+1.199
eting+1.167
wic+1.061
Neg logit contributions
phis-2.373
eatures-2.135
 adolesc-2.091
utonium-2.043
inatory-2.012
Token;
Token ID26
Feature activation-3.73e-02

Pos logit contributions
ICLE+0.882
cil+0.857
lich+0.850
eting+0.827
wic+0.742
Neg logit contributions
phis-1.889
eatures-1.701
 adolesc-1.672
utonium-1.634
inatory-1.611
Token something
Token ID1223
Feature activation+9.38e-01

Pos logit contributions
ICLE+0.023
cil+0.023
lich+0.023
eting+0.022
wic+0.020
Neg logit contributions
phis-0.039
eatures-0.035
 adolesc-0.034
utonium-0.033
inatory-0.033
Token lic
Token ID3476
Feature activation+4.38e+00

Pos logit contributions
phis+0.971
eatures+0.863
 adolesc+0.849
utonium+0.827
inatory+0.814
Neg logit contributions
ICLE-0.595
cil-0.578
lich-0.576
eting-0.562
wic-0.514
Token-
Token ID12
Feature activation-2.78e-01

Pos logit contributions
ICLE+1.117
cil+1.085
lich+1.078
eting+1.049
wic+0.949
Neg logit contributions
phis-2.163
eatures-1.940
 adolesc-1.907
utonium-1.862
inatory-1.835
Token Fle
Token ID12005
Feature activation+9.63e-01

Pos logit contributions
ICLE+0.204
cil+0.198
lich+0.197
eting+0.194
wic+0.179
Neg logit contributions
phis-0.263
eatures-0.229
 adolesc-0.223
utonium-0.218
eries-0.214
Tokenury
Token ID1601
Feature activation+1.01e+00

Pos logit contributions
phis+0.721
eatures+0.592
utonium+0.572
 adolesc+0.569
eries+0.563
Neg logit contributions
ICLE-0.896
cil-0.876
lich-0.870
eting-0.852
Acknowled-0.812
Token,
Token ID11
Feature activation-3.97e-03

Pos logit contributions
phis+0.972
eatures+0.854
 adolesc+0.832
utonium+0.814
eries+0.805
Neg logit contributions
ICLE-0.715
cil-0.699
lich-0.693
eting-0.681
Acknowled-0.631
Token Sidney
Token ID35727
Feature activation-5.23e+00

Pos logit contributions
ICLE+0.003
cil+0.002
lich+0.002
eting+0.002
wic+0.002
Neg logit contributions
phis-0.004
eatures-0.004
 adolesc-0.004
utonium-0.003
inatory-0.003
Token Crosby
Token ID33098
Feature activation-5.33e+00

Pos logit contributions
ICLE+2.698
cil+2.661
lich+2.598
eting+2.577
wic+2.279
Neg logit contributions
phis-5.991
eatures-5.409
 adolesc-5.344
utonium-5.134
eries-5.073
Token,
Token ID11
Feature activation-5.48e-01

Pos logit contributions
ICLE+2.794
cil+2.728
lich+2.709
eting+2.613
wic+2.357
Neg logit contributions
phis-6.020
eatures-5.435
 adolesc-5.359
utonium-5.202
inatory-5.126
Token Ev
Token ID4319
Feature activation-9.98e-01

Pos logit contributions
ICLE+0.381
cil+0.372
lich+0.370
eting+0.362
wic+0.334
Neg logit contributions
phis-0.536
eatures-0.473
 adolesc-0.464
utonium-0.451
inatory-0.444
Tokengen
Token ID5235
Feature activation-2.37e+00

Pos logit contributions
ICLE+0.798
cil+0.788
lich+0.784
eting+0.768
wic+0.717
Neg logit contributions
phis-0.864
eatures-0.756
 adolesc-0.738
utonium-0.711
inatory-0.697
Tokeni
Token ID72
Feature activation-2.82e-01

Pos logit contributions
ICLE+1.593
cil+1.581
lich+1.563
eting+1.536
wic+1.412
Neg logit contributions
phis-2.348
eatures-2.091
 adolesc-2.072
utonium-1.997
inatory-1.959
Token Malk
Token ID41980
Feature activation-1.07e+00

Pos logit contributions
ICLE+0.159
cil+0.155
lich+0.154
eting+0.150
wic+0.135
Neg logit contributions
phis-0.312
eatures-0.280
 adolesc-0.276
utonium-0.269
inatory-0.265
Token could
Token ID714
Feature activation+1.83e-01

Pos logit contributions
ICLE+0.916
cil+0.895
lich+0.891
eting+0.871
wic+0.805
Neg logit contributions
phis-1.255
eatures-1.107
 adolesc-1.085
utonium-1.055
inatory-1.038
Token shuffle
Token ID36273
Feature activation-1.06e+00

Pos logit contributions
phis+0.146
eatures+0.126
 adolesc+0.123
utonium+0.118
inatory+0.116
Neg logit contributions
ICLE-0.159
cil-0.156
lich-0.156
eting-0.153
wic-0.143
Token things
Token ID1243
Feature activation-1.35e+00

Pos logit contributions
ICLE+0.668
cil+0.652
lich+0.649
eting+0.635
wic+0.577
Neg logit contributions
phis-1.108
eatures-0.990
 adolesc-0.968
utonium-0.946
inatory-0.930
Token around
Token ID1088
Feature activation+9.92e-01

Pos logit contributions
ICLE+0.816
cil+0.797
lich+0.796
eting+0.777
wic+0.702
Neg logit contributions
phis-1.440
eatures-1.292
 adolesc-1.264
utonium-1.231
inatory-1.210
Token for
Token ID329
Feature activation-5.02e-01

Pos logit contributions
phis+1.103
eatures+0.987
 adolesc+0.973
utonium+0.951
inatory+0.938
Neg logit contributions
ICLE-0.554
cil-0.538
lich-0.532
eting-0.517
wic-0.469
Token Hong
Token ID9764
Feature activation+3.25e+00

Pos logit contributions
ICLE+0.339
cil+0.332
lich+0.330
eting+0.323
wic+0.296
Neg logit contributions
phis-0.499
eatures-0.443
 adolesc-0.434
utonium-0.423
inatory-0.416
Token Kong
Token ID9071
Feature activation+4.55e+00

Pos logit contributions
phis+2.114
eatures+1.627
 adolesc+1.610
utonium+1.604
eries+1.578
Neg logit contributions
ICLE-3.300
cil-3.165
lich-3.162
eting-3.134
Acknowled-2.994
Token,
Token ID11
Feature activation+2.68e-01

Pos logit contributions
phis+4.923
eatures+4.324
 adolesc+4.270
utonium+4.185
 Jagu+4.164
Neg logit contributions
ICLE-2.625
cil-2.524
lich-2.480
eting-2.416
Acknowled-2.241
Token though
Token ID996
Feature activation-9.02e-01

Pos logit contributions
phis+0.279
eatures+0.249
 adolesc+0.244
utonium+0.238
inatory+0.234
Neg logit contributions
ICLE-0.169
cil-0.165
lich-0.164
eting-0.160
wic-0.146
Token these
Token ID777
Feature activation-2.45e-01

Pos logit contributions
ICLE+0.532
cil+0.517
lich+0.514
eting+0.500
wic+0.454
Neg logit contributions
phis-0.977
eatures-0.874
 adolesc-0.858
utonium-0.838
inatory-0.826
Token outcomes
Token ID10906
Feature activation-7.06e-02

Pos logit contributions
ICLE+0.177
cil+0.173
lich+0.172
eting+0.168
wic+0.156
Neg logit contributions
phis-0.232
eatures-0.204
 adolesc-0.200
utonium-0.194
inatory-0.191
Token its
Token ID663
Feature activation+1.70e+00

Pos logit contributions
phis+0.893
eatures+0.784
 adolesc+0.769
utonium+0.744
inatory+0.736
Neg logit contributions
ICLE-0.668
cil-0.652
lich-0.649
eting-0.634
wic-0.591
Token government
Token ID1230
Feature activation-6.56e-02

Pos logit contributions
phis+1.572
eatures+1.368
 adolesc+1.348
utonium+1.300
inatory+1.289
Neg logit contributions
ICLE-1.260
lich-1.232
cil-1.231
eting-1.201
wic-1.125
Token has
Token ID468
Feature activation+1.84e+00

Pos logit contributions
ICLE+0.051
cil+0.050
lich+0.050
eting+0.049
wic+0.046
Neg logit contributions
phis-0.058
eatures-0.051
 adolesc-0.050
utonium-0.048
inatory-0.047
Token a
Token ID257
Feature activation+3.22e-01

Pos logit contributions
phis+1.888
eatures+1.667
 adolesc+1.646
utonium+1.599
inatory+1.584
Neg logit contributions
ICLE-1.180
cil-1.147
lich-1.144
eting-1.115
wic-1.035
Token good
Token ID922
Feature activation+3.73e-01

Pos logit contributions
phis+0.310
eatures+0.274
 adolesc+0.268
utonium+0.261
inatory+0.256
Neg logit contributions
ICLE-0.228
cil-0.222
lich-0.221
eting-0.217
wic-0.200
Token reputation
Token ID8507
Feature activation+3.29e+00

Pos logit contributions
phis+0.352
eatures+0.307
 adolesc+0.303
utonium+0.292
inatory+0.289
Neg logit contributions
ICLE-0.271
cil-0.265
lich-0.264
eting-0.257
wic-0.241
Token,
Token ID11
Feature activation+1.83e-01

Pos logit contributions
phis+3.588
eatures+3.175
 adolesc+3.149
utonium+3.057
inatory+3.028
Neg logit contributions
ICLE-1.901
cil-1.826
lich-1.812
eting-1.744
wic-1.611
Token the
Token ID262
Feature activation+3.73e-01

Pos logit contributions
phis+0.194
eatures+0.173
 adolesc+0.170
utonium+0.166
inatory+0.164
Neg logit contributions
ICLE-0.112
cil-0.109
lich-0.108
eting-0.105
wic-0.096
Token instruments
Token ID12834
Feature activation-2.67e+00

Pos logit contributions
phis+0.360
eatures+0.318
 adolesc+0.311
utonium+0.303
inatory+0.297
Neg logit contributions
ICLE-0.263
cil-0.258
lich-0.256
eting-0.251
wic-0.231
Token that
Token ID326
Feature activation-5.79e-02

Pos logit contributions
ICLE+1.562
cil+1.530
lich+1.517
eting+1.489
Acknowled+1.340
Neg logit contributions
phis-2.885
eatures-2.583
 adolesc-2.539
utonium-2.469
inatory-2.422
Token it
Token ID340
Feature activation+5.74e-01

Pos logit contributions
ICLE+0.045
cil+0.044
lich+0.044
eting+0.043
wic+0.040
Neg logit contributions
phis-0.052
eatures-0.045
 adolesc-0.044
utonium-0.043
inatory-0.042
Token
Token ID198
Feature activation-1.90e-02

Pos logit contributions
ICLE+0.210
cil+0.205
lich+0.204
eting+0.199
wic+0.183
Neg logit contributions
phis-0.330
eatures-0.293
 adolesc-0.288
utonium-0.280
inatory-0.276
Token
Token ID198
Feature activation+6.96e-02

Pos logit contributions
ICLE+0.013
cil+0.013
lich+0.013
eting+0.012
wic+0.012
Neg logit contributions
phis-0.018
utonium-0.015
eatures-0.015
 adolesc-0.015
eries-0.015
TokenThen
Token ID6423
Feature activation-5.80e-02

Pos logit contributions
phis+0.072
eatures+0.063
 adolesc+0.062
utonium+0.061
eries+0.060
Neg logit contributions
ICLE-0.044
cil-0.043
lich-0.043
eting-0.042
wic-0.038
Token he
Token ID339
Feature activation-3.77e-01

Pos logit contributions
ICLE+0.033
cil+0.032
lich+0.031
eting+0.031
wic+0.028
Neg logit contributions
phis-0.064
eatures-0.058
 adolesc-0.057
utonium-0.055
inatory-0.055
Token developed
Token ID4166
Feature activation-3.07e-01

Pos logit contributions
ICLE+0.266
cil+0.260
lich+0.259
eting+0.254
wic+0.234
Neg logit contributions
phis-0.364
eatures-0.322
 adolesc-0.316
utonium-0.306
inatory-0.301
Token graft
Token ID38455
Feature activation+3.05e+00

Pos logit contributions
ICLE+0.211
cil+0.206
lich+0.205
eting+0.201
wic+0.185
Neg logit contributions
phis-0.302
eatures-0.267
 adolesc-0.262
utonium-0.254
inatory-0.250
Token-
Token ID12
Feature activation-9.62e-02

Pos logit contributions
phis+2.638
eatures+2.283
 adolesc+2.225
utonium+2.165
inatory+2.131
Neg logit contributions
ICLE-2.449
cil-2.381
lich-2.357
eting-2.315
Acknowled-2.180
Tokenvers
Token ID690
Feature activation+2.13e+00

Pos logit contributions
ICLE+0.066
cil+0.065
lich+0.065
eting+0.063
wic+0.058
Neg logit contributions
phis-0.094
eatures-0.083
 adolesc-0.082
utonium-0.079
inatory-0.078
Tokenus
Token ID385
Feature activation-5.05e-01

Pos logit contributions
phis+1.747
eatures+1.505
 adolesc+1.442
utonium+1.423
inatory+1.399
Neg logit contributions
ICLE-1.806
cil-1.758
lich-1.746
eting-1.719
Acknowled-1.632
Token-
Token ID12
Feature activation-5.49e-01

Pos logit contributions
ICLE+0.271
cil+0.262
lich+0.260
eting+0.252
wic+0.227
Neg logit contributions
phis-0.573
eatures-0.513
 adolesc-0.506
utonium-0.496
inatory-0.489
Tokenhost
Token ID4774
Feature activation+2.91e-01

Pos logit contributions
ICLE+0.365
cil+0.357
lich+0.355
eting+0.347
wic+0.319
Neg logit contributions
phis-0.553
eatures-0.491
 adolesc-0.482
utonium-0.469
inatory-0.461
Token The
Token ID383
Feature activation-2.71e-01

Pos logit contributions
ICLE+0.490
cil+0.478
lich+0.475
eting+0.462
wic+0.431
Neg logit contributions
phis-0.719
eatures-0.634
 adolesc-0.620
utonium-0.606
inatory-0.602
Token Hill
Token ID3327
Feature activation+1.20e+00

Pos logit contributions
ICLE+0.188
cil+0.183
lich+0.180
eting+0.177
wic+0.165
Neg logit contributions
phis-0.263
eatures-0.230
 adolesc-0.227
utonium-0.223
eries-0.221
Token.
Token ID13
Feature activation-2.04e-02

Pos logit contributions
phis+1.334
 adolesc+1.167
eatures+1.161
utonium+1.148
inatory+1.146
Neg logit contributions
ICLE-0.672
lich-0.645
cil-0.642
eting-0.623
wic-0.569
Token<|endoftext|>
Token ID50256
Feature activation-3.37e-01

Pos logit contributions
ICLE+0.011
cil+0.010
lich+0.010
eting+0.010
Acknowled+0.009
Neg logit contributions
phis-0.024
eatures-0.021
 adolesc-0.021
utonium-0.020
inatory-0.020
TokenK
Token ID42
Feature activation+2.04e+00

Pos logit contributions
ICLE+0.224
cil+0.218
lich+0.217
eting+0.212
wic+0.195
Neg logit contributions
phis-0.339
eatures-0.300
 adolesc-0.294
utonium-0.287
inatory-0.282
TokenUAL
Token ID25620
Feature activation+4.16e+00

Pos logit contributions
phis+1.935
eatures+1.694
 adolesc+1.657
utonium+1.616
eries+1.591
Neg logit contributions
ICLE-1.476
cil-1.437
lich-1.428
eting-1.397
Acknowled-1.299
TokenA
Token ID32
Feature activation+3.52e-01

Pos logit contributions
phis+3.988
eatures+3.399
 adolesc+3.383
utonium+3.318
orea+3.284
Neg logit contributions
cil-2.864
lich-2.859
ICLE-2.833
eting-2.807
wic-2.600
Token L
Token ID406
Feature activation+1.46e+00

Pos logit contributions
phis+0.281
 adolesc+0.229
orea+0.223
eatures+0.221
 Jagu+0.220
Neg logit contributions
lich-0.300
ICLE-0.297
cil-0.294
eting-0.287
entimes-0.277
TokenUMP
Token ID20476
Feature activation+3.24e+00

Pos logit contributions
phis+1.151
 adolesc+0.936
eatures+0.920
utonium+0.909
orea+0.899
Neg logit contributions
ICLE-1.264
cil-1.260
lich-1.245
eting-1.230
entimes-1.172
TokenUR
Token ID4261
Feature activation-6.68e-02

Pos logit contributions
phis+3.080
eatures+2.685
 adolesc+2.647
utonium+2.577
inatory+2.534
Neg logit contributions
ICLE-2.311
cil-2.285
lich-2.270
eting-2.207
wic-2.056
Token --
Token ID1377
Feature activation+2.61e-01

Pos logit contributions
ICLE+0.036
cil+0.035
lich+0.035
eting+0.034
wic+0.030
Neg logit contributions
phis-0.076
eatures-0.068
 adolesc-0.067
utonium-0.065
inatory-0.065
Token be
Token ID307
Feature activation-7.38e-01

Pos logit contributions
phis+0.319
eatures+0.277
 adolesc+0.271
utonium+0.261
inatory+0.255
Neg logit contributions
ICLE-0.317
cil-0.312
lich-0.310
eting-0.305
wic-0.285
Token the
Token ID262
Feature activation-5.76e-01

Pos logit contributions
ICLE+0.480
cil+0.469
lich+0.466
eting+0.456
wic+0.417
Neg logit contributions
phis-0.752
eatures-0.669
 adolesc-0.655
utonium-0.639
inatory-0.628
Token first
Token ID717
Feature activation-4.68e-01

Pos logit contributions
ICLE+0.466
cil+0.457
lich+0.454
eting+0.446
wic+0.417
Neg logit contributions
phis-0.497
eatures-0.433
 adolesc-0.421
utonium-0.408
inatory-0.400
Token in
Token ID287
Feature activation+9.65e-02

Pos logit contributions
ICLE+0.292
cil+0.284
lich+0.283
eting+0.276
wic+0.253
Neg logit contributions
phis-0.489
eatures-0.435
 adolesc-0.428
utonium-0.417
inatory-0.412
Token the
Token ID262
Feature activation+5.12e-01

Pos logit contributions
phis+0.092
eatures+0.081
 adolesc+0.079
utonium+0.077
inatory+0.076
Neg logit contributions
ICLE-0.069
cil-0.068
lich-0.067
eting-0.066
wic-0.061
Token Philippines
Token ID13316
Feature activation+3.37e+00

Pos logit contributions
phis+0.461
eatures+0.402
 adolesc+0.393
utonium+0.381
inatory+0.374
Neg logit contributions
ICLE-0.396
cil-0.387
lich-0.386
eting-0.378
wic-0.352
Token to
Token ID284
Feature activation+1.09e+00

Pos logit contributions
phis+3.257
eatures+2.834
 adolesc+2.833
utonium+2.744
inatory+2.720
Neg logit contributions
ICLE-2.331
lich-2.280
cil-2.264
eting-2.220
wic-2.053
Token enforce
Token ID4605
Feature activation-6.10e-01

Pos logit contributions
phis+0.940
eatures+0.819
 adolesc+0.803
utonium+0.775
inatory+0.757
Neg logit contributions
ICLE-0.878
cil-0.864
lich-0.858
eting-0.842
wic-0.787
Token an
Token ID281
Feature activation+7.31e-02

Pos logit contributions
ICLE+0.395
cil+0.386
lich+0.383
eting+0.374
wic+0.343
Neg logit contributions
phis-0.624
eatures-0.554
 adolesc-0.544
utonium-0.530
inatory-0.522
Token outright
Token ID15828
Feature activation+3.99e-01

Pos logit contributions
phis+0.070
eatures+0.062
 adolesc+0.061
utonium+0.059
inatory+0.059
Neg logit contributions
ICLE-0.051
cil-0.050
lich-0.050
eting-0.049
wic-0.045
Token ban
Token ID3958
Feature activation+8.40e-01

Pos logit contributions
phis+0.422
eatures+0.372
 adolesc+0.368
utonium+0.359
inatory+0.356
Neg logit contributions
ICLE-0.245
cil-0.237
lich-0.235
eting-0.229
wic-0.212
Token created
Token ID2727
Feature activation+5.13e-01

Pos logit contributions
phis+1.287
eatures+1.133
 adolesc+1.107
utonium+1.079
eries+1.060
Neg logit contributions
ICLE-1.006
cil-0.979
lich-0.973
eting-0.954
wic-0.886
Token on
Token ID319
Feature activation+2.76e-01

Pos logit contributions
phis+0.520
eatures+0.461
 adolesc+0.453
utonium+0.441
inatory+0.434
Neg logit contributions
ICLE-0.338
cil-0.330
lich-0.328
eting-0.320
wic-0.294
Token the
Token ID262
Feature activation+6.22e-01

Pos logit contributions
phis+0.249
eatures+0.217
 adolesc+0.213
utonium+0.207
eries+0.203
Neg logit contributions
ICLE-0.212
cil-0.207
lich-0.206
eting-0.201
wic-0.188
Token basis
Token ID4308
Feature activation+7.97e-01

Pos logit contributions
phis+0.541
eatures+0.470
 adolesc+0.458
utonium+0.445
inatory+0.436
Neg logit contributions
ICLE-0.499
cil-0.490
lich-0.487
eting-0.479
wic-0.446
Token of
Token ID286
Feature activation+1.83e-03

Pos logit contributions
phis+0.874
eatures+0.783
 adolesc+0.770
utonium+0.752
inatory+0.740
Neg logit contributions
ICLE-0.458
cil-0.445
lich-0.442
eting-0.430
wic-0.390
Token the
Token ID262
Feature activation+7.85e-01

Pos logit contributions
phis+0.002
eatures+0.002
 adolesc+0.002
utonium+0.002
inatory+0.002
Neg logit contributions
ICLE-0.001
cil-0.001
lich-0.001
eting-0.001
wic-0.001
Token original
Token ID2656
Feature activation+1.60e+00

Pos logit contributions
phis+0.737
eatures+0.647
 adolesc+0.635
utonium+0.617
inatory+0.606
Neg logit contributions
ICLE-0.575
cil-0.562
lich-0.560
eting-0.548
wic-0.508
Token M
Token ID337
Feature activation+8.75e-01

Pos logit contributions
phis+1.525
eatures+1.338
 adolesc+1.314
utonium+1.279
inatory+1.258
Neg logit contributions
ICLE-1.149
cil-1.122
lich-1.115
eting-1.090
wic-1.011
Tokenoom
Token ID4207
Feature activation+1.57e+00

Pos logit contributions
phis+0.896
eatures+0.786
 adolesc+0.774
utonium+0.763
inatory+0.752
Neg logit contributions
ICLE-0.564
cil-0.549
lich-0.546
eting-0.532
wic-0.489
Tokenin
Token ID259
Feature activation-4.48e-01

Pos logit contributions
phis+1.670
eatures+1.491
 adolesc+1.462
utonium+1.430
inatory+1.412
Neg logit contributions
ICLE-0.956
cil-0.931
lich-0.924
eting-0.899
wic-0.821
Token works
Token ID2499
Feature activation+1.35e+00

Pos logit contributions
ICLE+0.333
cil+0.326
lich+0.324
eting+0.318
wic+0.295
Neg logit contributions
phis-0.415
eatures-0.364
 adolesc-0.356
utonium-0.346
inatory-0.340
Token for
Token ID329
Feature activation-6.29e-01

Pos logit contributions
phis+0.051
eatures+0.045
 adolesc+0.045
utonium+0.043
inatory+0.043
Neg logit contributions
ICLE-0.031
cil-0.030
lich-0.030
eting-0.029
wic-0.026
Token determining
Token ID13213
Feature activation-9.99e-01

Pos logit contributions
ICLE+0.427
cil+0.417
lich+0.415
eting+0.406
wic+0.373
Neg logit contributions
phis-0.624
eatures-0.553
 adolesc-0.542
utonium-0.527
inatory-0.517
Token environmental
Token ID6142
Feature activation-1.00e+00

Pos logit contributions
ICLE+0.613
cil+0.596
lich+0.593
eting+0.579
wic+0.527
Neg logit contributions
phis-1.056
eatures-0.945
 adolesc-0.925
utonium-0.903
eries-0.887
Token racism
Token ID10713
Feature activation+8.24e-01

Pos logit contributions
ICLE+0.745
lich+0.731
cil+0.729
eting+0.717
Acknowled+0.661
Neg logit contributions
phis-0.925
eatures-0.822
 adolesc-0.799
utonium-0.775
eries-0.758
Token.
Token ID13
Feature activation-4.29e-01

Pos logit contributions
phis+0.921
eatures+0.826
 adolesc+0.813
utonium+0.794
inatory+0.784
Neg logit contributions
ICLE-0.456
cil-0.443
lich-0.440
eting-0.427
wic-0.385
Token Advoc
Token ID37866
Feature activation+1.05e+00

Pos logit contributions
ICLE+0.287
cil+0.281
lich+0.279
eting+0.273
wic+0.251
Neg logit contributions
phis-0.431
eatures-0.383
 adolesc-0.375
utonium-0.365
inatory-0.358
Tokenates
Token ID689
Feature activation-5.39e-01

Pos logit contributions
phis+0.743
eatures+0.620
 adolesc+0.598
utonium+0.579
inatory+0.564
Neg logit contributions
ICLE-1.023
cil-1.000
lich-0.997
eting-0.981
wic-0.928
Token and
Token ID290
Feature activation-8.10e-02

Pos logit contributions
ICLE+0.360
cil+0.350
lich+0.348
eting+0.340
wic+0.313
Neg logit contributions
phis-0.542
eatures-0.480
 adolesc-0.471
utonium-0.459
inatory-0.451
Token recipient
Token ID17800
Feature activation+5.33e-01

Pos logit contributions
ICLE+0.053
cil+0.052
lich+0.052
eting+0.050
wic+0.047
Neg logit contributions
phis-0.082
eatures-0.073
 adolesc-0.071
utonium-0.069
inatory-0.068
Token agencies
Token ID5942
Feature activation-1.39e+00

Pos logit contributions
phis+0.517
eatures+0.456
 adolesc+0.447
utonium+0.435
inatory+0.428
Neg logit contributions
ICLE-0.375
cil-0.365
lich-0.363
eting-0.356
wic-0.329
Token alike
Token ID12936
Feature activation-5.48e-01

Pos logit contributions
ICLE+1.025
cil+1.000
lich+0.996
eting+0.975
wic+0.904
Neg logit contributions
phis-1.297
eatures-1.136
 adolesc-1.113
utonium-1.082
inatory-1.064
Token her
Token ID607
Feature activation+3.82e-01

Pos logit contributions
ICLE+0.403
cil+0.393
lich+0.390
eting+0.381
wic+0.348
Neg logit contributions
phis-0.684
eatures-0.610
 adolesc-0.599
utonium-0.584
inatory-0.575
Token travel
Token ID3067
Feature activation-1.98e+00

Pos logit contributions
phis+0.386
eatures+0.342
 adolesc+0.337
utonium+0.327
inatory+0.323
Neg logit contributions
ICLE-0.251
cil-0.245
lich-0.243
eting-0.237
wic-0.219
Token agent
Token ID5797
Feature activation-9.54e-01

Pos logit contributions
ICLE+1.276
cil+1.244
lich+1.239
eting+1.212
wic+1.109
Neg logit contributions
phis-2.031
eatures-1.812
 adolesc-1.774
utonium-1.729
inatory-1.697
Token earlier
Token ID2961
Feature activation-8.96e-01

Pos logit contributions
ICLE+0.532
cil+0.517
lich+0.513
eting+0.499
wic+0.451
Neg logit contributions
phis-1.062
eatures-0.953
 adolesc-0.937
utonium-0.915
inatory-0.902
Token in
Token ID287
Feature activation-2.27e-01

Pos logit contributions
ICLE+0.531
cil+0.516
lich+0.513
eting+0.500
wic+0.455
Neg logit contributions
phis-0.967
eatures-0.864
 adolesc-0.849
utonium-0.829
inatory-0.816
Token the
Token ID262
Feature activation+2.73e-01

Pos logit contributions
ICLE+0.133
cil+0.129
lich+0.129
eting+0.125
wic+0.114
Neg logit contributions
phis-0.246
eatures-0.220
 adolesc-0.217
utonium-0.211
inatory-0.208
Token week
Token ID1285
Feature activation+7.84e-01

Pos logit contributions
phis+0.265
eatures+0.234
 adolesc+0.230
utonium+0.223
inatory+0.220
Neg logit contributions
ICLE-0.191
cil-0.187
lich-0.186
eting-0.181
wic-0.168
Token to
Token ID284
Feature activation+3.74e-01

Pos logit contributions
phis+0.908
eatures+0.812
 adolesc+0.803
utonium+0.784
inatory+0.775
Neg logit contributions
ICLE-0.403
cil-0.388
lich-0.384
eting-0.371
wic-0.333
Token a
Token ID257
Feature activation-2.20e-01

Pos logit contributions
phis+0.333
eatures+0.288
 adolesc+0.282
utonium+0.274
inatory+0.269
Neg logit contributions
ICLE-0.293
cil-0.286
lich-0.284
eting-0.279
wic-0.261
Token different
Token ID1180
Feature activation-1.26e+00

Pos logit contributions
ICLE+0.154
cil+0.150
lich+0.150
eting+0.146
wic+0.135
Neg logit contributions
phis-0.213
eatures-0.187
 adolesc-0.184
utonium-0.179
inatory-0.176
Token flight
Token ID5474
Feature activation-1.95e+00

Pos logit contributions
ICLE+0.930
cil+0.909
lich+0.905
eting+0.887
wic+0.822
Neg logit contributions
phis-1.179
eatures-1.036
 adolesc-1.014
utonium-0.986
inatory-0.967
Token World
Token ID2159
Feature activation+1.31e+00

Pos logit contributions
phis+0.335
eatures+0.294
 adolesc+0.289
utonium+0.281
inatory+0.276
Neg logit contributions
ICLE-0.254
cil-0.248
lich-0.247
eting-0.242
wic-0.224
Token Trade
Token ID9601
Feature activation+1.46e+00

Pos logit contributions
phis+1.192
eatures+1.042
 adolesc+1.019
utonium+0.988
inatory+0.972
Neg logit contributions
ICLE-1.005
cil-0.984
lich-0.979
eting-0.960
wic-0.893
Token Center
Token ID3337
Feature activation-5.71e-01

Pos logit contributions
phis+1.707
eatures+1.541
 adolesc+1.517
utonium+1.482
inatory+1.463
Neg logit contributions
ICLE-0.727
cil-0.704
lich-0.699
eting-0.677
wic-0.604
Token towers
Token ID18028
Feature activation+2.58e-01

Pos logit contributions
ICLE+0.420
cil+0.410
lich+0.409
eting+0.400
wic+0.371
Neg logit contributions
phis-0.535
eatures-0.470
 adolesc-0.460
utonium-0.445
inatory-0.439
Token has
Token ID468
Feature activation+1.23e+00

Pos logit contributions
phis+0.262
eatures+0.232
 adolesc+0.228
utonium+0.222
inatory+0.219
Neg logit contributions
ICLE-0.170
cil-0.166
lich-0.165
eting-0.161
wic-0.148
Token been
Token ID587
Feature activation+1.80e-01

Pos logit contributions
phis+1.071
eatures+0.927
 adolesc+0.910
utonium+0.884
eries+0.864
Neg logit contributions
ICLE-0.985
cil-0.964
lich-0.958
eting-0.941
wic-0.882
Token injected
Token ID25077
Feature activation+8.21e-01

Pos logit contributions
phis+0.168
eatures+0.148
 adolesc+0.145
utonium+0.140
inatory+0.138
Neg logit contributions
ICLE-0.133
cil-0.130
lich-0.129
eting-0.127
wic-0.118
Token into
Token ID656
Feature activation+6.44e-01

Pos logit contributions
phis+0.749
eatures+0.652
 adolesc+0.641
utonium+0.623
inatory+0.611
Neg logit contributions
ICLE-0.623
cil-0.610
lich-0.606
eting-0.594
wic-0.553
Token a
Token ID257
Feature activation+1.64e-01

Pos logit contributions
phis+0.644
eatures+0.569
 adolesc+0.559
utonium+0.544
inatory+0.535
Neg logit contributions
ICLE-0.434
cil-0.423
lich-0.421
eting-0.411
wic-0.379
Token single
Token ID2060
Feature activation+5.33e-02

Pos logit contributions
phis+0.150
eatures+0.132
 adolesc+0.129
utonium+0.125
inatory+0.123
Neg logit contributions
ICLE-0.123
cil-0.121
lich-0.120
eting-0.118
wic-0.109
Token 46
Token ID6337
Feature activation-1.97e-01

Pos logit contributions
phis+0.051
eatures+0.045
 adolesc+0.044
utonium+0.043
inatory+0.042
Neg logit contributions
ICLE-0.038
cil-0.037
lich-0.037
eting-0.036
wic-0.034
Token legs
Token ID7405
Feature activation+7.96e-01

Pos logit contributions
ICLE+0.938
cil+0.920
lich+0.916
eting+0.900
wic+0.845
Neg logit contributions
phis-0.885
eatures-0.760
 adolesc-0.742
utonium-0.717
inatory-0.702
Token open
Token ID1280
Feature activation-2.07e+00

Pos logit contributions
phis+0.788
eatures+0.690
 adolesc+0.681
utonium+0.664
eries+0.656
Neg logit contributions
ICLE-0.545
cil-0.526
lich-0.524
eting-0.509
wic-0.472
Token.
Token ID13
Feature activation-2.80e-01

Pos logit contributions
ICLE+1.163
cil+1.131
lich+1.124
eting+1.097
wic+0.987
Neg logit contributions
phis-2.302
eatures-2.070
 adolesc-2.032
utonium-1.984
inatory-1.954
Token I
Token ID314
Feature activation-1.65e-01

Pos logit contributions
ICLE+0.174
cil+0.169
lich+0.168
eting+0.164
wic+0.150
Neg logit contributions
phis-0.293
eatures-0.260
 adolesc-0.256
utonium-0.250
inatory-0.246
Token found
Token ID1043
Feature activation-3.99e-01

Pos logit contributions
ICLE+0.119
cil+0.115
lich+0.115
eting+0.113
Acknowled+0.104
Neg logit contributions
phis-0.158
eatures-0.137
 adolesc-0.134
utonium-0.132
eries-0.130
Token it
Token ID340
Feature activation+2.32e-01

Pos logit contributions
ICLE+0.246
cil+0.239
lich+0.237
eting+0.231
wic+0.212
Neg logit contributions
phis-0.420
eatures-0.373
 adolesc-0.369
utonium-0.358
inatory-0.354
Token painful
Token ID12132
Feature activation-1.82e-01

Pos logit contributions
phis+0.213
eatures+0.184
 adolesc+0.183
utonium+0.177
inatory+0.174
Neg logit contributions
ICLE-0.175
cil-0.171
lich-0.169
eting-0.166
wic-0.156
Token.
Token ID13
Feature activation-3.25e-01

Pos logit contributions
ICLE+0.101
cil+0.098
lich+0.097
eting+0.094
wic+0.085
Neg logit contributions
phis-0.202
eatures-0.180
 adolesc-0.179
utonium-0.174
inatory-0.172
Token When
Token ID1649
Feature activation+1.73e-01

Pos logit contributions
ICLE+0.197
cil+0.192
lich+0.191
eting+0.185
wic+0.169
Neg logit contributions
phis-0.345
eatures-0.306
 adolesc-0.302
utonium-0.295
inatory-0.291
Token he
Token ID339
Feature activation-1.15e+00

Pos logit contributions
phis+0.195
eatures+0.174
 adolesc+0.172
utonium+0.167
eries+0.165
Neg logit contributions
ICLE-0.095
cil-0.092
lich-0.091
eting-0.089
wic-0.080
Token finished
Token ID5201
Feature activation-1.60e+00

Pos logit contributions
ICLE+0.777
cil+0.766
lich+0.760
eting+0.747
wic+0.686
Neg logit contributions
phis-1.130
eatures-1.011
 adolesc-0.990
utonium-0.955
inatory-0.943
Token objectives
Token ID15221
Feature activation+5.90e-01

Pos logit contributions
phis+0.342
eatures+0.304
 adolesc+0.298
utonium+0.290
inatory+0.286
Neg logit contributions
ICLE-0.215
cil-0.210
lich-0.209
eting-0.204
wic-0.187
Token feeling
Token ID4203
Feature activation+1.20e+00

Pos logit contributions
phis+0.588
eatures+0.519
 adolesc+0.509
utonium+0.497
inatory+0.489
Neg logit contributions
ICLE-0.397
cil-0.387
lich-0.385
eting-0.375
wic-0.346
Token tired
Token ID10032
Feature activation-2.88e+00

Pos logit contributions
phis+1.138
eatures+1.000
 adolesc+0.983
utonium+0.951
inatory+0.941
Neg logit contributions
ICLE-0.861
cil-0.836
lich-0.834
eting-0.816
wic-0.757
Token by
Token ID416
Feature activation-5.47e-01

Pos logit contributions
ICLE+1.598
cil+1.563
lich+1.553
eting+1.523
Acknowled+1.369
Neg logit contributions
phis-3.199
eatures-2.883
 adolesc-2.823
utonium-2.767
eries-2.706
Token the
Token ID262
Feature activation+6.25e-02

Pos logit contributions
ICLE+0.375
cil+0.366
lich+0.364
eting+0.356
wic+0.329
Neg logit contributions
phis-0.539
eatures-0.476
 adolesc-0.467
utonium-0.454
inatory-0.447
Token time
Token ID640
Feature activation-4.67e-01

Pos logit contributions
phis+0.057
eatures+0.050
 adolesc+0.049
utonium+0.048
inatory+0.047
Neg logit contributions
ICLE-0.047
cil-0.046
lich-0.046
eting-0.045
wic-0.042
Token that
Token ID326
Feature activation-4.35e-01

Pos logit contributions
ICLE+0.310
cil+0.303
lich+0.301
eting+0.294
wic+0.270
Neg logit contributions
phis-0.470
eatures-0.416
 adolesc-0.408
utonium-0.398
inatory-0.391
Token you
Token ID345
Feature activation+1.02e+00

Pos logit contributions
ICLE+0.295
cil+0.289
lich+0.287
eting+0.280
wic+0.258
Neg logit contributions
phis-0.432
eatures-0.381
 adolesc-0.374
utonium-0.365
inatory-0.359
Token reach
Token ID3151
Feature activation-1.36e+00

Pos logit contributions
phis+0.831
eatures+0.710
 adolesc+0.691
utonium+0.670
inatory+0.658
Neg logit contributions
ICLE-0.883
cil-0.862
lich-0.861
eting-0.844
wic-0.794
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
ICLE+0.832
cil+0.816
lich+0.809
eting+0.792
wic+0.717
Neg logit contributions
phis-1.435
eatures-1.281
 adolesc-1.254
utonium-1.224
inatory-1.210
Token final
Token ID2457
Feature activation-9.28e-02

Pos logit contributions
ICLE+0.099
cil+0.097
lich+0.096
eting+0.095
wic+0.088
Neg logit contributions
phis-0.111
eatures-0.096
 adolesc-0.094
utonium-0.091
inatory-0.090
Token United
Token ID1578
Feature activation-1.80e+00

Pos logit contributions
phis+0.621
eatures+0.547
 adolesc+0.535
utonium+0.521
eries+0.512
Neg logit contributions
ICLE-0.457
cil-0.445
lich-0.442
eting-0.432
wic-0.401
Token are
Token ID389
Feature activation+1.60e-01

Pos logit contributions
ICLE+1.325
cil+1.301
lich+1.296
eting+1.266
wic+1.175
Neg logit contributions
phis-1.679
eatures-1.475
 adolesc-1.448
utonium-1.408
inatory-1.381
Token set
Token ID900
Feature activation-1.16e+00

Pos logit contributions
phis+0.156
eatures+0.138
 adolesc+0.135
utonium+0.131
inatory+0.129
Neg logit contributions
ICLE-0.111
cil-0.109
lich-0.108
eting-0.106
wic-0.098
Token to
Token ID284
Feature activation+9.91e-02

Pos logit contributions
ICLE+0.753
cil+0.736
lich+0.732
eting+0.717
wic+0.656
Neg logit contributions
phis-1.183
eatures-1.056
 adolesc-1.032
utonium-1.007
inatory-0.989
Token bring
Token ID2222
Feature activation-4.04e-01

Pos logit contributions
phis+0.079
eatures+0.068
 adolesc+0.067
utonium+0.064
inatory+0.063
Neg logit contributions
ICLE-0.086
cil-0.085
lich-0.084
eting-0.083
wic-0.078
Token supporters
Token ID5941
Feature activation-1.16e+00

Pos logit contributions
ICLE+0.266
cil+0.260
lich+0.258
eting+0.253
wic+0.232
Neg logit contributions
phis-0.409
eatures-0.363
 adolesc-0.357
utonium-0.347
inatory-0.342
Token back
Token ID736
Feature activation+3.40e-01

Pos logit contributions
ICLE+0.764
cil+0.745
lich+0.741
eting+0.724
wic+0.665
Neg logit contributions
phis-1.182
eatures-1.049
 adolesc-1.029
utonium-1.003
inatory-0.987
Token into
Token ID656
Feature activation-6.20e-01

Pos logit contributions
phis+0.337
eatures+0.298
 adolesc+0.292
utonium+0.285
inatory+0.280
Neg logit contributions
ICLE-0.231
cil-0.225
lich-0.224
eting-0.218
wic-0.202
Token the
Token ID262
Feature activation+2.20e-01

Pos logit contributions
ICLE+0.366
cil+0.355
lich+0.354
eting+0.344
wic+0.313
Neg logit contributions
phis-0.671
eatures-0.600
 adolesc-0.590
utonium-0.575
inatory-0.567
Token board
Token ID3096
Feature activation-1.20e+00

Pos logit contributions
phis+0.203
eatures+0.178
 adolesc+0.175
utonium+0.170
inatory+0.167
Neg logit contributions
ICLE-0.164
cil-0.160
lich-0.159
eting-0.156
wic-0.145
Tokenroom
Token ID3823
Feature activation-1.87e-01

Pos logit contributions
ICLE+0.404
cil+0.385
lich+0.379
eting+0.362
wic+0.301
Neg logit contributions
phis-1.596
eatures-1.459
 adolesc-1.438
utonium-1.412
inatory-1.397
Token from
Token ID422
Feature activation+2.78e-01

Pos logit contributions
phis+0.030
eatures+0.027
 adolesc+0.027
utonium+0.026
inatory+0.026
Neg logit contributions
ICLE-0.018
cil-0.017
lich-0.017
eting-0.017
wic-0.015
Token above
Token ID2029
Feature activation+1.81e-02

Pos logit contributions
phis+0.242
eatures+0.210
 adolesc+0.205
utonium+0.199
inatory+0.195
Neg logit contributions
ICLE-0.223
cil-0.219
lich-0.218
eting-0.214
wic-0.199
Token the
Token ID262
Feature activation+3.52e-01

Pos logit contributions
phis+0.020
eatures+0.018
 adolesc+0.018
utonium+0.017
inatory+0.017
Neg logit contributions
ICLE-0.010
cil-0.010
lich-0.010
eting-0.010
wic-0.009
Token seven
Token ID3598
Feature activation-1.61e+00

Pos logit contributions
phis+0.385
eatures+0.345
 adolesc+0.339
utonium+0.331
inatory+0.327
Neg logit contributions
ICLE-0.203
cil-0.197
lich-0.196
eting-0.191
wic-0.173
Token heavens
Token ID27636
Feature activation+6.34e-01

Pos logit contributions
ICLE+1.474
cil+1.448
lich+1.442
eting+1.419
wic+1.337
Neg logit contributions
phis-1.216
eatures-1.031
 adolesc-1.005
utonium-0.968
inatory-0.946
Token.
Token ID13
Feature activation-2.75e-01

Pos logit contributions
phis+0.720
eatures+0.646
 adolesc+0.637
utonium+0.622
inatory+0.614
Neg logit contributions
ICLE-0.340
cil-0.329
lich-0.326
eting-0.317
wic-0.285
Token
Token ID447
Feature activation+6.92e-01

Pos logit contributions
ICLE+0.179
cil+0.174
lich+0.173
eting+0.169
wic+0.155
Neg logit contributions
phis-0.280
eatures-0.248
 adolesc-0.244
utonium-0.238
inatory-0.234
Token
Token ID251
Feature activation-6.75e-01

Pos logit contributions
phis+0.623
eatures+0.543
 adolesc+0.532
utonium+0.516
eries+0.508
Neg logit contributions
ICLE-0.530
cil-0.519
lich-0.516
eting-0.508
wic-0.473
Token6
Token ID21
Feature activation-5.87e-01

Pos logit contributions
ICLE+0.441
cil+0.430
lich+0.428
eting+0.418
wic+0.384
Neg logit contributions
phis-0.686
eatures-0.609
 adolesc-0.598
utonium-0.582
inatory-0.573
Token
Token ID198
Feature activation-9.02e-01

Pos logit contributions
ICLE+0.389
cil+0.380
lich+0.378
eting+0.369
wic+0.339
Neg logit contributions
phis-0.591
eatures-0.525
 adolesc-0.515
utonium-0.501
inatory-0.493
Token
Token ID198
Feature activation-7.54e-01

Pos logit contributions
ICLE+0.610
cil+0.594
lich+0.589
eting+0.576
wic+0.532
Neg logit contributions
phis-0.895
eatures-0.775
 adolesc-0.767
utonium-0.756
eries-0.747
Token adding
Token ID4375
Feature activation-1.57e+00

Pos logit contributions
ICLE+0.388
cil+0.376
lich+0.374
eting+0.365
wic+0.329
Neg logit contributions
phis-0.750
eatures-0.673
 adolesc-0.661
utonium-0.645
inatory-0.635
Token that
Token ID326
Feature activation-1.78e+00

Pos logit contributions
ICLE+0.899
cil+0.874
lich+0.869
eting+0.846
wic+0.765
Neg logit contributions
phis-1.732
eatures-1.553
 adolesc-1.526
utonium-1.491
inatory-1.469
Token she
Token ID673
Feature activation-4.87e-01

Pos logit contributions
ICLE+1.025
cil+0.996
lich+0.990
eting+0.964
wic+0.873
Neg logit contributions
phis-1.945
eatures-1.742
 adolesc-1.712
utonium-1.672
inatory-1.647
Token is
Token ID318
Feature activation-5.68e-03

Pos logit contributions
ICLE+0.336
cil+0.328
lich+0.326
eting+0.319
wic+0.294
Neg logit contributions
phis-0.478
eatures-0.422
 adolesc-0.414
utonium-0.403
inatory-0.396
Token
Token ID564
Feature activation-6.34e-01

Pos logit contributions
ICLE+0.004
cil+0.004
lich+0.004
eting+0.004
wic+0.003
Neg logit contributions
phis-0.006
eatures-0.005
 adolesc-0.005
utonium-0.005
inatory-0.005
Token
Token ID250
Feature activation-1.51e+00

Pos logit contributions
ICLE+0.446
cil+0.436
lich+0.434
eting+0.425
wic+0.392
Neg logit contributions
phis-0.613
eatures-0.542
 adolesc-0.531
utonium-0.516
inatory-0.507
Tokenp
Token ID79
Feature activation-4.89e-01

Pos logit contributions
ICLE+1.068
cil+1.053
lich+1.048
eting+1.026
wic+0.946
Neg logit contributions
phis-1.449
eatures-1.284
 adolesc-1.263
utonium-1.219
inatory-1.197
Tokenroud
Token ID5493
Feature activation-8.78e-01

Pos logit contributions
ICLE+0.419
cil+0.410
lich+0.408
eting+0.400
wic+0.376
Neg logit contributions
phis-0.400
eatures-0.343
 adolesc-0.335
utonium-0.325
inatory-0.318
Token of
Token ID286
Feature activation-1.03e+00

Pos logit contributions
ICLE+0.543
cil+0.529
lich+0.526
eting+0.513
wic+0.468
Neg logit contributions
phis-0.924
eatures-0.824
 adolesc-0.810
utonium-0.789
inatory-0.777
Token our
Token ID674
Feature activation-4.14e-01

Pos logit contributions
ICLE+0.629
cil+0.611
lich+0.608
eting+0.594
wic+0.541
Neg logit contributions
phis-1.099
eatures-0.983
 adolesc-0.966
utonium-0.943
inatory-0.926
Token work
Token ID670
Feature activation-1.69e+00

Pos logit contributions
ICLE+0.291
cil+0.284
lich+0.282
eting+0.277
wic+0.256
Neg logit contributions
phis-0.400
eatures-0.353
 adolesc-0.346
utonium-0.337
eries-0.330
Tokenthe
Token ID1169
Feature activation-5.14e-01

Pos logit contributions
ICLE+0.966
cil+0.940
lich+0.933
eting+0.912
Acknowled+0.836
Neg logit contributions
phis-1.583
eatures-1.414
 adolesc-1.388
utonium-1.351
inatory-1.327
Token First
Token ID3274
Feature activation-4.29e-01

Pos logit contributions
ICLE+0.377
cil+0.369
lich+0.367
eting+0.359
wic+0.333
Neg logit contributions
phis-0.481
eatures-0.423
 adolesc-0.414
utonium-0.402
inatory-0.395
Tokens
Token ID82
Feature activation-2.41e-01

Pos logit contributions
ICLE+0.312
cil+0.305
lich+0.303
eting+0.297
wic+0.275
Neg logit contributions
phis-0.406
eatures-0.357
 adolesc-0.349
utonium-0.339
inatory-0.333
Token Cors
Token ID26978
Feature activation-5.24e-01

Pos logit contributions
ICLE+0.165
cil+0.161
lich+0.160
eting+0.156
wic+0.144
Neg logit contributions
phis-0.238
eatures-0.210
 adolesc-0.206
utonium-0.201
inatory-0.197
Tokenairs
Token ID3468
Feature activation+1.55e+00

Pos logit contributions
ICLE+0.413
cil+0.405
lich+0.403
eting+0.396
wic+0.369
Neg logit contributions
phis-0.462
eatures-0.403
 adolesc-0.396
utonium-0.382
inatory-0.375
Token are
Token ID389
Feature activation-4.68e-01

Pos logit contributions
phis+1.542
eatures+1.354
 adolesc+1.329
utonium+1.296
eries+1.284
Neg logit contributions
ICLE-1.043
lich-1.014
cil-1.013
eting-0.983
Acknowled-0.908
Token the
Token ID262
Feature activation-3.67e-01

Pos logit contributions
ICLE+0.324
cil+0.316
lich+0.315
eting+0.308
wic+0.284
Neg logit contributions
phis-0.458
eatures-0.405
 adolesc-0.397
utonium-0.386
inatory-0.380
Token guardians
Token ID32769
Feature activation-1.10e+00

Pos logit contributions
ICLE+0.275
cil+0.269
lich+0.267
eting+0.262
wic+0.243
Neg logit contributions
phis-0.340
eatures-0.299
 adolesc-0.292
utonium-0.284
inatory-0.278
Token of
Token ID286
Feature activation-6.98e-01

Pos logit contributions
ICLE+0.619
cil+0.602
lich+0.598
eting+0.583
wic+0.524
Neg logit contributions
phis-1.215
eatures-1.092
 adolesc-1.074
utonium-1.048
inatory-1.032
Token values
Token ID3815
Feature activation+2.08e+00

Pos logit contributions
ICLE+0.456
cil+0.445
lich+0.442
eting+0.433
wic+0.397
Neg logit contributions
phis-0.709
eatures-0.630
 adolesc-0.618
utonium-0.602
inatory-0.593
Token and
Token ID290
Feature activation+4.95e-01

Pos logit contributions
phis+2.263
eatures+2.007
 adolesc+1.985
utonium+1.944
eries+1.916
Neg logit contributions
ICLE-1.197
lich-1.159
cil-1.159
eting-1.115
Acknowled-1.017
Token 1
Token ID352
Feature activation-5.04e-01

Pos logit contributions
phis+0.293
eatures+0.257
 adolesc+0.253
utonium+0.245
inatory+0.241
Neg logit contributions
ICLE-0.225
cil-0.220
lich-0.219
eting-0.214
Acknowled-0.199
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
ICLE+0.238
cil+0.229
lich+0.224
eting+0.218
wic+0.195
Neg logit contributions
phis-0.601
 adolesc-0.526
eatures-0.525
utonium-0.522
eries-0.519
Token425
Token ID32114
Feature activation-9.03e-01

Pos logit contributions
phis+0.189
eatures+0.168
 adolesc+0.165
utonium+0.161
inatory+0.159
Neg logit contributions
ICLE-0.106
cil-0.103
lich-0.102
eting-0.100
wic-0.091
Token voters
Token ID4446
Feature activation+1.42e+00

Pos logit contributions
ICLE+0.569
cil+0.554
lich+0.551
eting+0.538
wic+0.492
Neg logit contributions
phis-0.940
eatures-0.837
 adolesc-0.822
utonium-0.801
inatory-0.789
Token in
Token ID287
Feature activation+1.39e-01

Pos logit contributions
phis+1.434
eatures+1.239
 adolesc+1.232
utonium+1.214
eries+1.205
Neg logit contributions
ICLE-0.933
lich-0.891
cil-0.889
eting-0.859
Acknowled-0.801
Token Wisconsin
Token ID9279
Feature activation-3.11e+00

Pos logit contributions
phis+0.151
eatures+0.135
 adolesc+0.134
utonium+0.130
inatory+0.128
Neg logit contributions
ICLE-0.081
cil-0.078
lich-0.078
eting-0.075
Acknowled-0.069
Token.
Token ID13
Feature activation+1.94e-01

Pos logit contributions
ICLE+1.571
cil+1.540
lich+1.524
eting+1.487
wic+1.320
Neg logit contributions
phis-3.597
eatures-3.264
 adolesc-3.190
utonium-3.128
inatory-3.089
Token<|endoftext|>
Token ID50256
Feature activation-2.74e-01

Pos logit contributions
phis+0.186
eatures+0.162
 adolesc+0.159
utonium+0.157
eries+0.155
Neg logit contributions
ICLE-0.137
lich-0.132
cil-0.132
eting-0.129
entimes-0.119
TokenJohn
Token ID7554
Feature activation-3.10e-01

Pos logit contributions
ICLE+0.182
cil+0.177
lich+0.176
eting+0.172
wic+0.158
Neg logit contributions
phis-0.276
eatures-0.243
 adolesc-0.239
utonium-0.233
inatory-0.230
Token Sm
Token ID2439
Feature activation+8.52e-01

Pos logit contributions
ICLE+0.218
cil+0.213
lich+0.212
eting+0.208
wic+0.192
Neg logit contributions
phis-0.300
eatures-0.265
 adolesc-0.260
utonium-0.253
inatory-0.248
Tokenid
Token ID312
Feature activation-3.92e-01

Pos logit contributions
phis+0.772
eatures+0.667
utonium+0.645
eries+0.634
 adolesc+0.630
Neg logit contributions
ICLE-0.660
cil-0.628
lich-0.627
eting-0.614
Acknowled-0.591
Token hold
Token ID1745
Feature activation-1.94e+00

Pos logit contributions
phis+0.532
eatures+0.460
 adolesc+0.449
utonium+0.434
inatory+0.423
Neg logit contributions
ICLE-0.555
cil-0.546
lich-0.543
eting-0.534
wic-0.500
Token on
Token ID319
Feature activation-8.27e-01

Pos logit contributions
ICLE+1.241
cil+1.227
lich+1.214
eting+1.188
Acknowled+1.078
Neg logit contributions
phis-1.985
eatures-1.777
 adolesc-1.731
utonium-1.700
inatory-1.660
Token until
Token ID1566
Feature activation-1.77e+00

Pos logit contributions
ICLE+0.529
cil+0.517
lich+0.514
eting+0.502
wic+0.458
Neg logit contributions
phis-0.851
eatures-0.759
 adolesc-0.743
utonium-0.726
inatory-0.713
Token this
Token ID428
Feature activation+3.54e-01

Pos logit contributions
ICLE+1.171
cil+1.147
lich+1.140
eting+1.114
Acknowled+1.017
Neg logit contributions
phis-1.782
eatures-1.583
 adolesc-1.548
utonium-1.512
inatory-1.485
Token whole
Token ID2187
Feature activation-6.53e-01

Pos logit contributions
phis+0.305
eatures+0.266
 adolesc+0.258
utonium+0.251
eries+0.244
Neg logit contributions
ICLE-0.286
cil-0.281
lich-0.280
eting-0.275
Acknowled-0.256
Token Trump
Token ID1301
Feature activation-3.55e+00

Pos logit contributions
ICLE+0.505
cil+0.495
lich+0.493
eting+0.485
wic+0.449
Neg logit contributions
phis-0.586
eatures-0.513
 adolesc-0.500
utonium-0.487
inatory-0.475
Token thing
Token ID1517
Feature activation-6.46e-01

Pos logit contributions
ICLE+2.763
cil+2.715
lich+2.713
eting+2.703
wic+2.478
Neg logit contributions
phis-3.134
eatures-2.780
 adolesc-2.677
utonium-2.587
inatory-2.501
Token blows
Token ID20385
Feature activation+2.50e+00

Pos logit contributions
ICLE+0.511
cil+0.502
lich+0.499
eting+0.492
wic+0.458
Neg logit contributions
phis-0.569
eatures-0.496
 adolesc-0.485
utonium-0.467
inatory-0.459
Token over
Token ID625
Feature activation-2.19e-01

Pos logit contributions
phis+2.541
eatures+2.230
 adolesc+2.211
utonium+2.149
eries+2.133
Neg logit contributions
ICLE-1.624
cil-1.576
lich-1.573
eting-1.512
wic-1.409
Token.
Token ID13
Feature activation+1.69e-01

Pos logit contributions
ICLE+0.117
cil+0.114
lich+0.113
eting+0.110
wic+0.098
Neg logit contributions
phis-0.249
eatures-0.224
 adolesc-0.220
utonium-0.215
inatory-0.212
Token
Token ID198
Feature activation-4.73e-01

Pos logit contributions
phis+0.174
eatures+0.154
 adolesc+0.152
utonium+0.148
inatory+0.146
Neg logit contributions
ICLE-0.108
cil-0.106
lich-0.105
eting-0.103
wic-0.094
TokenYet
Token ID11486
Feature activation-7.55e-01

Pos logit contributions
ICLE+0.388
cil+0.379
lich+0.377
eting+0.368
wic+0.338
Neg logit contributions
phis-0.590
eatures-0.523
 adolesc-0.513
utonium-0.500
inatory-0.492
Token even
Token ID772
Feature activation-2.71e-01

Pos logit contributions
ICLE+0.476
cil+0.463
lich+0.460
eting+0.448
wic+0.410
Neg logit contributions
phis-0.787
eatures-0.700
 adolesc-0.688
utonium-0.670
inatory-0.660
Token these
Token ID777
Feature activation-1.24e-01

Pos logit contributions
ICLE+0.160
cil+0.155
lich+0.154
eting+0.150
wic+0.137
Neg logit contributions
phis-0.293
eatures-0.263
 adolesc-0.258
utonium-0.252
inatory-0.248
Token monuments
Token ID28814
Feature activation-2.13e+00

Pos logit contributions
ICLE+0.089
cil+0.087
lich+0.087
eting+0.085
wic+0.079
Neg logit contributions
phis-0.119
eatures-0.104
 adolesc-0.102
utonium-0.099
inatory-0.098
Token can
Token ID460
Feature activation+1.00e+00

Pos logit contributions
ICLE+1.498
cil+1.471
lich+1.458
eting+1.438
wic+1.319
Neg logit contributions
phis-2.058
eatures-1.819
 adolesc-1.797
utonium-1.734
inatory-1.700
Token reinforce
Token ID19594
Feature activation-3.69e+00

Pos logit contributions
phis+0.841
eatures+0.724
 adolesc+0.705
utonium+0.685
inatory+0.673
Neg logit contributions
ICLE-0.838
cil-0.818
lich-0.816
eting-0.800
wic-0.750
Token myths
Token ID22886
Feature activation-8.15e-01

Pos logit contributions
ICLE+2.368
cil+2.315
lich+2.301
eting+2.257
Acknowled+2.049
Neg logit contributions
phis-3.782
eatures-3.364
 adolesc-3.286
utonium-3.225
inatory-3.152
Token about
Token ID546
Feature activation-1.09e+00

Pos logit contributions
ICLE+0.454
cil+0.439
lich+0.437
eting+0.423
wic+0.383
Neg logit contributions
phis-0.909
eatures-0.813
 adolesc-0.802
utonium-0.783
inatory-0.773
Token slavery
Token ID13503
Feature activation-1.57e+00

Pos logit contributions
ICLE+0.718
cil+0.703
lich+0.699
eting+0.686
wic+0.626
Neg logit contributions
phis-1.090
eatures-0.970
 adolesc-0.945
utonium-0.927
inatory-0.908
Token.
Token ID13
Feature activation-9.22e-01

Pos logit contributions
ICLE+0.849
cil+0.824
lich+0.819
eting+0.797
wic+0.716
Neg logit contributions
phis-1.777
eatures-1.600
 adolesc-1.572
utonium-1.536
inatory-1.514
Token The
Token ID383
Feature activation-7.45e-01

Pos logit contributions
ICLE+0.615
cil+0.600
lich+0.597
eting+0.584
wic+0.537
Neg logit contributions
phis-0.927
eatures-0.822
 adolesc-0.806
utonium-0.785
inatory-0.772
Token)
Token ID8
Feature activation-5.12e-01

Pos logit contributions
ICLE+0.741
cil+0.724
lich+0.721
eting+0.701
wic+0.642
Neg logit contributions
phis-1.204
eatures-1.078
 adolesc-1.057
utonium-1.026
inatory-1.010
Token
Token ID198
Feature activation-9.02e-01

Pos logit contributions
ICLE+0.320
cil+0.312
lich+0.310
eting+0.302
wic+0.276
Neg logit contributions
phis-0.537
eatures-0.479
 adolesc-0.469
utonium-0.457
inatory-0.450
Token
Token ID198
Feature activation-7.62e-01

Pos logit contributions
ICLE+0.614
cil+0.596
lich+0.592
eting+0.577
wic+0.535
Neg logit contributions
phis-0.891
eatures-0.767
 adolesc-0.761
utonium-0.751
eries-0.743
Token20
Token ID1238
Feature activation+6.30e-01

Pos logit contributions
ICLE+0.359
cil+0.345
lich+0.342
eting+0.332
wic+0.294
Neg logit contributions
phis-0.913
eatures-0.825
 adolesc-0.814
utonium-0.796
inatory-0.787
Token.
Token ID13
Feature activation-1.17e-01

Pos logit contributions
phis+0.693
 adolesc+0.599
eatures+0.598
utonium+0.595
eries+0.593
Neg logit contributions
ICLE-0.353
cil-0.340
lich-0.336
eting-0.327
wic-0.299
Token Chris
Token ID5180
Feature activation-3.67e+00

Pos logit contributions
ICLE+0.082
cil+0.080
lich+0.080
eting+0.078
wic+0.072
Neg logit contributions
phis-0.114
eatures-0.101
 adolesc-0.098
utonium-0.095
inatory-0.094
Token F
Token ID376
Feature activation+2.64e-01

Pos logit contributions
ICLE+2.533
cil+2.513
lich+2.493
eting+2.460
wic+2.257
Neg logit contributions
phis-3.561
eatures-3.199
 adolesc-3.116
utonium-3.017
inatory-2.964
Tokenus
Token ID385
Feature activation-6.48e-01

Pos logit contributions
phis+0.249
eatures+0.219
 adolesc+0.214
utonium+0.209
inatory+0.205
Neg logit contributions
ICLE-0.193
cil-0.188
lich-0.187
eting-0.183
Acknowled-0.170
Tokenaro
Token ID12022
Feature activation-1.46e+00

Pos logit contributions
ICLE+0.421
cil+0.412
lich+0.410
eting+0.400
wic+0.367
Neg logit contributions
phis-0.661
eatures-0.587
 adolesc-0.577
utonium-0.561
inatory-0.552
Token (
Token ID357
Feature activation-5.18e-01

Pos logit contributions
ICLE+0.929
cil+0.915
lich+0.911
eting+0.890
wic+0.818
Neg logit contributions
phis-1.509
eatures-1.346
 adolesc-1.315
utonium-1.283
inatory-1.265
Token117
Token ID17657
Feature activation+5.69e-03

Pos logit contributions
ICLE+0.291
cil+0.282
lich+0.280
eting+0.273
wic+0.246
Neg logit contributions
phis-0.574
eatures-0.512
 adolesc-0.504
utonium-0.494
inatory-0.487
Token of
Token ID286
Feature activation-1.24e+00

Pos logit contributions
ICLE+0.817
cil+0.795
lich+0.791
eting+0.769
wic+0.699
Neg logit contributions
phis-1.503
eatures-1.344
 adolesc-1.319
utonium-1.291
inatory-1.268
Token people
Token ID661
Feature activation+6.86e-01

Pos logit contributions
ICLE+0.885
cil+0.867
lich+0.862
eting+0.844
wic+0.780
Neg logit contributions
phis-1.181
eatures-1.041
 adolesc-1.018
utonium-0.991
inatory-0.973
Token who
Token ID508
Feature activation+3.61e-02

Pos logit contributions
phis+0.711
eatures+0.628
 adolesc+0.620
utonium+0.603
eries+0.598
Neg logit contributions
ICLE-0.434
cil-0.420
lich-0.416
eting-0.406
wic-0.372
Token are
Token ID389
Feature activation-7.39e-01

Pos logit contributions
phis+0.033
eatures+0.029
 adolesc+0.028
utonium+0.028
inatory+0.027
Neg logit contributions
ICLE-0.027
cil-0.027
lich-0.026
eting-0.026
wic-0.024
Token just
Token ID655
Feature activation-3.56e-01

Pos logit contributions
ICLE+0.520
cil+0.508
lich+0.505
eting+0.495
wic+0.457
Neg logit contributions
phis-0.716
eatures-0.631
 adolesc-0.619
utonium-0.602
inatory-0.592
Token steak
Token ID26320
Feature activation-3.43e+00

Pos logit contributions
ICLE+0.247
cil+0.241
lich+0.240
eting+0.234
wic+0.217
Neg logit contributions
phis-0.347
eatures-0.306
 adolesc-0.300
utonium-0.292
inatory-0.288
Token.
Token ID13
Feature activation-6.40e-01

Pos logit contributions
ICLE+2.118
cil+2.080
lich+2.069
eting+2.024
wic+1.851
Neg logit contributions
phis-3.583
eatures-3.214
 adolesc-3.141
utonium-3.066
inatory-3.023
Token And
Token ID843
Feature activation-1.07e-01

Pos logit contributions
ICLE+0.413
cil+0.403
lich+0.400
eting+0.391
wic+0.358
Neg logit contributions
phis-0.656
eatures-0.582
 adolesc-0.571
utonium-0.557
inatory-0.548
Token,
Token ID11
Feature activation-1.56e-01

Pos logit contributions
ICLE+0.064
cil+0.062
lich+0.062
eting+0.060
Acknowled+0.055
Neg logit contributions
phis-0.114
eatures-0.101
 adolesc-0.100
utonium-0.097
eries-0.096
Token there
Token ID612
Feature activation-5.31e-01

Pos logit contributions
ICLE+0.097
cil+0.095
lich+0.094
eting+0.092
wic+0.084
Neg logit contributions
phis-0.163
eatures-0.145
 adolesc-0.142
utonium-0.139
inatory-0.137
Token
Token ID447
Feature activation-5.15e-02

Pos logit contributions
ICLE+0.364
cil+0.355
lich+0.354
eting+0.347
wic+0.319
Neg logit contributions
phis-0.522
eatures-0.462
 adolesc-0.453
utonium-0.441
inatory-0.433