TOP ACTIVATIONS
MAX = 5.014

4 , 2010 Subject : User reviews are a
is this genius Patrick O ' Brian and you 're not
13 , 2010 Subject : boys beware This film
5 , 2009 Subject : Que ers are Here
Sad r , a Shi ' ite cleric in Iraq ,
26 , 2009 Subject : THE IR ONY OF
6 , 2010 Subject : R iff Tra x
, 8 : 00 PM PDT The developer of
AB arry Maryland 1 hour ago This election was not about
witz West chester 1 hour ago Pretty simple Paul :
15 , 2010 Subject : Que er magnet ?
min iser ies since 2009 s Alice , the six
East on PA 1 hour ago I think a simple passing
9 , 2010 Subject : R ipe for M
the use of general - circ ulation models . I don
Others Marvin Wilson DT 6 ' 4 / 329 5 *
16 25 , when d ' Art agn an , rushing
annual report , Katherine d ' Ent rem ont calls for
States 6 83 Posts Last Edited : 2013 - 09 -
Our Seas Foundation 's D ' Ar ros Research Centre .

MIN ACTIVATIONS
MIN = -5.123

board ; the teen got stock options , too .
is set to 0 on stock kernel . The kernel is
! Let s try to power management .
. Let s try listening to its suggestion ,
have the Nexus 6 in Stock on Nov . 21 st
my life . I will try to start to find the
error has occurred . Please try again later . View all
the level at which Yahoo stock was trading when the bid
error has occurred . Please try again later . View all
Maybe you acted on a stock tip that was slightly too
error has occurred . Please try again later . View all
To start , I will try to use an approach similar
games , but I can try to get some recorded within
like faults , we shall try , by God 's help
, mix and run the stock t izen kernel with the
ay T ades e will try to break 2 : 00
So let s try to write something that reaches
by wealthier Canadians and the stock options available to corporate executives
shows she owns bank and stock funds worth as much as
basically ready . We will try to find bits and pieces

INTERVAL 2.480 - 5.014
CONTAINS 0.276%

At the Crescent Heights Social Justice Magnet School in Los Angeles
-- Start of read () ' s frame | size _
. J ' ai l ' hon ne ur d '
aspects . They deserve our respect and admiration . If my
( 0 , ($ i * $ FontSize * 2 +

INTERVAL -0.054 - 2.480
CONTAINS 52.739%

catastrophic . The main thing is avoid the catastrophic events .
crying alone into a pint of Ben and Jerry
for the authorities to call it a terrorist attack , for
friends to the web page where making donations is as intuitive
, people started tweeting about a Detroit Pur ge . Such

INTERVAL -2.589 - -0.054
CONTAINS 46.782%

Pan Advertisement As you might imagine ,
fuel . You will always naturally eat the lowest calories when
up stakes and start his franchise s title defense
workforce than other college - educated prime - age workers .
outcomes . Ad Policy Click here to help prevent disenfranch is

INTERVAL -5.123 - -2.589
CONTAINS 0.203%

has also upset defenders of wom ens rights in
settings to be able to post such quick times . He
plans to begin a " public dialogue " surrounding lowering nicotine
years built upon the ratio stock / ( year ly absorption
tele S UR English (@ tel es ure ng lish )
Token 4
Token ID604
Feature activation+2.11e-01

Pos logit contributions
llan+0.133
 Luthor+0.127
oid+0.121
+0.113
exclusive+0.111
Neg logit contributions
atorium-0.131
ratulations-0.123
everal-0.114
 manoeuv-0.113
Downloadha-0.112
Token,
Token ID11
Feature activation+5.08e-02

Pos logit contributions
llan+0.149
 Luthor+0.139
oid+0.135
exclusive+0.122
+0.121
Neg logit contributions
atorium-0.191
ratulations-0.180
everal-0.171
 manoeuv-0.167
Downloadha-0.165
Token 2010
Token ID3050
Feature activation+1.73e+00

Pos logit contributions
llan+0.043
 Luthor+0.041
oid+0.039
+0.037
exclusive+0.037
Neg logit contributions
atorium-0.038
ratulations-0.034
 manoeuv-0.033
Downloadha-0.031
everal-0.031
Token
Token ID198
Feature activation+1.29e+00

Pos logit contributions
llan+1.187
 Luthor+1.109
oid+1.073
exclusive+0.970
+0.961
Neg logit contributions
atorium-1.579
ratulations-1.503
everal-1.456
acebook-1.388
 manoeuv-1.385
Token
Token ID198
Feature activation+1.18e+00

Pos logit contributions
llan+0.887
 Luthor+0.827
oid+0.806
exclusive+0.724
+0.713
Neg logit contributions
atorium-1.181
ratulations-1.131
everal-1.100
acebook-1.046
 manoeuv-1.039
TokenSubject
Token ID19776
Feature activation+5.01e+00

Pos logit contributions
llan+0.671
 Luthor+0.620
oid+0.607
exclusive+0.538
+0.531
Neg logit contributions
atorium-1.216
ratulations-1.154
 manoeuv-1.100
everal-1.085
 scrape-1.066
Token:
Token ID25
Feature activation+1.55e+00

Pos logit contributions
llan+2.930
oid+2.713
 Luthor+2.663
exclusive+2.320
+2.254
Neg logit contributions
everal-4.996
atorium-4.983
ratulations-4.936
acebook-4.626
Downloadha-4.566
Token User
Token ID11787
Feature activation+1.05e+00

Pos logit contributions
llan+1.128
 Luthor+1.078
oid+1.036
+0.958
exclusive+0.954
Neg logit contributions
atorium-1.327
ratulations-1.207
 manoeuv-1.158
Downloadha-1.125
brance-1.094
Token reviews
Token ID8088
Feature activation+1.19e+00

Pos logit contributions
llan+0.769
 Luthor+0.732
oid+0.706
+0.653
exclusive+0.649
Neg logit contributions
atorium-0.900
ratulations-0.820
 manoeuv-0.787
Downloadha-0.761
 scrape-0.749
Token are
Token ID389
Feature activation+2.27e-02

Pos logit contributions
llan+0.839
 Luthor+0.803
oid+0.772
+0.711
exclusive+0.704
Neg logit contributions
atorium-1.045
ratulations-0.953
 manoeuv-0.913
Downloadha-0.886
brance-0.867
Token a
Token ID257
Feature activation+6.58e-01

Pos logit contributions
llan+0.017
 Luthor+0.016
oid+0.015
+0.014
exclusive+0.014
Neg logit contributions
atorium-0.019
ratulations-0.018
 manoeuv-0.017
Downloadha-0.016
 scrape-0.016
Token is
Token ID318
Feature activation+3.42e-01

Pos logit contributions
atorium+0.174
ratulations+0.158
 manoeuv+0.152
Downloadha+0.147
 scrape+0.145
Neg logit contributions
llan-0.143
 Luthor-0.136
oid-0.130
-0.120
exclusive-0.118
Token this
Token ID428
Feature activation+1.49e-01

Pos logit contributions
llan+0.276
 Luthor+0.266
oid+0.253
+0.237
exclusive+0.234
Neg logit contributions
atorium-0.269
ratulations-0.242
 manoeuv-0.231
Downloadha-0.223
 scrape-0.220
Token genius
Token ID15632
Feature activation+7.88e-01

Pos logit contributions
llan+0.116
 Luthor+0.111
oid+0.106
+0.099
exclusive+0.098
Neg logit contributions
atorium-0.122
ratulations-0.110
 manoeuv-0.105
Downloadha-0.102
 scrape-0.100
Token Patrick
Token ID9925
Feature activation-1.58e+00

Pos logit contributions
llan+0.593
 Luthor+0.566
oid+0.540
+0.504
exclusive+0.495
Neg logit contributions
atorium-0.665
ratulations-0.605
 manoeuv-0.575
Downloadha-0.559
 scrape-0.551
Token O
Token ID440
Feature activation+1.66e+00

Pos logit contributions
atorium+1.338
ratulations+1.215
 manoeuv+1.167
 scrape+1.116
Downloadha+1.113
Neg logit contributions
llan-1.181
 Luthor-1.118
oid-1.071
-1.008
exclusive-0.997
Token'
Token ID6
Feature activation+5.01e+00

Pos logit contributions
llan+1.316
 Luthor+1.240
oid+1.193
+1.129
exclusive+1.102
Neg logit contributions
atorium-1.335
ratulations-1.211
 manoeuv-1.151
Downloadha-1.115
 scrape-1.101
TokenBrian
Token ID24761
Feature activation+1.86e-01

Pos logit contributions
llan+3.644
 Luthor+3.427
oid+3.282
+3.121
exclusive+3.023
Neg logit contributions
atorium-4.280
ratulations-3.870
 manoeuv-3.697
Downloadha-3.589
 scrape-3.550
Token and
Token ID290
Feature activation-2.59e-01

Pos logit contributions
llan+0.140
 Luthor+0.134
oid+0.128
+0.119
exclusive+0.117
Neg logit contributions
atorium-0.157
ratulations-0.142
 manoeuv-0.136
Downloadha-0.131
 scrape-0.130
Token you
Token ID345
Feature activation+4.25e-01

Pos logit contributions
atorium+0.207
ratulations+0.187
 manoeuv+0.178
Downloadha+0.172
 scrape+0.170
Neg logit contributions
llan-0.206
 Luthor-0.198
oid-0.189
-0.177
exclusive-0.175
Token're
Token ID821
Feature activation+9.74e-01

Pos logit contributions
llan+0.322
 Luthor+0.308
oid+0.294
+0.270
exclusive+0.269
Neg logit contributions
atorium-0.360
ratulations-0.325
 manoeuv-0.306
Downloadha-0.303
acebook-0.295
Token not
Token ID407
Feature activation+4.91e-02

Pos logit contributions
llan+0.771
 Luthor+0.758
oid+0.714
+0.658
exclusive+0.656
Neg logit contributions
atorium-0.778
ratulations-0.701
Downloadha-0.658
 manoeuv-0.653
acebook-0.636
Token 13
Token ID1511
Feature activation-2.21e-01

Pos logit contributions
atorium+0.389
ratulations+0.361
 manoeuv+0.335
everal+0.331
Downloadha+0.328
Neg logit contributions
llan-0.400
 Luthor-0.383
oid-0.368
-0.341
exclusive-0.337
Token,
Token ID11
Feature activation-1.74e-01

Pos logit contributions
atorium+0.194
ratulations+0.178
 manoeuv+0.169
Downloadha+0.164
everal+0.163
Neg logit contributions
llan-0.161
 Luthor-0.152
oid-0.146
-0.135
exclusive-0.134
Token 2010
Token ID3050
Feature activation+1.15e+00

Pos logit contributions
atorium+0.134
ratulations+0.120
 manoeuv+0.115
Downloadha+0.110
 scrape+0.109
Neg logit contributions
llan-0.143
 Luthor-0.137
oid-0.132
-0.124
exclusive-0.123
Token
Token ID198
Feature activation+1.39e+00

Pos logit contributions
llan+0.815
 Luthor+0.769
oid+0.738
exclusive+0.673
+0.673
Neg logit contributions
atorium-1.024
ratulations-0.966
everal-0.914
 manoeuv-0.899
Downloadha-0.889
Token
Token ID198
Feature activation+1.15e+00

Pos logit contributions
llan+0.945
 Luthor+0.883
oid+0.861
exclusive+0.773
+0.758
Neg logit contributions
atorium-1.282
ratulations-1.230
everal-1.201
acebook-1.142
 manoeuv-1.130
TokenSubject
Token ID19776
Feature activation+5.00e+00

Pos logit contributions
llan+0.663
 Luthor+0.618
oid+0.591
exclusive+0.532
+0.530
Neg logit contributions
atorium-1.165
ratulations-1.086
 manoeuv-1.047
 scrape-1.009
Downloadha-1.004
Token:
Token ID25
Feature activation+1.28e+00

Pos logit contributions
llan+2.905
oid+2.678
 Luthor+2.656
exclusive+2.296
 Negative+2.244
Neg logit contributions
atorium-4.998
ratulations-4.901
everal-4.896
acebook-4.589
Downloadha-4.520
Token boys
Token ID6510
Feature activation+1.56e-01

Pos logit contributions
llan+0.934
 Luthor+0.893
oid+0.853
+0.790
exclusive+0.786
Neg logit contributions
atorium-1.102
ratulations-1.004
 manoeuv-0.963
Downloadha-0.937
 scrape-0.912
Token beware
Token ID40600
Feature activation-4.16e-01

Pos logit contributions
llan+0.118
 Luthor+0.112
oid+0.108
+0.100
exclusive+0.100
Neg logit contributions
atorium-0.132
ratulations-0.119
 manoeuv-0.114
Downloadha-0.110
 scrape-0.109
Token This
Token ID770
Feature activation+4.60e-01

Pos logit contributions
atorium+0.358
ratulations+0.326
 manoeuv+0.312
Downloadha+0.300
 scrape+0.298
Neg logit contributions
llan-0.305
 Luthor-0.291
oid-0.278
-0.259
exclusive-0.255
Token film
Token ID2646
Feature activation-5.97e-01

Pos logit contributions
llan+0.338
 Luthor+0.322
oid+0.309
+0.286
exclusive+0.283
Neg logit contributions
atorium-0.394
ratulations-0.361
 manoeuv-0.344
Downloadha-0.334
 scrape-0.328
Token 5
Token ID642
Feature activation-3.91e-01

Pos logit contributions
atorium+0.186
ratulations+0.173
 manoeuv+0.159
everal+0.159
Downloadha+0.157
Neg logit contributions
llan-0.190
 Luthor-0.182
oid-0.175
-0.163
exclusive-0.161
Token,
Token ID11
Feature activation-8.58e-02

Pos logit contributions
atorium+0.350
ratulations+0.328
everal+0.308
 manoeuv+0.307
Downloadha+0.301
Neg logit contributions
llan-0.277
 Luthor-0.261
oid-0.252
-0.229
exclusive-0.228
Token 2009
Token ID3717
Feature activation+1.32e+00

Pos logit contributions
atorium+0.053
ratulations+0.047
 manoeuv+0.044
 scrape+0.043
acebook+0.042
Neg logit contributions
llan-0.085
 Luthor-0.080
oid-0.076
-0.074
exclusive-0.072
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
llan+0.913
 Luthor+0.858
oid+0.828
exclusive+0.749
+0.745
Neg logit contributions
atorium-1.194
ratulations-1.134
everal-1.092
 manoeuv-1.047
acebook-1.046
Token
Token ID198
Feature activation+1.18e+00

Pos logit contributions
llan+0.892
 Luthor+0.831
oid+0.810
exclusive+0.728
+0.718
Neg logit contributions
atorium-1.186
ratulations-1.135
everal-1.103
acebook-1.050
 manoeuv-1.044
TokenSubject
Token ID19776
Feature activation+4.98e+00

Pos logit contributions
llan+0.669
 Luthor+0.621
oid+0.606
exclusive+0.538
+0.532
Neg logit contributions
atorium-1.213
ratulations-1.151
 manoeuv-1.097
everal-1.080
 scrape-1.063
Token:
Token ID25
Feature activation+1.40e+00

Pos logit contributions
llan+2.916
oid+2.702
 Luthor+2.652
exclusive+2.307
+2.247
Neg logit contributions
everal-4.960
atorium-4.936
ratulations-4.898
acebook-4.593
Downloadha-4.528
Token Que
Token ID4670
Feature activation+1.29e-01

Pos logit contributions
llan+1.018
 Luthor+0.973
oid+0.934
+0.864
exclusive+0.859
Neg logit contributions
atorium-1.207
ratulations-1.098
 manoeuv-1.053
Downloadha-1.023
brance-0.996
Tokeners
Token ID364
Feature activation+3.38e-01

Pos logit contributions
llan+0.105
 Luthor+0.101
oid+0.096
+0.092
exclusive+0.090
Neg logit contributions
atorium-0.101
ratulations-0.090
 manoeuv-0.086
 scrape-0.082
Downloadha-0.080
Token are
Token ID389
Feature activation-2.40e-01

Pos logit contributions
llan+0.248
 Luthor+0.236
oid+0.227
+0.211
exclusive+0.208
Neg logit contributions
atorium-0.291
ratulations-0.266
 manoeuv-0.254
Downloadha-0.245
 scrape-0.241
Token Here
Token ID3423
Feature activation-3.21e-01

Pos logit contributions
atorium+0.206
ratulations+0.187
 manoeuv+0.178
Downloadha+0.171
 scrape+0.170
Neg logit contributions
llan-0.178
 Luthor-0.171
oid-0.163
-0.151
exclusive-0.150
TokenSad
Token ID26699
Feature activation+5.79e-01

Pos logit contributions
atorium+0.801
ratulations+0.723
 manoeuv+0.684
Downloadha+0.654
 scrape+0.652
Neg logit contributions
llan-0.909
 Luthor-0.865
oid-0.836
-0.786
exclusive-0.779
Tokenr
Token ID81
Feature activation+7.10e-01

Pos logit contributions
llan+0.297
 Luthor+0.266
oid+0.260
exclusive+0.224
essim+0.220
Neg logit contributions
atorium-0.620
ratulations-0.583
 manoeuv-0.563
acebook-0.550
Downloadha-0.547
Token,
Token ID11
Feature activation-2.69e-01

Pos logit contributions
llan+0.522
 Luthor+0.494
oid+0.474
+0.443
exclusive+0.436
Neg logit contributions
atorium-0.610
ratulations-0.557
 manoeuv-0.529
Downloadha-0.512
 scrape-0.509
Token a
Token ID257
Feature activation-1.07e-01

Pos logit contributions
atorium+0.224
ratulations+0.203
 manoeuv+0.193
Downloadha+0.186
 scrape+0.185
Neg logit contributions
llan-0.207
 Luthor-0.196
oid-0.188
-0.176
exclusive-0.174
Token Shi
Token ID16380
Feature activation+6.36e-01

Pos logit contributions
atorium+0.096
ratulations+0.089
 manoeuv+0.084
Downloadha+0.082
 scrape+0.081
Neg logit contributions
llan-0.074
 Luthor-0.070
oid-0.067
-0.062
exclusive-0.061
Token'
Token ID6
Feature activation+4.95e+00

Pos logit contributions
llan+0.490
 Luthor+0.459
oid+0.453
exclusive+0.415
+0.415
Neg logit contributions
atorium-0.519
ratulations-0.476
 manoeuv-0.449
Downloadha-0.441
 scrape-0.435
Tokenite
Token ID578
Feature activation-1.69e-01

Pos logit contributions
llan+3.709
oid+3.466
 Luthor+3.443
exclusive+3.155
+3.143
Neg logit contributions
atorium-4.111
ratulations-3.841
 manoeuv-3.549
Downloadha-3.495
 scrape-3.402
Token cleric
Token ID33824
Feature activation+1.55e+00

Pos logit contributions
atorium+0.142
ratulations+0.129
 manoeuv+0.122
Downloadha+0.118
 scrape+0.117
Neg logit contributions
llan-0.129
 Luthor-0.122
oid-0.117
-0.109
exclusive-0.108
Token in
Token ID287
Feature activation+9.01e-01

Pos logit contributions
llan+1.154
 Luthor+1.093
oid+1.058
+0.971
exclusive+0.962
Neg logit contributions
atorium-1.320
ratulations-1.204
 manoeuv-1.136
Downloadha-1.106
 scrape-1.100
Token Iraq
Token ID3908
Feature activation+1.28e+00

Pos logit contributions
llan+0.653
 Luthor+0.620
oid+0.594
+0.549
exclusive+0.545
Neg logit contributions
atorium-0.787
ratulations-0.720
 manoeuv-0.680
Downloadha-0.661
 scrape-0.654
Token,
Token ID11
Feature activation+1.88e-01

Pos logit contributions
llan+0.963
 Luthor+0.914
oid+0.882
+0.819
exclusive+0.809
Neg logit contributions
atorium-1.090
ratulations-0.992
 manoeuv-0.939
Downloadha-0.908
 scrape-0.904
Token 26
Token ID2608
Feature activation+5.22e-01

Pos logit contributions
atorium+0.409
ratulations+0.381
 manoeuv+0.352
everal+0.351
Downloadha+0.346
Neg logit contributions
llan-0.429
 Luthor-0.410
oid-0.394
-0.365
exclusive-0.363
Token,
Token ID11
Feature activation+2.95e-01

Pos logit contributions
llan+0.365
 Luthor+0.342
oid+0.330
exclusive+0.298
+0.298
Neg logit contributions
atorium-0.473
ratulations-0.447
everal-0.424
 manoeuv-0.415
acebook-0.409
Token 2009
Token ID3717
Feature activation+1.77e+00

Pos logit contributions
llan+0.285
 Luthor+0.269
oid+0.258
+0.245
exclusive+0.244
Neg logit contributions
atorium-0.190
ratulations-0.168
 manoeuv-0.157
 scrape-0.151
brance-0.148
Token
Token ID198
Feature activation+1.18e+00

Pos logit contributions
llan+1.210
 Luthor+1.131
oid+1.096
exclusive+0.988
+0.977
Neg logit contributions
atorium-1.615
ratulations-1.541
everal-1.496
acebook-1.428
 manoeuv-1.419
Token
Token ID198
Feature activation+1.01e+00

Pos logit contributions
llan+0.810
 Luthor+0.755
oid+0.735
exclusive+0.661
+0.653
Neg logit contributions
atorium-1.075
ratulations-1.030
everal-0.999
acebook-0.952
 manoeuv-0.948
TokenSubject
Token ID19776
Feature activation+4.86e+00

Pos logit contributions
llan+0.567
 Luthor+0.524
oid+0.513
exclusive+0.454
+0.449
Neg logit contributions
atorium-1.040
ratulations-0.990
 manoeuv-0.943
everal-0.932
 scrape-0.913
Token:
Token ID25
Feature activation+1.20e+00

Pos logit contributions
llan+2.855
oid+2.649
 Luthor+2.613
exclusive+2.269
+2.222
Neg logit contributions
everal-4.810
atorium-4.794
ratulations-4.776
acebook-4.472
Downloadha-4.404
Token THE
Token ID3336
Feature activation+4.44e-02

Pos logit contributions
llan+0.867
 Luthor+0.827
oid+0.796
+0.735
exclusive+0.732
Neg logit contributions
atorium-1.031
ratulations-0.939
 manoeuv-0.900
Downloadha-0.874
 scrape-0.852
Token IR
Token ID14826
Feature activation+5.32e-01

Pos logit contributions
llan+0.036
 Luthor+0.034
oid+0.033
+0.031
exclusive+0.030
Neg logit contributions
atorium-0.035
ratulations-0.032
 manoeuv-0.030
Downloadha-0.029
 scrape-0.029
TokenONY
Token ID40508
Feature activation-1.43e+00

Pos logit contributions
llan+0.409
 Luthor+0.389
oid+0.373
+0.348
exclusive+0.347
Neg logit contributions
atorium-0.438
ratulations-0.398
 manoeuv-0.381
Downloadha-0.366
 scrape-0.365
Token OF
Token ID3963
Feature activation-2.08e+00

Pos logit contributions
atorium+1.170
ratulations+1.060
 manoeuv+1.014
Downloadha+0.971
 scrape+0.968
Neg logit contributions
llan-1.105
 Luthor-1.052
oid-1.007
-0.947
exclusive-0.934
Token 6
Token ID718
Feature activation-7.99e-02

Pos logit contributions
atorium+0.483
ratulations+0.450
 manoeuv+0.416
everal+0.415
Downloadha+0.408
Neg logit contributions
llan-0.500
 Luthor-0.478
oid-0.458
-0.424
exclusive-0.422
Token,
Token ID11
Feature activation+3.12e-01

Pos logit contributions
atorium+0.072
ratulations+0.067
everal+0.063
 manoeuv+0.063
Downloadha+0.061
Neg logit contributions
llan-0.057
 Luthor-0.053
oid-0.051
-0.047
exclusive-0.047
Token 2010
Token ID3050
Feature activation+1.91e+00

Pos logit contributions
llan+0.299
 Luthor+0.287
oid+0.272
+0.260
exclusive+0.256
Neg logit contributions
atorium-0.202
ratulations-0.180
 manoeuv-0.168
 scrape-0.160
 rese-0.158
Token
Token ID198
Feature activation+1.50e+00

Pos logit contributions
llan+1.307
 Luthor+1.217
oid+1.182
exclusive+1.067
+1.053
Neg logit contributions
atorium-1.752
ratulations-1.675
everal-1.630
acebook-1.554
 manoeuv-1.542
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
llan+1.015
 Luthor+0.944
oid+0.924
exclusive+0.828
+0.813
Neg logit contributions
atorium-1.379
ratulations-1.326
everal-1.297
acebook-1.230
Downloadha-1.217
TokenSubject
Token ID19776
Feature activation+4.83e+00

Pos logit contributions
llan+0.733
 Luthor+0.678
oid+0.658
exclusive+0.588
+0.580
Neg logit contributions
atorium-1.339
ratulations-1.265
 manoeuv-1.210
everal-1.172
 scrape-1.170
Token:
Token ID25
Feature activation+1.47e+00

Pos logit contributions
llan+2.832
oid+2.618
 Luthor+2.572
exclusive+2.255
+2.182
Neg logit contributions
atorium-4.810
everal-4.798
ratulations-4.756
acebook-4.450
Downloadha-4.386
Token R
Token ID371
Feature activation-8.61e-02

Pos logit contributions
llan+1.074
 Luthor+1.026
oid+0.985
+0.910
exclusive+0.908
Neg logit contributions
atorium-1.254
ratulations-1.140
 manoeuv-1.093
Downloadha-1.064
 scrape-1.035
Tokeniff
Token ID733
Feature activation-1.07e+00

Pos logit contributions
atorium+0.072
ratulations+0.066
 manoeuv+0.063
Downloadha+0.061
 scrape+0.061
Neg logit contributions
llan-0.064
 Luthor-0.061
oid-0.060
-0.055
exclusive-0.054
TokenTra
Token ID15721
Feature activation+1.44e-01

Pos logit contributions
atorium+0.917
ratulations+0.833
 manoeuv+0.800
 scrape+0.766
Downloadha+0.762
Neg logit contributions
llan-0.786
 Luthor-0.744
oid-0.706
-0.665
exclusive-0.656
Tokenx
Token ID87
Feature activation+8.00e-01

Pos logit contributions
llan+0.071
 Luthor+0.065
oid+0.061
+0.054
exclusive+0.053
Neg logit contributions
atorium-0.159
ratulations-0.149
 manoeuv-0.144
Downloadha-0.139
 scrape-0.139
Token,
Token ID11
Feature activation-2.10e-01

Pos logit contributions
llan+0.515
 Luthor+0.489
oid+0.467
+0.435
exclusive+0.430
Neg logit contributions
atorium-0.603
ratulations-0.548
 manoeuv-0.524
Downloadha-0.502
 scrape-0.498
Token 8
Token ID807
Feature activation-7.78e-02

Pos logit contributions
atorium+0.177
ratulations+0.160
 manoeuv+0.152
Downloadha+0.146
acebook+0.145
Neg logit contributions
llan-0.159
 Luthor-0.152
oid-0.145
-0.135
exclusive-0.134
Token:
Token ID25
Feature activation+1.86e+00

Pos logit contributions
atorium+0.067
ratulations+0.061
 manoeuv+0.058
Downloadha+0.056
 scrape+0.056
Neg logit contributions
llan-0.057
 Luthor-0.054
oid-0.052
-0.049
exclusive-0.048
Token00
Token ID405
Feature activation+8.21e-01

Pos logit contributions
llan+1.464
 Luthor+1.392
oid+1.341
exclusive+1.252
+1.224
Neg logit contributions
atorium-1.518
ratulations-1.442
everal-1.347
 manoeuv-1.318
acebook-1.300
Token PM
Token ID3122
Feature activation+3.68e+00

Pos logit contributions
llan+0.623
 Luthor+0.592
oid+0.566
+0.532
exclusive+0.525
Neg logit contributions
atorium-0.686
ratulations-0.623
 manoeuv-0.596
Downloadha-0.570
 scrape-0.569
Token PDT
Token ID28288
Feature activation+4.72e+00

Pos logit contributions
llan+2.615
 Luthor+2.483
oid+2.362
+2.211
exclusive+2.176
Neg logit contributions
atorium-3.201
ratulations-2.942
 manoeuv-2.804
everal-2.656
acebook-2.647
Token
Token ID198
Feature activation+3.52e-01

Pos logit contributions
llan+3.223
 Luthor+3.037
oid+2.908
+2.666
exclusive+2.649
Neg logit contributions
atorium-4.224
ratulations-3.877
 manoeuv-3.695
acebook-3.532
everal-3.511
Token
Token ID198
Feature activation+2.02e-01

Pos logit contributions
llan+0.248
 Luthor+0.233
oid+0.226
exclusive+0.205
+0.204
Neg logit contributions
atorium-0.315
ratulations-0.298
everal-0.284
 manoeuv-0.276
acebook-0.274
TokenThe
Token ID464
Feature activation+6.12e-02

Pos logit contributions
llan+0.153
 Luthor+0.145
oid+0.140
+0.131
exclusive+0.130
Neg logit contributions
atorium-0.169
ratulations-0.154
 manoeuv-0.148
 scrape-0.141
Downloadha-0.140
Token developer
Token ID8517
Feature activation-4.98e-01

Pos logit contributions
llan+0.049
 Luthor+0.046
oid+0.045
+0.042
exclusive+0.041
Neg logit contributions
atorium-0.049
ratulations-0.044
 manoeuv-0.042
Downloadha-0.040
 scrape-0.040
Token of
Token ID286
Feature activation+6.25e-01

Pos logit contributions
atorium+0.412
ratulations+0.374
 manoeuv+0.357
Downloadha+0.343
 scrape+0.340
Neg logit contributions
llan-0.381
 Luthor-0.363
oid-0.349
-0.327
exclusive-0.322
TokenAB
Token ID6242
Feature activation-2.45e+00

Pos logit contributions
llan+0.018
 Luthor+0.017
oid+0.017
+0.015
exclusive+0.015
Neg logit contributions
atorium-0.021
ratulations-0.019
 manoeuv-0.018
Downloadha-0.017
 scrape-0.017
Tokenarry
Token ID6532
Feature activation-5.97e-01

Pos logit contributions
atorium+2.026
ratulations+1.830
 manoeuv+1.753
 scrape+1.679
Downloadha+1.664
Neg logit contributions
llan-1.869
 Luthor-1.780
oid-1.695
-1.606
exclusive-1.579
Token Maryland
Token ID10769
Feature activation-9.33e-01

Pos logit contributions
atorium+0.500
ratulations+0.454
 manoeuv+0.435
Downloadha+0.417
 scrape+0.415
Neg logit contributions
llan-0.453
 Luthor-0.430
oid-0.412
-0.386
exclusive-0.381
Token 1
Token ID352
Feature activation+1.67e-01

Pos logit contributions
atorium+0.701
ratulations+0.631
 manoeuv+0.597
Downloadha+0.575
 scrape+0.565
Neg logit contributions
llan-0.787
 Luthor-0.756
oid-0.727
-0.682
exclusive-0.676
Token hour
Token ID1711
Feature activation+6.24e-01

Pos logit contributions
llan+0.140
 Luthor+0.134
oid+0.129
+0.122
exclusive+0.120
Neg logit contributions
atorium-0.126
ratulations-0.113
 manoeuv-0.108
Downloadha-0.103
 scrape-0.102
Token ago
Token ID2084
Feature activation+4.72e+00

Pos logit contributions
llan+0.365
 Luthor+0.341
oid+0.321
+0.295
exclusive+0.290
Neg logit contributions
atorium-0.631
ratulations-0.584
 manoeuv-0.562
Downloadha-0.543
 scrape-0.541
Token This
Token ID770
Feature activation+1.72e+00

Pos logit contributions
llan+3.212
 Luthor+3.112
oid+2.926
 Negative+2.701
 Fired+2.686
Neg logit contributions
atorium-4.183
ratulations-3.886
 manoeuv-3.691
Downloadha-3.607
everal-3.548
Token election
Token ID3071
Feature activation+6.60e-01

Pos logit contributions
llan+1.252
 Luthor+1.192
oid+1.141
+1.048
exclusive+1.040
Neg logit contributions
atorium-1.488
ratulations-1.359
 manoeuv-1.283
Downloadha-1.273
 scrape-1.229
Token was
Token ID373
Feature activation+3.53e-01

Pos logit contributions
llan+0.522
 Luthor+0.499
oid+0.479
+0.447
exclusive+0.443
Neg logit contributions
atorium-0.529
ratulations-0.480
 manoeuv-0.455
Downloadha-0.442
 scrape-0.435
Token not
Token ID407
Feature activation-4.41e-01

Pos logit contributions
llan+0.257
 Luthor+0.246
oid+0.234
+0.216
exclusive+0.215
Neg logit contributions
atorium-0.305
ratulations-0.280
 manoeuv-0.264
Downloadha-0.259
 scrape-0.254
Token about
Token ID546
Feature activation-4.90e-02

Pos logit contributions
atorium+0.401
ratulations+0.370
 manoeuv+0.351
Downloadha+0.343
 scrape+0.338
Neg logit contributions
llan-0.302
 Luthor-0.288
oid-0.272
-0.251
exclusive-0.248
Tokenwitz
Token ID28155
Feature activation+3.72e-01

Pos logit contributions
llan+0.032
 Luthor+0.031
oid+0.029
+0.028
exclusive+0.027
Neg logit contributions
atorium-0.033
ratulations-0.030
 manoeuv-0.028
Downloadha-0.027
 scrape-0.027
Token West
Token ID2688
Feature activation-8.00e-01

Pos logit contributions
llan+0.297
 Luthor+0.284
oid+0.272
+0.255
exclusive+0.252
Neg logit contributions
atorium-0.296
ratulations-0.267
 manoeuv-0.256
Downloadha-0.245
 scrape-0.243
Tokenchester
Token ID35983
Feature activation+1.02e+00

Pos logit contributions
atorium+0.614
ratulations+0.552
 manoeuv+0.526
Downloadha+0.501
 scrape+0.501
Neg logit contributions
llan-0.662
 Luthor-0.632
oid-0.606
-0.573
exclusive-0.566
Token 1
Token ID352
Feature activation+4.14e-01

Pos logit contributions
llan+0.771
 Luthor+0.735
oid+0.704
+0.654
exclusive+0.646
Neg logit contributions
atorium-0.861
ratulations-0.783
 manoeuv-0.749
Downloadha-0.721
 scrape-0.715
Token hour
Token ID1711
Feature activation+9.10e-01

Pos logit contributions
llan+0.336
 Luthor+0.320
oid+0.308
+0.290
exclusive+0.286
Neg logit contributions
atorium-0.325
ratulations-0.293
 manoeuv-0.279
Downloadha-0.267
 scrape-0.266
Token ago
Token ID2084
Feature activation+4.71e+00

Pos logit contributions
llan+0.495
 Luthor+0.459
oid+0.434
exclusive+0.388
+0.375
Neg logit contributions
atorium-0.955
ratulations-0.899
 manoeuv-0.858
everal-0.850
acebook-0.841
Token Pretty
Token ID20090
Feature activation+1.54e+00

Pos logit contributions
llan+3.237
 Luthor+3.154
oid+2.961
 Fired+2.779
 Negative+2.771
Neg logit contributions
atorium-4.143
ratulations-3.857
 manoeuv-3.654
Downloadha-3.557
everal-3.517
Token simple
Token ID2829
Feature activation+1.49e+00

Pos logit contributions
llan+1.171
 Luthor+1.122
oid+1.076
+0.990
exclusive+0.983
Neg logit contributions
atorium-1.278
ratulations-1.157
 manoeuv-1.097
Downloadha-1.087
brance-1.045
Token Paul
Token ID3362
Feature activation+3.17e-01

Pos logit contributions
llan+1.097
 Luthor+1.044
oid+1.003
+0.924
exclusive+0.906
Neg logit contributions
atorium-1.279
ratulations-1.158
 manoeuv-1.089
Downloadha-1.084
everal-1.055
Token:
Token ID25
Feature activation+1.28e+00

Pos logit contributions
llan+0.230
 Luthor+0.218
oid+0.209
+0.195
exclusive+0.192
Neg logit contributions
atorium-0.275
ratulations-0.250
 manoeuv-0.240
Downloadha-0.231
 scrape-0.230
Token
Token ID198
Feature activation+1.17e+00

Pos logit contributions
llan+0.931
 Luthor+0.890
oid+0.851
+0.790
exclusive+0.782
Neg logit contributions
atorium-1.098
ratulations-1.000
 manoeuv-0.956
Downloadha-0.922
brance-0.906
Token 15
Token ID1315
Feature activation+3.66e-01

Pos logit contributions
atorium+0.281
ratulations+0.261
everal+0.242
 manoeuv+0.241
Downloadha+0.238
Neg logit contributions
llan-0.290
 Luthor-0.278
oid-0.266
-0.247
exclusive-0.245
Token,
Token ID11
Feature activation+7.30e-02

Pos logit contributions
llan+0.257
 Luthor+0.241
oid+0.232
exclusive+0.210
+0.209
Neg logit contributions
atorium-0.331
ratulations-0.313
everal-0.298
 manoeuv-0.291
acebook-0.287
Token 2010
Token ID3050
Feature activation+2.05e+00

Pos logit contributions
llan+0.070
 Luthor+0.067
oid+0.064
+0.061
exclusive+0.060
Neg logit contributions
atorium-0.047
ratulations-0.042
 manoeuv-0.039
 scrape-0.037
acebook-0.037
Token
Token ID198
Feature activation+1.45e+00

Pos logit contributions
llan+1.400
 Luthor+1.305
oid+1.267
exclusive+1.141
+1.132
Neg logit contributions
atorium-1.875
ratulations-1.790
everal-1.744
acebook-1.657
 manoeuv-1.653
Token
Token ID198
Feature activation+1.25e+00

Pos logit contributions
llan+0.989
 Luthor+0.920
oid+0.899
exclusive+0.807
+0.793
Neg logit contributions
atorium-1.334
ratulations-1.279
everal-1.248
acebook-1.185
Downloadha-1.175
TokenSubject
Token ID19776
Feature activation+4.69e+00

Pos logit contributions
llan+0.698
 Luthor+0.645
oid+0.631
exclusive+0.561
+0.550
Neg logit contributions
atorium-1.290
ratulations-1.223
 manoeuv-1.168
everal-1.144
 scrape-1.130
Token:
Token ID25
Feature activation+1.41e+00

Pos logit contributions
llan+2.765
oid+2.561
 Luthor+2.525
exclusive+2.201
+2.153
Neg logit contributions
atorium-4.642
everal-4.623
ratulations-4.594
acebook-4.288
Downloadha-4.237
Token Que
Token ID4670
Feature activation-2.88e-01

Pos logit contributions
llan+1.034
 Luthor+0.988
oid+0.949
+0.878
exclusive+0.875
Neg logit contributions
atorium-1.203
ratulations-1.094
 manoeuv-1.051
Downloadha-1.020
brance-0.991
Tokener
Token ID263
Feature activation+1.05e+00

Pos logit contributions
atorium+0.235
ratulations+0.213
 manoeuv+0.204
Downloadha+0.195
 scrape+0.194
Neg logit contributions
llan-0.223
 Luthor-0.213
oid-0.204
-0.191
exclusive-0.189
Token magnet
Token ID19972
Feature activation-1.09e+00

Pos logit contributions
llan+0.764
 Luthor+0.724
oid+0.703
+0.646
exclusive+0.642
Neg logit contributions
atorium-0.894
ratulations-0.823
 manoeuv-0.785
Downloadha-0.766
 scrape-0.747
Token?
Token ID30
Feature activation-1.67e-01

Pos logit contributions
atorium+0.949
ratulations+0.865
 manoeuv+0.830
Downloadha+0.797
 scrape+0.794
Neg logit contributions
llan-0.797
 Luthor-0.756
oid-0.723
-0.676
exclusive-0.665
Token min
Token ID949
Feature activation+8.77e-01

Pos logit contributions
atorium+0.395
ratulations+0.358
 manoeuv+0.340
Downloadha+0.327
 scrape+0.325
Neg logit contributions
llan-0.394
 Luthor-0.377
oid-0.361
-0.339
exclusive-0.335
Tokeniser
Token ID5847
Feature activation+5.30e-01

Pos logit contributions
llan+0.657
 Luthor+0.624
oid+0.597
+0.559
exclusive+0.552
Neg logit contributions
atorium-0.741
ratulations-0.674
 manoeuv-0.645
Downloadha-0.619
 scrape-0.617
Tokenies
Token ID444
Feature activation-1.15e+00

Pos logit contributions
llan+0.467
 Luthor+0.451
oid+0.450
+0.408
exclusive+0.406
Neg logit contributions
atorium-0.364
ratulations-0.340
 manoeuv-0.313
Downloadha-0.312
 scrape-0.302
Token since
Token ID1201
Feature activation-1.22e+00

Pos logit contributions
atorium+0.994
ratulations+0.896
 manoeuv+0.866
 scrape+0.828
Downloadha+0.826
Neg logit contributions
llan-0.846
 Luthor-0.800
oid-0.765
-0.720
exclusive-0.707
Token 2009
Token ID3717
Feature activation+4.05e-01

Pos logit contributions
atorium+0.981
ratulations+0.890
 manoeuv+0.847
Downloadha+0.813
 scrape+0.807
Neg logit contributions
llan-0.968
 Luthor-0.927
oid-0.886
-0.832
exclusive-0.822
Token
Token ID17478
Feature activation+4.69e+00

Pos logit contributions
llan+0.311
 Luthor+0.295
oid+0.281
+0.266
exclusive+0.261
Neg logit contributions
atorium-0.336
ratulations-0.302
 manoeuv-0.291
Downloadha-0.278
 scrape-0.278
Tokens
Token ID82
Feature activation-2.76e-01

Pos logit contributions
llan+2.024
 Luthor+1.883
oid+1.700
+1.465
exclusive+1.462
Neg logit contributions
atorium-5.371
ratulations-5.128
 manoeuv-4.849
Downloadha-4.807
everal-4.734
Token Alice
Token ID14862
Feature activation+5.00e-01

Pos logit contributions
atorium+0.237
ratulations+0.218
 manoeuv+0.207
Downloadha+0.200
 scrape+0.198
Neg logit contributions
llan-0.203
 Luthor-0.193
oid-0.184
-0.172
exclusive-0.170
Token,
Token ID11
Feature activation-2.32e-01

Pos logit contributions
llan+0.350
 Luthor+0.331
oid+0.315
+0.294
exclusive+0.290
Neg logit contributions
atorium-0.448
ratulations-0.409
 manoeuv-0.393
Downloadha-0.378
 scrape-0.377
Token the
Token ID262
Feature activation+9.68e-02

Pos logit contributions
atorium+0.195
ratulations+0.177
 manoeuv+0.170
Downloadha+0.163
 scrape+0.162
Neg logit contributions
llan-0.175
 Luthor-0.167
oid-0.159
-0.149
exclusive-0.147
Token six
Token ID2237
Feature activation+2.46e-01

Pos logit contributions
llan+0.076
 Luthor+0.073
oid+0.069
+0.065
exclusive+0.065
Neg logit contributions
atorium-0.078
ratulations-0.072
 manoeuv-0.067
Downloadha-0.066
 scrape-0.064
Token East
Token ID3687
Feature activation-1.77e+00

Pos logit contributions
atorium+0.176
ratulations+0.160
 manoeuv+0.154
Downloadha+0.147
 scrape+0.147
Neg logit contributions
llan-0.156
 Luthor-0.149
oid-0.142
-0.133
exclusive-0.131
Tokenon
Token ID261
Feature activation+9.14e-01

Pos logit contributions
atorium+1.508
ratulations+1.370
 manoeuv+1.312
 scrape+1.259
Downloadha+1.256
Neg logit contributions
llan-1.303
 Luthor-1.240
oid-1.183
-1.114
exclusive-1.092
Token PA
Token ID8147
Feature activation+1.98e-01

Pos logit contributions
llan+0.691
 Luthor+0.658
oid+0.630
+0.589
exclusive+0.581
Neg logit contributions
atorium-0.765
ratulations-0.695
 manoeuv-0.667
Downloadha-0.639
 scrape-0.636
Token 1
Token ID352
Feature activation+3.52e-01

Pos logit contributions
llan+0.158
 Luthor+0.151
oid+0.145
+0.136
exclusive+0.135
Neg logit contributions
atorium-0.158
ratulations-0.143
 manoeuv-0.136
Downloadha-0.130
 scrape-0.130
Token hour
Token ID1711
Feature activation+9.56e-01

Pos logit contributions
llan+0.277
 Luthor+0.260
oid+0.253
exclusive+0.234
+0.234
Neg logit contributions
atorium-0.289
ratulations-0.261
 manoeuv-0.248
Downloadha-0.241
 scrape-0.236
Token ago
Token ID2084
Feature activation+4.65e+00

Pos logit contributions
llan+0.518
 Luthor+0.480
oid+0.459
exclusive+0.407
+0.392
Neg logit contributions
atorium-1.000
ratulations-0.944
 manoeuv-0.900
everal-0.897
acebook-0.885
Token I
Token ID314
Feature activation+5.59e-01

Pos logit contributions
llan+3.194
 Luthor+3.087
oid+2.899
 Fired+2.704
 Negative+2.692
Neg logit contributions
atorium-4.131
ratulations-3.835
 manoeuv-3.649
Downloadha-3.550
everal-3.520
Token think
Token ID892
Feature activation-9.57e-02

Pos logit contributions
llan+0.438
 Luthor+0.416
oid+0.400
+0.366
exclusive+0.365
Neg logit contributions
atorium-0.460
ratulations-0.412
 manoeuv-0.389
Downloadha-0.388
acebook-0.376
Token a
Token ID257
Feature activation-3.42e-01

Pos logit contributions
atorium+0.082
ratulations+0.075
 manoeuv+0.071
Downloadha+0.069
 scrape+0.068
Neg logit contributions
llan-0.071
 Luthor-0.068
oid-0.064
-0.060
exclusive-0.059
Token simple
Token ID2829
Feature activation+2.75e-01

Pos logit contributions
atorium+0.265
ratulations+0.239
 manoeuv+0.227
Downloadha+0.220
 scrape+0.215
Neg logit contributions
llan-0.282
 Luthor-0.269
oid-0.258
-0.243
exclusive-0.239
Token passing
Token ID6427
Feature activation-6.35e-01

Pos logit contributions
llan+0.217
 Luthor+0.207
oid+0.199
+0.185
exclusive+0.181
Neg logit contributions
atorium-0.223
ratulations-0.202
 manoeuv-0.191
Downloadha-0.187
everal-0.181
Token 9
Token ID860
Feature activation-1.94e-01

Pos logit contributions
atorium+0.196
ratulations+0.184
everal+0.170
 manoeuv+0.169
Downloadha+0.167
Neg logit contributions
llan-0.201
 Luthor-0.192
oid-0.184
-0.170
exclusive-0.169
Token,
Token ID11
Feature activation+8.91e-01

Pos logit contributions
atorium+0.173
ratulations+0.162
everal+0.152
 manoeuv+0.152
Downloadha+0.149
Neg logit contributions
llan-0.138
 Luthor-0.130
oid-0.126
-0.115
exclusive-0.114
Token 2010
Token ID3050
Feature activation+2.26e+00

Pos logit contributions
llan+0.846
 Luthor+0.810
oid+0.771
+0.739
exclusive+0.727
Neg logit contributions
atorium-0.583
ratulations-0.521
 manoeuv-0.483
 scrape-0.462
 rese-0.454
Token
Token ID198
Feature activation+1.51e+00

Pos logit contributions
llan+1.535
 Luthor+1.431
oid+1.389
exclusive+1.252
+1.237
Neg logit contributions
atorium-2.072
ratulations-1.981
everal-1.936
acebook-1.841
Downloadha-1.826
Token
Token ID198
Feature activation+1.31e+00

Pos logit contributions
llan+1.023
 Luthor+0.952
oid+0.931
exclusive+0.834
+0.819
Neg logit contributions
atorium-1.385
ratulations-1.330
everal-1.300
acebook-1.234
Downloadha-1.222
TokenSubject
Token ID19776
Feature activation+4.58e+00

Pos logit contributions
llan+0.735
 Luthor+0.679
oid+0.663
exclusive+0.591
+0.580
Neg logit contributions
atorium-1.351
ratulations-1.279
 manoeuv-1.224
everal-1.194
 scrape-1.183
Token:
Token ID25
Feature activation+1.44e+00

Pos logit contributions
llan+2.711
oid+2.510
 Luthor+2.475
exclusive+2.163
+2.108
Neg logit contributions
atorium-4.524
everal-4.490
ratulations-4.461
acebook-4.169
Downloadha-4.119
Token R
Token ID371
Feature activation+4.56e-02

Pos logit contributions
llan+1.053
 Luthor+1.007
oid+0.966
+0.895
exclusive+0.892
Neg logit contributions
atorium-1.231
ratulations-1.121
 manoeuv-1.076
Downloadha-1.045
 scrape-1.016
Tokenipe
Token ID3757
Feature activation+3.43e-01

Pos logit contributions
llan+0.034
 Luthor+0.032
oid+0.031
+0.029
exclusive+0.029
Neg logit contributions
atorium-0.039
ratulations-0.035
 manoeuv-0.034
Downloadha-0.032
 scrape-0.032
Token for
Token ID329
Feature activation+1.91e-01

Pos logit contributions
llan+0.254
 Luthor+0.241
oid+0.232
+0.215
exclusive+0.213
Neg logit contributions
atorium-0.293
ratulations-0.267
 manoeuv-0.256
Downloadha-0.247
 scrape-0.243
Token M
Token ID337
Feature activation-9.95e-02

Pos logit contributions
llan+0.145
 Luthor+0.139
oid+0.133
+0.124
exclusive+0.122
Neg logit contributions
atorium-0.159
ratulations-0.144
 manoeuv-0.137
Downloadha-0.133
 scrape-0.131
Token the
Token ID262
Feature activation+4.40e-02

Pos logit contributions
atorium+0.075
ratulations+0.068
 manoeuv+0.064
Downloadha+0.062
 scrape+0.061
Neg logit contributions
llan-0.076
 Luthor-0.073
oid-0.070
-0.066
exclusive-0.065
Token use
Token ID779
Feature activation+2.04e-01

Pos logit contributions
llan+0.036
 Luthor+0.035
oid+0.033
+0.031
exclusive+0.031
Neg logit contributions
atorium-0.034
ratulations-0.031
 manoeuv-0.029
Downloadha-0.028
 scrape-0.027
Token of
Token ID286
Feature activation+7.60e-01

Pos logit contributions
llan+0.121
 Luthor+0.113
oid+0.107
+0.097
exclusive+0.096
Neg logit contributions
atorium-0.204
ratulations-0.190
 manoeuv-0.181
Downloadha-0.176
 scrape-0.176
Token general
Token ID2276
Feature activation+7.95e-01

Pos logit contributions
llan+0.600
 Luthor+0.573
oid+0.548
+0.516
exclusive+0.509
Neg logit contributions
atorium-0.614
ratulations-0.556
 manoeuv-0.522
Downloadha-0.508
 scrape-0.499
Token-
Token ID12
Feature activation+7.61e-01

Pos logit contributions
llan+0.659
 Luthor+0.635
oid+0.615
+0.574
essim+0.566
Neg logit contributions
atorium-0.603
ratulations-0.548
 manoeuv-0.509
Downloadha-0.498
 scrape-0.489
Tokencirc
Token ID21170
Feature activation+4.45e+00

Pos logit contributions
llan+0.739
 Luthor+0.713
oid+0.692
+0.658
exclusive+0.653
Neg logit contributions
atorium-0.470
ratulations-0.415
 manoeuv-0.388
Downloadha-0.367
 scrape-0.366
Tokenulation
Token ID1741
Feature activation-5.60e-01

Pos logit contributions
llan+4.535
 Luthor+4.278
oid+4.269
essim+3.993
exclusive+3.975
Neg logit contributions
atorium-2.481
ratulations-2.185
Downloadha-1.957
 manoeuv-1.950
 scrape-1.876
Token models
Token ID4981
Feature activation+1.07e-01

Pos logit contributions
atorium+0.432
ratulations+0.390
 manoeuv+0.367
Downloadha+0.355
 scrape+0.351
Neg logit contributions
llan-0.461
 Luthor-0.441
oid-0.425
-0.399
exclusive-0.394
Token.
Token ID13
Feature activation-3.65e-01

Pos logit contributions
llan+0.079
 Luthor+0.075
oid+0.072
+0.067
exclusive+0.066
Neg logit contributions
atorium-0.092
ratulations-0.083
 manoeuv-0.079
Downloadha-0.077
 scrape-0.076
Token I
Token ID314
Feature activation+1.21e-01

Pos logit contributions
atorium+0.324
ratulations+0.300
 manoeuv+0.285
Downloadha+0.276
 scrape+0.273
Neg logit contributions
llan-0.259
 Luthor-0.247
oid-0.235
-0.219
exclusive-0.214
Token don
Token ID836
Feature activation-9.23e-01

Pos logit contributions
llan+0.093
 Luthor+0.088
oid+0.085
exclusive+0.077
+0.077
Neg logit contributions
atorium-0.102
ratulations-0.092
Downloadha-0.086
 manoeuv-0.086
acebook-0.084
Token Others
Token ID12691
Feature activation+1.63e+00

Pos logit contributions
llan+1.547
 Luthor+1.432
oid+1.397
exclusive+1.301
+1.299
Neg logit contributions
atorium-1.573
ratulations-1.442
 manoeuv-1.386
Downloadha-1.321
 scrape-1.305
Token Marvin
Token ID35105
Feature activation-2.09e-01

Pos logit contributions
llan+1.252
 Luthor+1.181
oid+1.133
+1.055
exclusive+1.050
Neg logit contributions
atorium-1.342
ratulations-1.228
 manoeuv-1.173
Downloadha-1.123
 scrape-1.106
Token Wilson
Token ID8127
Feature activation+4.69e-01

Pos logit contributions
atorium+0.193
ratulations+0.176
 manoeuv+0.169
Downloadha+0.163
 scrape+0.163
Neg logit contributions
llan-0.140
 Luthor-0.132
oid-0.125
-0.117
exclusive-0.116
Token DT
Token ID24311
Feature activation+1.31e+00

Pos logit contributions
llan+0.352
 Luthor+0.334
oid+0.320
+0.298
exclusive+0.295
Neg logit contributions
atorium-0.397
ratulations-0.363
 manoeuv-0.346
Downloadha-0.333
 scrape-0.330
Token 6
Token ID718
Feature activation+1.29e+00

Pos logit contributions
llan+1.011
 Luthor+0.962
oid+0.918
+0.863
exclusive+0.851
Neg logit contributions
atorium-1.081
ratulations-0.990
 manoeuv-0.941
Downloadha-0.903
 scrape-0.892
Token'
Token ID6
Feature activation+4.41e+00

Pos logit contributions
llan+0.914
 Luthor+0.863
oid+0.827
+0.775
exclusive+0.757
Neg logit contributions
atorium-1.138
ratulations-1.044
 manoeuv-1.000
Downloadha-0.965
 scrape-0.952
Token4
Token ID19
Feature activation+8.24e-01

Pos logit contributions
llan+3.078
 Luthor+2.937
oid+2.796
+2.603
exclusive+2.561
Neg logit contributions
atorium-3.890
ratulations-3.669
 manoeuv-3.440
everal-3.352
Downloadha-3.330
Token/
Token ID14
Feature activation+1.68e+00

Pos logit contributions
llan+0.627
 Luthor+0.598
oid+0.573
+0.537
exclusive+0.527
Neg logit contributions
atorium-0.686
ratulations-0.624
 manoeuv-0.596
Downloadha-0.571
 scrape-0.567
Token329
Token ID37967
Feature activation+6.97e-01

Pos logit contributions
llan+1.525
 Luthor+1.468
oid+1.432
+1.362
exclusive+1.357
Neg logit contributions
atorium-1.134
ratulations-1.027
 manoeuv-0.962
Downloadha-0.914
 scrape-0.906
Token 5
Token ID642
Feature activation+4.51e-01

Pos logit contributions
llan+0.565
 Luthor+0.542
oid+0.519
+0.489
exclusive+0.480
Neg logit contributions
atorium-0.545
ratulations-0.495
 manoeuv-0.470
Downloadha-0.450
 scrape-0.445
Token*
Token ID9
Feature activation+3.33e+00

Pos logit contributions
llan+0.341
 Luthor+0.325
oid+0.312
+0.292
exclusive+0.286
Neg logit contributions
atorium-0.377
ratulations-0.344
 manoeuv-0.329
Downloadha-0.317
 scrape-0.313
Token 16
Token ID1467
Feature activation+8.12e-01

Pos logit contributions
llan+0.108
 Luthor+0.102
oid+0.098
+0.091
exclusive+0.090
Neg logit contributions
atorium-0.112
ratulations-0.102
 manoeuv-0.096
Downloadha-0.093
 scrape-0.092
Token25
Token ID1495
Feature activation+6.30e-01

Pos logit contributions
llan+0.613
 Luthor+0.580
oid+0.556
+0.518
exclusive+0.512
Neg logit contributions
atorium-0.688
ratulations-0.626
 manoeuv-0.596
Downloadha-0.574
 scrape-0.568
Token,
Token ID11
Feature activation-9.93e-02

Pos logit contributions
llan+0.463
 Luthor+0.439
oid+0.420
+0.392
exclusive+0.386
Neg logit contributions
atorium-0.544
ratulations-0.496
 manoeuv-0.474
Downloadha-0.456
 scrape-0.453
Token when
Token ID618
Feature activation+8.87e-01

Pos logit contributions
atorium+0.086
ratulations+0.078
 manoeuv+0.075
Downloadha+0.072
 scrape+0.071
Neg logit contributions
llan-0.073
 Luthor-0.069
oid-0.066
-0.062
exclusive-0.061
Token d
Token ID288
Feature activation-2.89e-01

Pos logit contributions
llan+0.673
 Luthor+0.639
oid+0.608
+0.567
exclusive+0.558
Neg logit contributions
atorium-0.745
ratulations-0.677
 manoeuv-0.644
Downloadha-0.627
 scrape-0.617
Token'
Token ID6
Feature activation+4.40e+00

Pos logit contributions
atorium+0.240
ratulations+0.218
 manoeuv+0.208
Downloadha+0.200
 scrape+0.199
Neg logit contributions
llan-0.222
 Luthor-0.210
oid-0.203
-0.189
exclusive-0.187
TokenArt
Token ID8001
Feature activation+1.24e+00

Pos logit contributions
llan+3.123
 Luthor+2.973
oid+2.901
exclusive+2.696
essim+2.621
Neg logit contributions
atorium-3.773
ratulations-3.434
 manoeuv-3.294
 scrape-3.252
acebook-3.192
Tokenagn
Token ID4660
Feature activation-1.44e+00

Pos logit contributions
llan+0.926
 Luthor+0.874
oid+0.840
+0.778
exclusive+0.773
Neg logit contributions
atorium-1.050
ratulations-0.961
 manoeuv-0.915
Downloadha-0.886
 scrape-0.880
Tokenan
Token ID272
Feature activation-9.23e-01

Pos logit contributions
atorium+1.454
ratulations+1.335
 manoeuv+1.285
 scrape+1.236
Downloadha+1.233
Neg logit contributions
llan-0.843
 Luthor-0.798
oid-0.744
-0.694
exclusive-0.678
Token,
Token ID11
Feature activation-4.60e-01

Pos logit contributions
atorium+0.784
ratulations+0.713
 manoeuv+0.681
Downloadha+0.655
 scrape+0.652
Neg logit contributions
llan-0.690
 Luthor-0.656
oid-0.627
-0.588
exclusive-0.578
Token rushing
Token ID15795
Feature activation+1.19e+00

Pos logit contributions
atorium+0.384
ratulations+0.348
 manoeuv+0.331
Downloadha+0.319
 scrape+0.317
Neg logit contributions
llan-0.352
 Luthor-0.336
oid-0.320
-0.300
exclusive-0.295
Token annual
Token ID5079
Feature activation+5.07e-01

Pos logit contributions
llan+0.730
 Luthor+0.694
oid+0.674
+0.620
exclusive+0.619
Neg logit contributions
atorium-0.692
ratulations-0.622
 manoeuv-0.575
Downloadha-0.571
everal-0.554
Token report
Token ID989
Feature activation+8.67e-02

Pos logit contributions
llan+0.399
 Luthor+0.379
oid+0.368
+0.341
exclusive+0.337
Neg logit contributions
atorium-0.411
ratulations-0.370
 manoeuv-0.347
Downloadha-0.341
 scrape-0.333
Token,
Token ID11
Feature activation+3.13e-01

Pos logit contributions
llan+0.065
 Luthor+0.062
oid+0.059
+0.055
exclusive+0.054
Neg logit contributions
atorium-0.073
ratulations-0.066
 manoeuv-0.064
 scrape-0.061
Downloadha-0.061
Token Katherine
Token ID32719
Feature activation-2.26e-01

Pos logit contributions
llan+0.239
 Luthor+0.228
oid+0.217
+0.204
exclusive+0.201
Neg logit contributions
atorium-0.261
ratulations-0.237
 manoeuv-0.226
Downloadha-0.217
 scrape-0.216
Token d
Token ID288
Feature activation-9.40e-01

Pos logit contributions
atorium+0.193
ratulations+0.176
 manoeuv+0.168
Downloadha+0.161
 scrape+0.160
Neg logit contributions
llan-0.169
 Luthor-0.161
oid-0.153
-0.143
exclusive-0.141
Token'
Token ID6
Feature activation+4.40e+00

Pos logit contributions
atorium+0.739
ratulations+0.666
 manoeuv+0.636
Downloadha+0.606
 scrape+0.605
Neg logit contributions
llan-0.760
 Luthor-0.726
oid-0.696
-0.657
exclusive-0.648
TokenEnt
Token ID14539
Feature activation+1.76e+00

Pos logit contributions
llan+2.957
 Luthor+2.814
oid+2.739
exclusive+2.516
+2.444
Neg logit contributions
atorium-3.969
ratulations-3.685
 manoeuv-3.467
 scrape-3.407
acebook-3.373
Tokenrem
Token ID2787
Feature activation-9.85e-01

Pos logit contributions
llan+1.289
 Luthor+1.196
oid+1.164
+1.067
exclusive+1.064
Neg logit contributions
atorium-1.531
ratulations-1.394
 manoeuv-1.340
Downloadha-1.295
 scrape-1.288
Tokenont
Token ID756
Feature activation-1.00e+00

Pos logit contributions
atorium+0.597
ratulations+0.526
 manoeuv+0.493
Downloadha+0.468
 scrape+0.460
Neg logit contributions
llan-0.977
 Luthor-0.930
oid-0.908
-0.861
exclusive-0.854
Token calls
Token ID3848
Feature activation-4.86e-01

Pos logit contributions
atorium+0.865
ratulations+0.787
 manoeuv+0.753
Downloadha+0.723
 scrape+0.722
Neg logit contributions
llan-0.735
 Luthor-0.697
oid-0.668
-0.623
exclusive-0.614
Token for
Token ID329
Feature activation+2.18e-01

Pos logit contributions
atorium+0.455
ratulations+0.417
 manoeuv+0.400
Downloadha+0.387
 scrape+0.385
Neg logit contributions
llan-0.320
 Luthor-0.303
oid-0.287
-0.265
exclusive-0.262
Token States
Token ID1829
Feature activation+7.14e-01

Pos logit contributions
llan+1.210
 Luthor+1.138
oid+1.072
+0.958
exclusive+0.935
Neg logit contributions
atorium-2.362
ratulations-2.252
 manoeuv-2.145
Downloadha-2.121
everal-2.099
Token 6
Token ID718
Feature activation+3.17e-01

Pos logit contributions
llan+0.582
 Luthor+0.557
oid+0.534
+0.502
exclusive+0.492
Neg logit contributions
atorium-0.556
ratulations-0.522
 manoeuv-0.481
Downloadha-0.474
everal-0.470
Token83
Token ID5999
Feature activation+2.60e-01

Pos logit contributions
llan+0.258
 Luthor+0.247
oid+0.238
+0.223
exclusive+0.221
Neg logit contributions
atorium-0.248
ratulations-0.227
 manoeuv-0.214
Downloadha-0.205
everal-0.203
Token Posts
Token ID12043
Feature activation+3.72e+00

Pos logit contributions
llan+0.181
 Luthor+0.172
oid+0.163
+0.150
exclusive+0.148
Neg logit contributions
atorium-0.236
ratulations-0.224
 manoeuv-0.209
everal-0.208
Downloadha-0.204
Token Last
Token ID4586
Feature activation+2.86e+00

Pos logit contributions
llan+2.386
 Luthor+2.253
oid+2.139
+1.982
exclusive+1.945
Neg logit contributions
atorium-3.526
ratulations-3.241
 manoeuv-3.119
Downloadha-3.005
 scrape-2.996
Token Edited
Token ID34212
Feature activation+4.38e+00

Pos logit contributions
llan+0.447
 Luthor+0.322
oid+0.270
+0.142
exclusive+0.064
Neg logit contributions
atorium-4.133
ratulations-4.008
everal-3.868
 manoeuv-3.791
Downloadha-3.754
Token:
Token ID25
Feature activation+1.24e+00

Pos logit contributions
llan+2.532
 Luthor+2.369
oid+2.329
exclusive+1.997
+1.963
Neg logit contributions
everal-4.393
ratulations-4.388
atorium-4.369
acebook-4.058
Downloadha-4.019
Token 2013
Token ID2211
Feature activation+2.86e-02

Pos logit contributions
llan+0.931
 Luthor+0.886
oid+0.853
+0.778
exclusive+0.776
Neg logit contributions
atorium-1.052
ratulations-0.989
everal-0.937
 manoeuv-0.918
Downloadha-0.914
Token-
Token ID12
Feature activation+1.24e-01

Pos logit contributions
llan+0.018
 Luthor+0.016
oid+0.016
+0.014
exclusive+0.014
Neg logit contributions
atorium-0.028
ratulations-0.027
everal-0.025
 manoeuv-0.025
Downloadha-0.025
Token09
Token ID2931
Feature activation+6.58e-01

Pos logit contributions
llan+0.095
 Luthor+0.090
oid+0.088
exclusive+0.082
+0.081
Neg logit contributions
atorium-0.103
ratulations-0.096
everal-0.090
 manoeuv-0.090
acebook-0.087
Token-
Token ID12
Feature activation+4.21e-01

Pos logit contributions
llan+0.404
 Luthor+0.376
oid+0.365
+0.325
exclusive+0.323
Neg logit contributions
atorium-0.649
ratulations-0.618
everal-0.588
 manoeuv-0.572
acebook-0.571
Token Our
Token ID3954
Feature activation+2.11e-01

Pos logit contributions
atorium+0.086
ratulations+0.080
 manoeuv+0.076
Downloadha+0.073
 scrape+0.072
Neg logit contributions
llan-0.080
 Luthor-0.076
oid-0.073
-0.068
exclusive-0.067
Token Seas
Token ID32306
Feature activation+2.15e-01

Pos logit contributions
llan+0.173
 Luthor+0.165
oid+0.160
+0.148
exclusive+0.148
Neg logit contributions
atorium-0.163
ratulations-0.149
 manoeuv-0.142
Downloadha-0.137
 scrape-0.135
Token Foundation
Token ID5693
Feature activation-4.86e-01

Pos logit contributions
llan+0.169
 Luthor+0.159
oid+0.155
+0.145
exclusive+0.142
Neg logit contributions
atorium-0.172
ratulations-0.158
 manoeuv-0.150
Downloadha-0.148
 scrape-0.142
Token's
Token ID338
Feature activation+3.85e-01

Pos logit contributions
atorium+0.412
ratulations+0.374
 manoeuv+0.359
Downloadha+0.344
 scrape+0.343
Neg logit contributions
llan-0.362
 Luthor-0.344
oid-0.329
-0.309
exclusive-0.304
Token D
Token ID360
Feature activation-5.65e-02

Pos logit contributions
llan+0.304
 Luthor+0.289
oid+0.279
+0.259
exclusive+0.257
Neg logit contributions
atorium-0.308
ratulations-0.281
 manoeuv-0.265
Downloadha-0.260
 scrape-0.253
Token'
Token ID6
Feature activation+4.30e+00

Pos logit contributions
atorium+0.047
ratulations+0.042
 manoeuv+0.041
Downloadha+0.039
 scrape+0.039
Neg logit contributions
llan-0.043
 Luthor-0.041
oid-0.040
-0.037
essim-0.036
TokenAr
Token ID3163
Feature activation+2.92e+00

Pos logit contributions
llan+3.106
 Luthor+2.936
oid+2.892
exclusive+2.676
essim+2.615
Neg logit contributions
atorium-3.611
ratulations-3.329
 manoeuv-3.200
 scrape-3.115
acebook-3.060
Tokenros
Token ID4951
Feature activation+1.68e-01

Pos logit contributions
llan+2.087
 Luthor+1.921
oid+1.887
exclusive+1.730
+1.705
Neg logit contributions
atorium-2.563
ratulations-2.354
 manoeuv-2.260
 scrape-2.186
Downloadha-2.180
Token Research
Token ID4992
Feature activation-1.24e+00

Pos logit contributions
llan+0.131
 Luthor+0.124
oid+0.121
+0.113
exclusive+0.110
Neg logit contributions
atorium-0.136
ratulations-0.125
 manoeuv-0.117
Downloadha-0.115
 scrape-0.113
Token Centre
Token ID9072
Feature activation-1.93e+00

Pos logit contributions
atorium+1.109
ratulations+1.027
 manoeuv+0.980
Downloadha+0.962
 scrape+0.939
Neg logit contributions
llan-0.853
 Luthor-0.807
oid-0.771
-0.714
exclusive-0.700
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
atorium+1.654
ratulations+1.495
 manoeuv+1.438
 scrape+1.375
Downloadha+1.369
Neg logit contributions
llan-1.424
 Luthor-1.360
oid-1.292
-1.213
exclusive-1.199
Token board
Token ID3096
Feature activation+3.71e-01

Pos logit contributions
atorium+0.111
ratulations+0.098
 manoeuv+0.091
Downloadha+0.087
 scrape+0.086
Neg logit contributions
llan-0.172
 Luthor-0.166
oid-0.160
-0.152
exclusive-0.151
Token;
Token ID26
Feature activation-3.22e-02

Pos logit contributions
llan+0.238
 Luthor+0.224
oid+0.212
+0.197
exclusive+0.193
Neg logit contributions
atorium-0.354
ratulations-0.325
 manoeuv-0.313
Downloadha-0.302
 scrape-0.301
Token the
Token ID262
Feature activation-2.95e-01

Pos logit contributions
atorium+0.027
ratulations+0.025
 manoeuv+0.024
Downloadha+0.023
 scrape+0.023
Neg logit contributions
llan-0.024
 Luthor-0.023
oid-0.022
-0.020
exclusive-0.020
Token teen
Token ID6036
Feature activation-1.76e-01

Pos logit contributions
atorium+0.245
ratulations+0.223
 manoeuv+0.211
Downloadha+0.206
 scrape+0.201
Neg logit contributions
llan-0.227
 Luthor-0.217
oid-0.207
-0.193
exclusive-0.192
Token got
Token ID1392
Feature activation-8.83e-01

Pos logit contributions
atorium+0.151
ratulations+0.137
 manoeuv+0.131
Downloadha+0.127
 scrape+0.125
Neg logit contributions
llan-0.130
 Luthor-0.123
oid-0.118
-0.111
exclusive-0.109
Token stock
Token ID4283
Feature activation-5.12e+00

Pos logit contributions
atorium+0.748
ratulations+0.675
 manoeuv+0.646
Downloadha+0.629
 scrape+0.613
Neg logit contributions
llan-0.667
 Luthor-0.639
oid-0.604
-0.564
exclusive-0.564
Token options
Token ID3689
Feature activation-1.62e-01

Pos logit contributions
atorium+4.182
ratulations+3.796
 manoeuv+3.669
 scrape+3.484
 rese+3.451
Neg logit contributions
llan-3.893
 Luthor-3.629
oid-3.512
-3.340
essim-3.265
Token,
Token ID11
Feature activation+2.89e-02

Pos logit contributions
atorium+0.144
ratulations+0.131
 manoeuv+0.126
Downloadha+0.121
 scrape+0.120
Neg logit contributions
llan-0.115
 Luthor-0.109
oid-0.103
-0.096
exclusive-0.095
Token too
Token ID1165
Feature activation-8.04e-02

Pos logit contributions
llan+0.022
 Luthor+0.021
oid+0.019
exclusive+0.018
+0.018
Neg logit contributions
atorium-0.025
ratulations-0.022
 manoeuv-0.021
Downloadha-0.021
 scrape-0.020
Token.
Token ID13
Feature activation-3.02e-02

Pos logit contributions
atorium+0.066
ratulations+0.060
 manoeuv+0.058
 scrape+0.055
Downloadha+0.055
Neg logit contributions
llan-0.062
 Luthor-0.059
oid-0.056
-0.053
exclusive-0.052
Token
Token ID198
Feature activation+3.33e-01

Pos logit contributions
atorium+0.027
ratulations+0.025
 manoeuv+0.024
Downloadha+0.023
 scrape+0.023
Neg logit contributions
llan-0.021
 Luthor-0.021
oid-0.019
-0.018
exclusive-0.018
Token is
Token ID318
Feature activation-5.92e-01

Pos logit contributions
atorium+0.385
ratulations+0.352
 manoeuv+0.335
Downloadha+0.323
 scrape+0.320
Neg logit contributions
llan-0.315
 Luthor-0.300
oid-0.287
-0.266
exclusive-0.263
Token set
Token ID900
Feature activation+1.09e+00

Pos logit contributions
atorium+0.506
ratulations+0.463
 manoeuv+0.438
Downloadha+0.423
 scrape+0.421
Neg logit contributions
llan-0.438
 Luthor-0.418
oid-0.400
-0.372
exclusive-0.368
Token to
Token ID284
Feature activation-4.03e-01

Pos logit contributions
llan+0.758
 Luthor+0.717
oid+0.684
+0.634
exclusive+0.626
Neg logit contributions
atorium-0.991
ratulations-0.907
 manoeuv-0.864
Downloadha-0.833
 scrape-0.831
Token 0
Token ID657
Feature activation-8.07e-01

Pos logit contributions
atorium+0.326
ratulations+0.296
 manoeuv+0.279
Downloadha+0.271
acebook+0.265
Neg logit contributions
llan-0.319
 Luthor-0.304
oid-0.292
-0.271
exclusive-0.270
Token on
Token ID319
Feature activation-9.24e-01

Pos logit contributions
atorium+0.668
ratulations+0.605
 manoeuv+0.577
Downloadha+0.554
 scrape+0.550
Neg logit contributions
llan-0.623
 Luthor-0.591
oid-0.566
-0.532
exclusive-0.525
Token stock
Token ID4283
Feature activation-5.07e+00

Pos logit contributions
atorium+0.713
ratulations+0.640
 manoeuv+0.607
Downloadha+0.582
 scrape+0.577
Neg logit contributions
llan-0.764
 Luthor-0.731
oid-0.702
-0.659
exclusive-0.653
Token kernel
Token ID9720
Feature activation+2.62e-01

Pos logit contributions
atorium+4.479
ratulations+4.106
 manoeuv+3.997
Downloadha+3.831
 scrape+3.831
Neg logit contributions
llan-3.470
 Luthor-3.260
oid-3.077
-2.964
exclusive-2.885
Token.
Token ID13
Feature activation+2.79e-01

Pos logit contributions
llan+0.192
 Luthor+0.183
oid+0.176
+0.163
exclusive+0.162
Neg logit contributions
atorium-0.226
ratulations-0.205
 manoeuv-0.195
Downloadha-0.188
 scrape-0.187
Token The
Token ID383
Feature activation-4.84e-01

Pos logit contributions
llan+0.201
 Luthor+0.190
oid+0.183
+0.170
exclusive+0.168
Neg logit contributions
atorium-0.243
ratulations-0.222
 manoeuv-0.213
Downloadha-0.205
 scrape-0.204
Token kernel
Token ID9720
Feature activation+1.39e-01

Pos logit contributions
atorium+0.417
ratulations+0.380
 manoeuv+0.363
Downloadha+0.350
 scrape+0.347
Neg logit contributions
llan-0.355
 Luthor-0.337
oid-0.323
-0.301
exclusive-0.297
Token is
Token ID318
Feature activation+2.21e-01

Pos logit contributions
llan+0.107
 Luthor+0.102
oid+0.098
+0.092
exclusive+0.091
Neg logit contributions
atorium-0.114
ratulations-0.103
 manoeuv-0.098
Downloadha-0.095
 scrape-0.094
Token!
Token ID0
Feature activation+1.08e+00

Pos logit contributions
atorium+0.340
ratulations+0.309
 manoeuv+0.295
Downloadha+0.284
 scrape+0.283
Neg logit contributions
llan-0.289
 Luthor-0.274
oid-0.262
-0.246
exclusive-0.242
Token Let
Token ID3914
Feature activation-3.79e-01

Pos logit contributions
llan+0.753
 Luthor+0.718
oid+0.680
+0.637
exclusive+0.617
Neg logit contributions
atorium-0.976
ratulations-0.901
 manoeuv-0.850
Downloadha-0.827
everal-0.823
Token
Token ID447
Feature activation+6.31e-01

Pos logit contributions
atorium+0.307
ratulations+0.277
 manoeuv+0.266
 scrape+0.254
Downloadha+0.253
Neg logit contributions
llan-0.297
 Luthor-0.283
oid-0.270
-0.254
exclusive-0.252
Token
Token ID247
Feature activation+3.61e-01

Pos logit contributions
llan+0.376
 Luthor+0.351
oid+0.329
+0.304
exclusive+0.293
Neg logit contributions
atorium-0.633
ratulations-0.591
 manoeuv-0.567
Downloadha-0.552
acebook-0.547
Tokens
Token ID82
Feature activation-2.51e-01

Pos logit contributions
llan+0.180
 Luthor+0.167
oid+0.155
+0.140
exclusive+0.137
Neg logit contributions
atorium-0.395
ratulations-0.367
 manoeuv-0.356
 scrape-0.345
Downloadha-0.344
Token try
Token ID1949
Feature activation-5.01e+00

Pos logit contributions
atorium+0.204
ratulations+0.185
Downloadha+0.172
 manoeuv+0.169
everal+0.168
Neg logit contributions
llan-0.200
 Luthor-0.191
oid-0.182
-0.171
essim-0.166
Token to
Token ID284
Feature activation-7.65e-01

Pos logit contributions
atorium+4.099
ratulations+3.731
 manoeuv+3.619
 scrape+3.452
Downloadha+3.410
Neg logit contributions
llan-3.797
 Luthor-3.590
oid-3.442
-3.250
exclusive-3.233
Token power
Token ID1176
Feature activation-1.48e+00

Pos logit contributions
atorium+0.620
ratulations+0.560
Downloadha+0.521
 manoeuv+0.514
acebook+0.508
Neg logit contributions
llan-0.610
 Luthor-0.584
oid-0.558
-0.523
essim-0.508
Token management
Token ID4542
Feature activation+1.60e-01

Pos logit contributions
atorium+1.197
ratulations+1.082
 manoeuv+1.033
Downloadha+0.989
 scrape+0.986
Neg logit contributions
llan-1.159
 Luthor-1.104
oid-1.058
-0.996
exclusive-0.982
Token.
Token ID13
Feature activation+2.46e-01

Pos logit contributions
llan+0.117
 Luthor+0.110
oid+0.106
+0.098
exclusive+0.096
Neg logit contributions
atorium-0.140
ratulations-0.128
 manoeuv-0.121
Downloadha-0.119
 scrape-0.116
Token
Token ID198
Feature activation-2.36e-01

Pos logit contributions
llan+0.179
 Luthor+0.170
oid+0.162
+0.152
exclusive+0.149
Neg logit contributions
atorium-0.215
ratulations-0.196
 manoeuv-0.187
Downloadha-0.180
 scrape-0.179
Token.
Token ID13
Feature activation-1.71e-01

Pos logit contributions
atorium+0.660
ratulations+0.601
 manoeuv+0.572
Downloadha+0.553
 scrape+0.546
Neg logit contributions
llan-0.589
 Luthor-0.559
oid-0.536
-0.499
exclusive-0.492
Token Let
Token ID3914
Feature activation-1.13e-01

Pos logit contributions
atorium+0.154
ratulations+0.142
 manoeuv+0.135
Downloadha+0.131
 scrape+0.129
Neg logit contributions
llan-0.120
 Luthor-0.114
oid-0.108
-0.101
exclusive-0.099
Token
Token ID447
Feature activation+4.72e-01

Pos logit contributions
atorium+0.094
ratulations+0.085
 manoeuv+0.081
 scrape+0.078
Downloadha+0.077
Neg logit contributions
llan-0.087
 Luthor-0.083
oid-0.079
-0.074
exclusive-0.073
Token
Token ID247
Feature activation+3.83e-01

Pos logit contributions
llan+0.284
 Luthor+0.266
oid+0.250
+0.231
exclusive+0.224
Neg logit contributions
atorium-0.471
ratulations-0.438
 manoeuv-0.422
Downloadha-0.409
acebook-0.404
Tokens
Token ID82
Feature activation-1.25e-01

Pos logit contributions
llan+0.187
 Luthor+0.172
oid+0.161
+0.145
exclusive+0.141
Neg logit contributions
atorium-0.424
ratulations-0.395
 manoeuv-0.382
Downloadha-0.372
 scrape-0.369
Token try
Token ID1949
Feature activation-4.96e+00

Pos logit contributions
atorium+0.102
ratulations+0.093
Downloadha+0.087
 manoeuv+0.085
everal+0.085
Neg logit contributions
llan-0.098
 Luthor-0.093
oid-0.090
-0.084
exclusive-0.081
Token listening
Token ID8680
Feature activation+1.16e+00

Pos logit contributions
atorium+4.046
ratulations+3.667
 manoeuv+3.562
 scrape+3.403
Downloadha+3.336
Neg logit contributions
llan-3.770
 Luthor-3.580
oid-3.402
-3.232
exclusive-3.222
Token to
Token ID284
Feature activation+9.95e-02

Pos logit contributions
llan+0.796
 Luthor+0.748
oid+0.719
+0.665
exclusive+0.651
Neg logit contributions
atorium-1.055
ratulations-0.968
 manoeuv-0.927
Downloadha-0.901
 scrape-0.889
Token its
Token ID663
Feature activation-1.05e+00

Pos logit contributions
llan+0.076
 Luthor+0.073
oid+0.070
+0.065
exclusive+0.064
Neg logit contributions
atorium-0.082
ratulations-0.075
 manoeuv-0.071
Downloadha-0.069
 scrape-0.068
Token suggestion
Token ID13052
Feature activation+1.33e+00

Pos logit contributions
atorium+0.837
ratulations+0.758
 manoeuv+0.716
Downloadha+0.693
 scrape+0.683
Neg logit contributions
llan-0.837
 Luthor-0.802
oid-0.769
-0.721
exclusive-0.714
Token,
Token ID11
Feature activation+3.57e-01

Pos logit contributions
llan+0.945
 Luthor+0.889
oid+0.861
+0.792
essim+0.772
Neg logit contributions
atorium-1.179
ratulations-1.086
 manoeuv-1.031
Downloadha-1.004
 scrape-0.984
Token have
Token ID423
Feature activation+1.69e-01

Pos logit contributions
llan+0.149
 Luthor+0.143
oid+0.137
+0.128
exclusive+0.127
Neg logit contributions
atorium-0.146
ratulations-0.134
 manoeuv-0.125
Downloadha-0.123
acebook-0.119
Token the
Token ID262
Feature activation+1.38e-01

Pos logit contributions
llan+0.132
 Luthor+0.127
oid+0.121
+0.113
exclusive+0.112
Neg logit contributions
atorium-0.138
ratulations-0.125
 manoeuv-0.119
Downloadha-0.114
 scrape-0.114
Token Nexus
Token ID16756
Feature activation+8.51e-01

Pos logit contributions
llan+0.109
 Luthor+0.104
oid+0.100
+0.093
exclusive+0.093
Neg logit contributions
atorium-0.111
ratulations-0.101
 manoeuv-0.096
Downloadha-0.092
 scrape-0.091
Token 6
Token ID718
Feature activation+2.32e+00

Pos logit contributions
llan+0.738
 Luthor+0.709
oid+0.684
+0.644
exclusive+0.639
Neg logit contributions
atorium-0.617
ratulations-0.556
 manoeuv-0.520
Downloadha-0.501
 scrape-0.494
Token in
Token ID287
Feature activation-3.53e-02

Pos logit contributions
llan+1.726
 Luthor+1.630
oid+1.583
exclusive+1.465
+1.459
Neg logit contributions
atorium-1.983
ratulations-1.813
 manoeuv-1.700
Downloadha-1.653
brance-1.623
Token Stock
Token ID10500
Feature activation-4.94e+00

Pos logit contributions
atorium+0.028
ratulations+0.026
 manoeuv+0.025
Downloadha+0.024
 scrape+0.023
Neg logit contributions
llan-0.028
 Luthor-0.027
oid-0.025
-0.024
exclusive-0.024
Token on
Token ID319
Feature activation+6.03e-01

Pos logit contributions
atorium+4.070
ratulations+3.682
 manoeuv+3.556
 scrape+3.408
Downloadha+3.383
Neg logit contributions
llan-3.737
 Luthor-3.521
oid-3.365
-3.218
exclusive-3.140
Token Nov
Token ID5267
Feature activation+4.83e-01

Pos logit contributions
llan+0.483
 Luthor+0.465
oid+0.445
+0.414
exclusive+0.412
Neg logit contributions
atorium-0.481
ratulations-0.438
 manoeuv-0.411
Downloadha-0.394
 scrape-0.392
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
llan+0.372
 Luthor+0.354
oid+0.344
+0.316
exclusive+0.315
Neg logit contributions
atorium-0.396
ratulations-0.363
 manoeuv-0.346
Downloadha-0.332
 scrape-0.331
Token 21
Token ID2310
Feature activation-7.11e-01

Pos logit contributions
atorium+0.229
ratulations+0.212
 manoeuv+0.198
everal+0.192
Downloadha+0.189
Neg logit contributions
llan-0.237
 Luthor-0.228
oid-0.218
-0.203
exclusive-0.202
Tokenst
Token ID301
Feature activation+4.60e-01

Pos logit contributions
atorium+0.606
ratulations+0.551
 manoeuv+0.528
Downloadha+0.506
 scrape+0.506
Neg logit contributions
llan-0.527
 Luthor-0.500
oid-0.477
-0.449
exclusive-0.441
Token my
Token ID616
Feature activation-5.74e-01

Pos logit contributions
atorium+0.682
ratulations+0.588
 manoeuv+0.547
Downloadha+0.511
 scrape+0.509
Neg logit contributions
llan-1.257
 Luthor-1.212
oid-1.173
-1.123
exclusive-1.108
Token life
Token ID1204
Feature activation-1.00e+00

Pos logit contributions
atorium+0.455
ratulations+0.413
 manoeuv+0.392
Downloadha+0.378
 scrape+0.373
Neg logit contributions
llan-0.461
 Luthor-0.439
oid-0.422
-0.398
exclusive-0.390
Token.
Token ID13
Feature activation-5.58e-01

Pos logit contributions
atorium+0.823
ratulations+0.744
 manoeuv+0.713
 scrape+0.681
Downloadha+0.680
Neg logit contributions
llan-0.772
 Luthor-0.736
oid-0.703
-0.661
exclusive-0.654
Token I
Token ID314
Feature activation-2.64e-01

Pos logit contributions
atorium+0.480
ratulations+0.440
 manoeuv+0.420
Downloadha+0.402
 scrape+0.401
Neg logit contributions
llan-0.411
 Luthor-0.391
oid-0.373
-0.350
exclusive-0.344
Token will
Token ID481
Feature activation-1.12e+00

Pos logit contributions
atorium+0.224
ratulations+0.204
 manoeuv+0.194
Downloadha+0.189
acebook+0.184
Neg logit contributions
llan-0.199
 Luthor-0.188
oid-0.180
-0.169
exclusive-0.165
Token try
Token ID1949
Feature activation-4.87e+00

Pos logit contributions
atorium+1.044
ratulations+0.965
 manoeuv+0.915
Downloadha+0.895
acebook+0.877
Neg logit contributions
llan-0.752
 Luthor-0.710
oid-0.671
-0.627
exclusive-0.615
Token to
Token ID284
Feature activation-1.03e+00

Pos logit contributions
atorium+3.904
ratulations+3.502
 manoeuv+3.398
 scrape+3.249
Downloadha+3.208
Neg logit contributions
llan-3.714
 Luthor-3.580
oid-3.401
exclusive-3.231
-3.209
Token start
Token ID923
Feature activation-2.16e-02

Pos logit contributions
atorium+0.853
ratulations+0.778
 manoeuv+0.724
Downloadha+0.721
acebook+0.704
Neg logit contributions
llan-0.803
 Luthor-0.761
oid-0.735
-0.681
exclusive-0.668
Token to
Token ID284
Feature activation-3.86e-02

Pos logit contributions
atorium+0.017
ratulations+0.016
 manoeuv+0.015
Downloadha+0.014
 scrape+0.014
Neg logit contributions
llan-0.017
 Luthor-0.016
oid-0.016
-0.015
essim-0.015
Token find
Token ID1064
Feature activation+5.15e-01

Pos logit contributions
atorium+0.033
ratulations+0.030
Downloadha+0.028
 manoeuv+0.028
everal+0.027
Neg logit contributions
llan-0.029
 Luthor-0.028
oid-0.027
-0.025
essim-0.024
Token the
Token ID262
Feature activation-4.40e-01

Pos logit contributions
llan+0.424
 Luthor+0.405
oid+0.389
+0.365
essim+0.359
Neg logit contributions
atorium-0.400
ratulations-0.359
 manoeuv-0.340
Downloadha-0.328
 scrape-0.322
Token error
Token ID4049
Feature activation-1.07e+00

Pos logit contributions
atorium+1.562
ratulations+1.444
 manoeuv+1.388
Downloadha+1.348
 scrape+1.342
Neg logit contributions
llan-0.910
 Luthor-0.853
oid-0.810
-0.736
exclusive-0.730
Token has
Token ID468
Feature activation-1.89e+00

Pos logit contributions
atorium+0.966
ratulations+0.889
 manoeuv+0.842
Downloadha+0.820
 scrape+0.813
Neg logit contributions
llan-0.749
 Luthor-0.709
oid-0.684
-0.625
exclusive-0.621
Token occurred
Token ID5091
Feature activation-1.07e+00

Pos logit contributions
atorium+1.526
ratulations+1.399
 manoeuv+1.309
Downloadha+1.267
 scrape+1.263
Neg logit contributions
llan-1.501
 Luthor-1.431
oid-1.384
-1.270
exclusive-1.270
Token.
Token ID13
Feature activation-1.86e+00

Pos logit contributions
atorium+0.939
ratulations+0.873
everal+0.818
 manoeuv+0.813
Downloadha+0.802
Neg logit contributions
llan-0.781
 Luthor-0.738
oid-0.715
-0.651
exclusive-0.643
Token Please
Token ID4222
Feature activation-2.65e+00

Pos logit contributions
atorium+1.428
ratulations+1.314
 manoeuv+1.221
everal+1.205
Downloadha+1.186
Neg logit contributions
llan-1.547
 Luthor-1.487
oid-1.428
-1.337
exclusive-1.319
Token try
Token ID1949
Feature activation-4.82e+00

Pos logit contributions
atorium+1.405
ratulations+1.221
 manoeuv+1.094
Downloadha+1.054
everal+1.037
Neg logit contributions
llan-2.845
 Luthor-2.731
oid-2.667
-2.538
exclusive-2.504
Token again
Token ID757
Feature activation-7.61e-01

Pos logit contributions
atorium+3.282
ratulations+2.846
 manoeuv+2.783
 scrape+2.595
Downloadha+2.568
Neg logit contributions
llan-4.344
 Luthor-4.205
oid-4.028
-3.870
exclusive-3.820
Token later
Token ID1568
Feature activation-9.04e-01

Pos logit contributions
atorium+0.543
ratulations+0.490
everal+0.449
 manoeuv+0.446
Downloadha+0.445
Neg logit contributions
llan-0.678
 Luthor-0.643
oid-0.625
-0.586
exclusive-0.574
Token.
Token ID13
Feature activation-1.85e+00

Pos logit contributions
atorium+0.771
ratulations+0.714
 manoeuv+0.671
everal+0.659
Downloadha+0.656
Neg logit contributions
llan-0.678
 Luthor-0.640
oid-0.615
-0.572
exclusive-0.563
Token View
Token ID3582
Feature activation-1.14e+00

Pos logit contributions
atorium+1.451
ratulations+1.320
 manoeuv+1.251
Downloadha+1.196
 scrape+1.193
Neg logit contributions
llan-1.498
 Luthor-1.430
oid-1.370
-1.291
exclusive-1.271
Token all
Token ID477
Feature activation-8.11e-01

Pos logit contributions
atorium+0.970
ratulations+0.896
 manoeuv+0.832
everal+0.826
Downloadha+0.822
Neg logit contributions
llan-0.858
 Luthor-0.812
oid-0.786
-0.718
exclusive-0.712
Token the
Token ID262
Feature activation-1.15e-01

Pos logit contributions
llan+0.701
 Luthor+0.670
oid+0.647
exclusive+0.601
+0.600
Neg logit contributions
atorium-0.659
ratulations-0.591
 manoeuv-0.554
Downloadha-0.538
 scrape-0.528
Token level
Token ID1241
Feature activation-1.10e+00

Pos logit contributions
atorium+0.094
ratulations+0.087
 manoeuv+0.081
Downloadha+0.079
 scrape+0.077
Neg logit contributions
llan-0.089
 Luthor-0.085
oid-0.082
exclusive-0.075
-0.075
Token at
Token ID379
Feature activation-4.14e-01

Pos logit contributions
atorium+0.946
ratulations+0.860
 manoeuv+0.822
Downloadha+0.791
 scrape+0.787
Neg logit contributions
llan-0.815
 Luthor-0.773
oid-0.739
-0.690
exclusive-0.681
Token which
Token ID543
Feature activation+5.42e-01

Pos logit contributions
atorium+0.355
ratulations+0.323
 manoeuv+0.306
Downloadha+0.296
 scrape+0.294
Neg logit contributions
llan-0.308
 Luthor-0.292
oid-0.280
-0.261
exclusive-0.259
Token Yahoo
Token ID16551
Feature activation-1.68e+00

Pos logit contributions
llan+0.440
 Luthor+0.420
oid+0.403
+0.377
exclusive+0.374
Neg logit contributions
atorium-0.426
ratulations-0.383
 manoeuv-0.363
Downloadha-0.350
 scrape-0.347
Token stock
Token ID4283
Feature activation-4.82e+00

Pos logit contributions
atorium+1.458
ratulations+1.333
 manoeuv+1.263
Downloadha+1.230
 scrape+1.216
Neg logit contributions
llan-1.226
 Luthor-1.163
oid-1.113
-1.034
exclusive-1.022
Token was
Token ID373
Feature activation+4.17e-01

Pos logit contributions
atorium+3.925
ratulations+3.462
 manoeuv+3.451
 scrape+3.243
 rese+3.232
Neg logit contributions
llan-3.702
 Luthor-3.499
oid-3.309
-3.196
essim-3.117
Token trading
Token ID7313
Feature activation-5.74e-01

Pos logit contributions
llan+0.290
 Luthor+0.277
oid+0.263
+0.243
exclusive+0.240
Neg logit contributions
atorium-0.376
ratulations-0.345
Downloadha-0.322
 manoeuv-0.322
everal-0.313
Token when
Token ID618
Feature activation+6.51e-01

Pos logit contributions
atorium+0.490
ratulations+0.446
 manoeuv+0.427
Downloadha+0.410
 scrape+0.409
Neg logit contributions
llan-0.425
 Luthor-0.404
oid-0.386
-0.361
exclusive-0.356
Token the
Token ID262
Feature activation-1.99e-02

Pos logit contributions
llan+0.492
 Luthor+0.467
oid+0.447
+0.416
exclusive+0.412
Neg logit contributions
atorium-0.549
ratulations-0.497
 manoeuv-0.472
Downloadha-0.458
 scrape-0.454
Token bid
Token ID8406
Feature activation+8.57e-02

Pos logit contributions
atorium+0.016
ratulations+0.014
 manoeuv+0.013
Downloadha+0.013
brance+0.013
Neg logit contributions
llan-0.016
 Luthor-0.016
oid-0.015
exclusive-0.014
-0.014
Token error
Token ID4049
Feature activation-1.19e+00

Pos logit contributions
atorium+1.370
ratulations+1.266
 manoeuv+1.218
Downloadha+1.181
 scrape+1.176
Neg logit contributions
llan-0.803
 Luthor-0.753
oid-0.714
-0.651
exclusive-0.644
Token has
Token ID468
Feature activation-2.00e+00

Pos logit contributions
atorium+1.062
ratulations+0.975
 manoeuv+0.926
Downloadha+0.899
 scrape+0.893
Neg logit contributions
llan-0.832
 Luthor-0.788
oid-0.759
-0.697
exclusive-0.691
Token occurred
Token ID5091
Feature activation-9.11e-01

Pos logit contributions
atorium+1.606
ratulations+1.467
 manoeuv+1.378
Downloadha+1.330
 scrape+1.326
Neg logit contributions
llan-1.599
 Luthor-1.525
oid-1.473
-1.358
exclusive-1.355
Token.
Token ID13
Feature activation-2.12e+00

Pos logit contributions
atorium+0.801
ratulations+0.745
everal+0.699
 manoeuv+0.692
Downloadha+0.684
Neg logit contributions
llan-0.664
 Luthor-0.626
oid-0.608
-0.552
exclusive-0.545
Token Please
Token ID4222
Feature activation-2.75e+00

Pos logit contributions
atorium+1.608
ratulations+1.471
 manoeuv+1.372
everal+1.334
Downloadha+1.327
Neg logit contributions
llan-1.789
 Luthor-1.719
oid-1.651
-1.552
exclusive-1.530
Token try
Token ID1949
Feature activation-4.82e+00

Pos logit contributions
atorium+1.438
ratulations+1.244
 manoeuv+1.120
Downloadha+1.070
acebook+1.047
Neg logit contributions
llan-2.961
 Luthor-2.848
oid-2.777
-2.646
exclusive-2.612
Token again
Token ID757
Feature activation-6.57e-01

Pos logit contributions
atorium+3.281
ratulations+2.845
 manoeuv+2.782
 scrape+2.594
Downloadha+2.569
Neg logit contributions
llan-4.338
 Luthor-4.197
oid-4.021
-3.860
exclusive-3.814
Token later
Token ID1568
Feature activation-7.15e-01

Pos logit contributions
atorium+0.467
ratulations+0.421
 manoeuv+0.385
everal+0.384
Downloadha+0.381
Neg logit contributions
llan-0.587
 Luthor-0.558
oid-0.541
-0.509
exclusive-0.498
Token.
Token ID13
Feature activation-2.02e+00

Pos logit contributions
atorium+0.611
ratulations+0.567
 manoeuv+0.532
everal+0.524
Downloadha+0.521
Neg logit contributions
llan-0.535
 Luthor-0.505
oid-0.486
-0.451
exclusive-0.444
Token View
Token ID3582
Feature activation-1.20e+00

Pos logit contributions
atorium+1.586
ratulations+1.440
 manoeuv+1.367
Downloadha+1.305
 scrape+1.303
Neg logit contributions
llan-1.641
 Luthor-1.565
oid-1.500
-1.414
exclusive-1.392
Token all
Token ID477
Feature activation-8.41e-01

Pos logit contributions
atorium+1.023
ratulations+0.944
 manoeuv+0.877
everal+0.869
Downloadha+0.865
Neg logit contributions
llan-0.908
 Luthor-0.859
oid-0.832
-0.760
exclusive-0.754
Token Maybe
Token ID6674
Feature activation+9.10e-01

Pos logit contributions
llan+0.117
 Luthor+0.112
oid+0.106
+0.098
exclusive+0.096
Neg logit contributions
atorium-0.160
ratulations-0.150
 manoeuv-0.143
Downloadha-0.138
everal-0.138
Token you
Token ID345
Feature activation+8.05e-01

Pos logit contributions
llan+0.621
 Luthor+0.595
oid+0.562
+0.519
exclusive+0.506
Neg logit contributions
atorium-0.829
ratulations-0.756
 manoeuv-0.723
Downloadha-0.705
 scrape-0.691
Token acted
Token ID13134
Feature activation+4.30e-01

Pos logit contributions
llan+0.576
 Luthor+0.552
oid+0.526
+0.477
exclusive+0.470
Neg logit contributions
atorium-0.710
ratulations-0.651
Downloadha-0.611
 manoeuv-0.604
everal-0.593
Token on
Token ID319
Feature activation+7.91e-01

Pos logit contributions
llan+0.301
 Luthor+0.289
oid+0.273
+0.254
exclusive+0.248
Neg logit contributions
atorium-0.387
ratulations-0.352
 manoeuv-0.334
Downloadha-0.327
 scrape-0.321
Token a
Token ID257
Feature activation+6.22e-01

Pos logit contributions
llan+0.591
 Luthor+0.570
oid+0.543
+0.504
exclusive+0.494
Neg logit contributions
atorium-0.671
ratulations-0.608
 manoeuv-0.573
Downloadha-0.561
 scrape-0.550
Token stock
Token ID4283
Feature activation-4.79e+00

Pos logit contributions
llan+0.470
 Luthor+0.455
oid+0.430
+0.400
exclusive+0.392
Neg logit contributions
atorium-0.525
ratulations-0.480
 manoeuv-0.446
Downloadha-0.441
ochet-0.425
Token tip
Token ID8171
Feature activation+2.70e+00

Pos logit contributions
atorium+3.787
ratulations+3.387
 manoeuv+3.349
 scrape+3.213
 rese+3.092
Neg logit contributions
llan-3.754
 Luthor-3.498
oid-3.345
-3.190
exclusive-3.184
Token that
Token ID326
Feature activation+6.85e-01

Pos logit contributions
llan+1.850
 Luthor+1.759
oid+1.697
+1.541
exclusive+1.503
Neg logit contributions
atorium-2.455
ratulations-2.231
 manoeuv-2.129
Downloadha-2.111
everal-2.047
Token was
Token ID373
Feature activation+7.47e-01

Pos logit contributions
llan+0.473
 Luthor+0.460
oid+0.436
+0.399
exclusive+0.389
Neg logit contributions
atorium-0.619
ratulations-0.565
 manoeuv-0.533
Downloadha-0.527
everal-0.513
Token slightly
Token ID4622
Feature activation+1.63e+00

Pos logit contributions
llan+0.527
 Luthor+0.508
oid+0.480
+0.445
exclusive+0.435
Neg logit contributions
atorium-0.666
ratulations-0.606
 manoeuv-0.574
Downloadha-0.565
brance-0.553
Token too
Token ID1165
Feature activation+8.51e-01

Pos logit contributions
llan+1.140
 Luthor+1.102
oid+1.046
+0.967
exclusive+0.943
Neg logit contributions
atorium-1.452
ratulations-1.329
 manoeuv-1.246
Downloadha-1.230
brance-1.206
Token error
Token ID4049
Feature activation-1.13e+00

Pos logit contributions
atorium+1.364
ratulations+1.261
 manoeuv+1.213
Downloadha+1.177
 scrape+1.172
Neg logit contributions
llan-0.794
 Luthor-0.745
oid-0.707
-0.643
exclusive-0.637
Token has
Token ID468
Feature activation-1.89e+00

Pos logit contributions
atorium+1.014
ratulations+0.932
 manoeuv+0.884
Downloadha+0.859
 scrape+0.853
Neg logit contributions
llan-0.792
 Luthor-0.751
oid-0.723
-0.664
exclusive-0.658
Token occurred
Token ID5091
Feature activation-9.42e-01

Pos logit contributions
atorium+1.522
ratulations+1.392
 manoeuv+1.307
Downloadha+1.262
 scrape+1.258
Neg logit contributions
llan-1.507
 Luthor-1.437
oid-1.390
-1.279
exclusive-1.277
Token.
Token ID13
Feature activation-1.98e+00

Pos logit contributions
atorium+0.826
ratulations+0.768
everal+0.721
 manoeuv+0.715
Downloadha+0.706
Neg logit contributions
llan-0.688
 Luthor-0.649
oid-0.630
-0.573
exclusive-0.566
Token Please
Token ID4222
Feature activation-2.66e+00

Pos logit contributions
atorium+1.505
ratulations+1.378
 manoeuv+1.286
everal+1.254
Downloadha+1.244
Neg logit contributions
llan-1.670
 Luthor-1.603
oid-1.541
-1.448
exclusive-1.426
Token try
Token ID1949
Feature activation-4.77e+00

Pos logit contributions
atorium+1.388
ratulations+1.199
 manoeuv+1.082
Downloadha+1.030
acebook+1.008
Neg logit contributions
llan-2.871
 Luthor-2.762
oid-2.693
-2.567
exclusive-2.535
Token again
Token ID757
Feature activation-6.70e-01

Pos logit contributions
atorium+3.248
ratulations+2.816
 manoeuv+2.754
 scrape+2.569
Downloadha+2.543
Neg logit contributions
llan-4.296
 Luthor-4.157
oid-3.982
-3.821
exclusive-3.777
Token later
Token ID1568
Feature activation-7.76e-01

Pos logit contributions
atorium+0.474
ratulations+0.427
 manoeuv+0.391
everal+0.390
Downloadha+0.388
Neg logit contributions
llan-0.599
 Luthor-0.569
oid-0.552
-0.519
exclusive-0.509
Token.
Token ID13
Feature activation-1.82e+00

Pos logit contributions
atorium+0.662
ratulations+0.615
 manoeuv+0.577
everal+0.569
Downloadha+0.564
Neg logit contributions
llan-0.581
 Luthor-0.549
oid-0.528
-0.490
exclusive-0.483
Token View
Token ID3582
Feature activation-1.06e+00

Pos logit contributions
atorium+1.436
ratulations+1.307
 manoeuv+1.239
Downloadha+1.184
 scrape+1.182
Neg logit contributions
llan-1.473
 Luthor-1.404
oid-1.346
-1.268
exclusive-1.247
Token all
Token ID477
Feature activation-7.50e-01

Pos logit contributions
atorium+0.906
ratulations+0.837
 manoeuv+0.777
everal+0.773
Downloadha+0.768
Neg logit contributions
llan-0.800
 Luthor-0.756
oid-0.733
-0.668
exclusive-0.663
Token To
Token ID1675
Feature activation-7.61e-01

Pos logit contributions
llan+0.305
 Luthor+0.289
oid+0.277
+0.259
exclusive+0.254
Neg logit contributions
atorium-0.374
ratulations-0.343
 manoeuv-0.328
Downloadha-0.315
 scrape-0.313
Token start
Token ID923
Feature activation+8.03e-01

Pos logit contributions
atorium+0.626
ratulations+0.570
 manoeuv+0.535
Downloadha+0.526
acebook+0.514
Neg logit contributions
llan-0.593
 Luthor-0.566
oid-0.547
-0.513
exclusive-0.496
Token,
Token ID11
Feature activation+5.26e-01

Pos logit contributions
llan+0.568
 Luthor+0.540
oid+0.519
+0.481
exclusive+0.470
Neg logit contributions
atorium-0.712
ratulations-0.650
 manoeuv-0.620
Downloadha-0.600
 scrape-0.593
Token I
Token ID314
Feature activation+2.26e-01

Pos logit contributions
llan+0.341
 Luthor+0.322
oid+0.306
+0.283
exclusive+0.276
Neg logit contributions
atorium-0.500
ratulations-0.459
 manoeuv-0.439
Downloadha-0.427
everal-0.420
Token will
Token ID481
Feature activation-1.08e+00

Pos logit contributions
llan+0.178
 Luthor+0.168
oid+0.163
+0.153
exclusive+0.150
Neg logit contributions
atorium-0.184
ratulations-0.168
 manoeuv-0.158
Downloadha-0.153
acebook-0.151
Token try
Token ID1949
Feature activation-4.74e+00

Pos logit contributions
atorium+0.855
ratulations+0.782
 manoeuv+0.730
Downloadha+0.720
acebook+0.708
Neg logit contributions
llan-0.876
 Luthor-0.835
oid-0.803
-0.754
exclusive-0.741
Token to
Token ID284
Feature activation-7.79e-01

Pos logit contributions
atorium+3.884
ratulations+3.476
 manoeuv+3.411
 scrape+3.310
Downloadha+3.231
Neg logit contributions
llan-3.567
 Luthor-3.380
oid-3.193
exclusive-3.029
-3.017
Token use
Token ID779
Feature activation-1.07e+00

Pos logit contributions
atorium+0.626
ratulations+0.571
 manoeuv+0.529
Downloadha+0.528
acebook+0.518
Neg logit contributions
llan-0.621
 Luthor-0.592
oid-0.573
-0.534
exclusive-0.520
Token an
Token ID281
Feature activation-4.36e-01

Pos logit contributions
atorium+0.860
ratulations+0.778
 manoeuv+0.742
Downloadha+0.710
 scrape+0.707
Neg logit contributions
llan-0.842
 Luthor-0.803
oid-0.770
-0.724
exclusive-0.714
Token approach
Token ID3164
Feature activation-9.64e-02

Pos logit contributions
atorium+0.354
ratulations+0.321
 manoeuv+0.305
Downloadha+0.292
 scrape+0.290
Neg logit contributions
llan-0.339
 Luthor-0.325
oid-0.315
-0.293
exclusive-0.291
Token similar
Token ID2092
Feature activation+1.37e+00

Pos logit contributions
atorium+0.089
ratulations+0.081
 manoeuv+0.078
Downloadha+0.075
 scrape+0.075
Neg logit contributions
llan-0.065
 Luthor-0.061
oid-0.059
-0.054
exclusive-0.053
Token games
Token ID1830
Feature activation+4.82e-01

Pos logit contributions
llan+0.353
 Luthor+0.339
oid+0.326
exclusive+0.304
+0.304
Neg logit contributions
atorium-0.335
ratulations-0.302
 manoeuv-0.282
Downloadha-0.274
brance-0.269
Token,
Token ID11
Feature activation+3.11e-01

Pos logit contributions
llan+0.352
 Luthor+0.334
oid+0.321
+0.298
exclusive+0.295
Neg logit contributions
atorium-0.418
ratulations-0.383
 manoeuv-0.364
Downloadha-0.352
 scrape-0.348
Token but
Token ID475
Feature activation-1.21e-01

Pos logit contributions
llan+0.227
 Luthor+0.218
oid+0.207
+0.193
exclusive+0.192
Neg logit contributions
atorium-0.269
ratulations-0.246
 manoeuv-0.233
Downloadha-0.225
everal-0.222
Token I
Token ID314
Feature activation-1.69e-01

Pos logit contributions
atorium+0.105
ratulations+0.096
 manoeuv+0.091
Downloadha+0.089
acebook+0.086
Neg logit contributions
llan-0.088
 Luthor-0.085
oid-0.080
-0.074
exclusive-0.073
Token can
Token ID460
Feature activation-1.15e+00

Pos logit contributions
atorium+0.145
ratulations+0.131
 manoeuv+0.123
Downloadha+0.123
acebook+0.119
Neg logit contributions
llan-0.126
 Luthor-0.121
oid-0.116
-0.105
exclusive-0.105
Token try
Token ID1949
Feature activation-4.73e+00

Pos logit contributions
atorium+0.946
ratulations+0.858
 manoeuv+0.808
Downloadha+0.801
acebook+0.779
Neg logit contributions
llan-0.890
 Luthor-0.853
oid-0.818
-0.762
exclusive-0.750
Token to
Token ID284
Feature activation-1.07e+00

Pos logit contributions
atorium+3.967
ratulations+3.583
 manoeuv+3.461
 scrape+3.328
Downloadha+3.285
Neg logit contributions
llan-3.545
 Luthor-3.347
oid-3.198
-3.022
exclusive-2.979
Token get
Token ID651
Feature activation-7.39e-01

Pos logit contributions
atorium+0.850
ratulations+0.775
Downloadha+0.723
 manoeuv+0.719
acebook+0.699
Neg logit contributions
llan-0.851
 Luthor-0.817
oid-0.792
-0.731
exclusive-0.721
Token some
Token ID617
Feature activation-7.04e-01

Pos logit contributions
atorium+0.588
ratulations+0.532
 manoeuv+0.504
Downloadha+0.489
 scrape+0.477
Neg logit contributions
llan-0.590
 Luthor-0.566
oid-0.543
-0.508
exclusive-0.505
Token recorded
Token ID6264
Feature activation-9.20e-01

Pos logit contributions
atorium+0.599
ratulations+0.547
 manoeuv+0.520
Downloadha+0.505
 scrape+0.493
Neg logit contributions
llan-0.523
 Luthor-0.500
oid-0.477
-0.445
exclusive-0.441
Token within
Token ID1626
Feature activation+7.88e-03

Pos logit contributions
atorium+0.739
ratulations+0.671
 manoeuv+0.633
Downloadha+0.616
 scrape+0.602
Neg logit contributions
llan-0.727
 Luthor-0.697
oid-0.668
-0.623
exclusive-0.619
Token like
Token ID588
Feature activation-1.43e-02

Pos logit contributions
llan+1.268
 Luthor+1.210
oid+1.172
+1.070
exclusive+1.070
Neg logit contributions
atorium-1.312
ratulations-1.197
Downloadha-1.100
 manoeuv-1.095
ochet-1.077
Token faults
Token ID31025
Feature activation-7.07e-01

Pos logit contributions
atorium+0.011
ratulations+0.010
 manoeuv+0.010
Downloadha+0.009
 scrape+0.009
Neg logit contributions
llan-0.011
 Luthor-0.011
oid-0.011
-0.010
exclusive-0.010
Token,
Token ID11
Feature activation-2.24e-01

Pos logit contributions
atorium+0.619
ratulations+0.565
 manoeuv+0.540
Downloadha+0.520
 scrape+0.518
Neg logit contributions
llan-0.509
 Luthor-0.484
oid-0.462
-0.429
exclusive-0.424
Token we
Token ID356
Feature activation-4.49e-01

Pos logit contributions
atorium+0.208
ratulations+0.191
 manoeuv+0.183
Downloadha+0.177
 scrape+0.176
Neg logit contributions
llan-0.149
 Luthor-0.141
oid-0.133
-0.122
exclusive-0.122
Token shall
Token ID2236
Feature activation+1.03e+00

Pos logit contributions
atorium+0.371
ratulations+0.338
 manoeuv+0.313
Downloadha+0.312
acebook+0.304
Neg logit contributions
llan-0.350
 Luthor-0.331
oid-0.318
exclusive-0.293
-0.291
Token try
Token ID1949
Feature activation-4.73e+00

Pos logit contributions
llan+0.806
 Luthor+0.761
oid+0.733
exclusive+0.672
+0.659
Neg logit contributions
atorium-0.840
ratulations-0.771
Downloadha-0.724
acebook-0.705
 manoeuv-0.701
Token,
Token ID11
Feature activation-2.53e-01

Pos logit contributions
atorium+3.984
ratulations+3.607
 manoeuv+3.505
 scrape+3.332
Downloadha+3.297
Neg logit contributions
llan-3.457
 Luthor-3.325
oid-3.153
-3.030
exclusive-2.922
Token by
Token ID416
Feature activation-1.23e+00

Pos logit contributions
atorium+0.228
ratulations+0.208
 manoeuv+0.197
Downloadha+0.193
 scrape+0.190
Neg logit contributions
llan-0.176
 Luthor-0.166
oid-0.160
exclusive-0.146
-0.146
Token God
Token ID1793
Feature activation+1.14e-01

Pos logit contributions
atorium+0.977
ratulations+0.883
 manoeuv+0.837
Downloadha+0.808
 scrape+0.800
Neg logit contributions
llan-0.994
 Luthor-0.947
oid-0.908
-0.852
exclusive-0.845
Token's
Token ID338
Feature activation+4.59e-01

Pos logit contributions
llan+0.085
 Luthor+0.080
oid+0.077
+0.072
exclusive+0.071
Neg logit contributions
atorium-0.097
ratulations-0.089
 manoeuv-0.085
Downloadha-0.082
 scrape-0.081
Token help
Token ID1037
Feature activation+6.40e-01

Pos logit contributions
llan+0.381
 Luthor+0.363
oid+0.349
exclusive+0.328
+0.323
Neg logit contributions
atorium-0.351
ratulations-0.317
Downloadha-0.295
 manoeuv-0.294
acebook-0.285
Token,
Token ID11
Feature activation-1.46e-01

Pos logit contributions
atorium+0.760
ratulations+0.690
 manoeuv+0.665
Downloadha+0.640
 scrape+0.640
Neg logit contributions
llan-0.751
 Luthor-0.711
oid-0.683
exclusive-0.647
-0.641
Token mix
Token ID5022
Feature activation+1.20e+00

Pos logit contributions
atorium+0.119
ratulations+0.108
 manoeuv+0.101
Downloadha+0.099
acebook+0.097
Neg logit contributions
llan-0.115
 Luthor-0.110
oid-0.105
-0.098
exclusive-0.097
Token and
Token ID290
Feature activation+5.64e-04

Pos logit contributions
llan+0.918
 Luthor+0.874
oid+0.841
+0.788
exclusive+0.777
Neg logit contributions
atorium-0.997
ratulations-0.903
 manoeuv-0.862
Downloadha-0.830
 scrape-0.825
Token run
Token ID1057
Feature activation+1.04e+00

Pos logit contributions
llan+0.000
 Luthor+0.000
oid+0.000
+0.000
exclusive+0.000
Neg logit contributions
atorium-0.000
ratulations-0.000
 manoeuv-0.000
Downloadha-0.000
acebook-0.000
Token the
Token ID262
Feature activation-2.68e-02

Pos logit contributions
llan+0.780
 Luthor+0.747
oid+0.716
+0.664
exclusive+0.659
Neg logit contributions
atorium-0.871
ratulations-0.793
 manoeuv-0.747
Downloadha-0.720
 scrape-0.715
Token stock
Token ID4283
Feature activation-4.69e+00

Pos logit contributions
atorium+0.023
ratulations+0.021
 manoeuv+0.020
Downloadha+0.019
 scrape+0.019
Neg logit contributions
llan-0.020
 Luthor-0.019
oid-0.018
-0.017
exclusive-0.017
Token t
Token ID256
Feature activation-2.63e-01

Pos logit contributions
atorium+4.355
ratulations+3.986
 manoeuv+3.896
 scrape+3.750
Downloadha+3.721
Neg logit contributions
llan-3.052
 Luthor-2.856
oid-2.678
-2.537
exclusive-2.491
Tokenizen
Token ID33977
Feature activation+6.86e-01

Pos logit contributions
atorium+0.211
ratulations+0.190
 manoeuv+0.182
Downloadha+0.174
 scrape+0.173
Neg logit contributions
llan-0.208
 Luthor-0.199
oid-0.190
-0.179
exclusive-0.177
Token kernel
Token ID9720
Feature activation-3.59e-01

Pos logit contributions
llan+0.480
 Luthor+0.456
oid+0.440
+0.407
exclusive+0.401
Neg logit contributions
atorium-0.614
ratulations-0.560
 manoeuv-0.533
Downloadha-0.516
 scrape-0.510
Token with
Token ID351
Feature activation-4.76e-01

Pos logit contributions
atorium+0.312
ratulations+0.284
 manoeuv+0.271
Downloadha+0.261
 scrape+0.260
Neg logit contributions
llan-0.261
 Luthor-0.248
oid-0.237
-0.221
exclusive-0.218
Token the
Token ID262
Feature activation-2.38e-01

Pos logit contributions
atorium+0.391
ratulations+0.355
 manoeuv+0.338
Downloadha+0.324
 scrape+0.323
Neg logit contributions
llan-0.368
 Luthor-0.351
oid-0.336
-0.315
exclusive-0.311
Tokenay
Token ID323
Feature activation-9.19e-01

Pos logit contributions
atorium+0.227
ratulations+0.207
 manoeuv+0.198
Downloadha+0.192
 scrape+0.190
Neg logit contributions
llan-0.192
 Luthor-0.182
oid-0.175
-0.163
exclusive-0.160
Token T
Token ID309
Feature activation-4.25e-01

Pos logit contributions
atorium+0.782
ratulations+0.710
 manoeuv+0.681
Downloadha+0.652
 scrape+0.651
Neg logit contributions
llan-0.683
 Luthor-0.649
oid-0.620
-0.582
exclusive-0.574
Tokenades
Token ID2367
Feature activation-2.26e-01

Pos logit contributions
atorium+0.357
ratulations+0.324
 manoeuv+0.310
Downloadha+0.299
 scrape+0.297
Neg logit contributions
llan-0.322
 Luthor-0.304
oid-0.293
-0.273
exclusive-0.269
Tokene
Token ID68
Feature activation+9.98e-01

Pos logit contributions
atorium+0.201
ratulations+0.183
 manoeuv+0.176
Downloadha+0.169
 scrape+0.169
Neg logit contributions
llan-0.160
 Luthor-0.152
oid-0.145
-0.135
exclusive-0.133
Token will
Token ID481
Feature activation-1.66e+00

Pos logit contributions
llan+0.759
 Luthor+0.717
oid+0.690
+0.644
exclusive+0.628
Neg logit contributions
atorium-0.834
ratulations-0.766
 manoeuv-0.717
Downloadha-0.705
 scrape-0.685
Token try
Token ID1949
Feature activation-4.68e+00

Pos logit contributions
atorium+1.285
ratulations+1.172
Downloadha+1.097
 manoeuv+1.089
everal+1.046
Neg logit contributions
llan-1.363
 Luthor-1.304
oid-1.252
-1.162
exclusive-1.152
Token to
Token ID284
Feature activation-8.17e-01

Pos logit contributions
atorium+3.716
ratulations+3.312
 manoeuv+3.302
 scrape+3.126
Downloadha+3.060
Neg logit contributions
llan-3.611
 Luthor-3.474
oid-3.245
-3.134
exclusive-3.096
Token break
Token ID2270
Feature activation+7.95e-01

Pos logit contributions
atorium+0.668
ratulations+0.613
Downloadha+0.572
 manoeuv+0.564
everal+0.548
Neg logit contributions
llan-0.638
 Luthor-0.607
oid-0.586
-0.540
exclusive-0.533
Token 2
Token ID362
Feature activation-1.35e+00

Pos logit contributions
llan+0.621
 Luthor+0.591
oid+0.566
+0.530
exclusive+0.524
Neg logit contributions
atorium-0.649
ratulations-0.592
 manoeuv-0.560
Downloadha-0.539
 scrape-0.533
Token:
Token ID25
Feature activation-2.70e-01

Pos logit contributions
atorium+1.098
ratulations+0.992
 manoeuv+0.959
 scrape+0.916
Downloadha+0.905
Neg logit contributions
llan-1.036
 Luthor-0.996
oid-0.946
-0.895
exclusive-0.884
Token00
Token ID405
Feature activation-4.12e-01

Pos logit contributions
atorium+0.255
ratulations+0.235
 manoeuv+0.226
Downloadha+0.217
 scrape+0.217
Neg logit contributions
llan-0.176
 Luthor-0.166
oid-0.157
-0.146
exclusive-0.144
Token So
Token ID1406
Feature activation+2.42e-02

Pos logit contributions
llan+0.189
 Luthor+0.181
oid+0.172
+0.159
exclusive+0.157
Neg logit contributions
atorium-0.245
ratulations-0.226
 manoeuv-0.215
Downloadha-0.207
everal-0.206
Token let
Token ID1309
Feature activation+4.03e-02

Pos logit contributions
llan+0.018
 Luthor+0.017
oid+0.016
+0.015
exclusive+0.015
Neg logit contributions
atorium-0.021
ratulations-0.019
 manoeuv-0.018
Downloadha-0.018
acebook-0.017
Token
Token ID447
Feature activation+1.02e-01

Pos logit contributions
llan+0.031
 Luthor+0.029
oid+0.028
+0.026
exclusive+0.026
Neg logit contributions
atorium-0.033
ratulations-0.030
 manoeuv-0.029
 scrape-0.028
Downloadha-0.028
Token
Token ID247
Feature activation+4.81e-01

Pos logit contributions
llan+0.064
 Luthor+0.060
oid+0.057
+0.053
exclusive+0.051
Neg logit contributions
atorium-0.099
ratulations-0.092
 manoeuv-0.088
Downloadha-0.085
 scrape-0.084
Tokens
Token ID82
Feature activation-2.19e-01

Pos logit contributions
llan+0.240
 Luthor+0.218
oid+0.206
+0.184
exclusive+0.182
Neg logit contributions
atorium-0.530
ratulations-0.494
 manoeuv-0.477
Downloadha-0.465
 scrape-0.460
Token try
Token ID1949
Feature activation-4.67e+00

Pos logit contributions
atorium+0.180
ratulations+0.165
Downloadha+0.153
 manoeuv+0.151
everal+0.150
Neg logit contributions
llan-0.171
 Luthor-0.163
oid-0.156
-0.146
essim-0.142
Token to
Token ID284
Feature activation-6.04e-01

Pos logit contributions
atorium+3.797
ratulations+3.431
 manoeuv+3.318
 scrape+3.179
Downloadha+3.149
Neg logit contributions
llan-3.606
 Luthor-3.415
oid-3.252
-3.092
exclusive-3.057
Token write
Token ID3551
Feature activation-1.15e-01

Pos logit contributions
atorium+0.491
ratulations+0.449
Downloadha+0.419
 manoeuv+0.411
acebook+0.410
Neg logit contributions
llan-0.475
 Luthor-0.454
oid-0.440
-0.406
exclusive-0.395
Token something
Token ID1223
Feature activation+7.91e-02

Pos logit contributions
atorium+0.095
ratulations+0.086
 manoeuv+0.082
Downloadha+0.079
 scrape+0.078
Neg logit contributions
llan-0.089
 Luthor-0.085
oid-0.081
-0.076
exclusive-0.075
Token that
Token ID326
Feature activation+1.43e+00

Pos logit contributions
llan+0.057
 Luthor+0.054
oid+0.052
+0.048
exclusive+0.048
Neg logit contributions
atorium-0.069
ratulations-0.063
 manoeuv-0.060
Downloadha-0.058
 scrape-0.058
Token reaches
Token ID12229
Feature activation+1.91e+00

Pos logit contributions
llan+1.067
 Luthor+1.010
oid+0.971
+0.909
exclusive+0.878
Neg logit contributions
atorium-1.218
ratulations-1.118
 manoeuv-1.046
Downloadha-1.022
everal-1.006
Token by
Token ID416
Feature activation+6.35e-01

Pos logit contributions
llan+0.243
 Luthor+0.231
oid+0.221
+0.208
exclusive+0.205
Neg logit contributions
atorium-0.270
ratulations-0.245
 manoeuv-0.235
Downloadha-0.225
 scrape-0.224
Token wealthier
Token ID49311
Feature activation-9.02e-01

Pos logit contributions
llan+0.508
 Luthor+0.485
oid+0.463
+0.431
exclusive+0.428
Neg logit contributions
atorium-0.509
ratulations-0.464
Downloadha-0.429
 manoeuv-0.425
 scrape-0.413
Token Canadians
Token ID14008
Feature activation+6.48e-01

Pos logit contributions
atorium+0.703
ratulations+0.634
 manoeuv+0.588
Downloadha+0.584
 scrape+0.565
Neg logit contributions
llan-0.745
 Luthor-0.710
oid-0.682
-0.636
exclusive-0.631
Token and
Token ID290
Feature activation+9.82e-02

Pos logit contributions
llan+0.472
 Luthor+0.448
oid+0.431
+0.396
exclusive+0.391
Neg logit contributions
atorium-0.566
ratulations-0.519
 manoeuv-0.485
Downloadha-0.476
 scrape-0.467
Token the
Token ID262
Feature activation+2.85e-02

Pos logit contributions
llan+0.079
 Luthor+0.075
oid+0.072
+0.066
exclusive+0.066
Neg logit contributions
atorium-0.078
ratulations-0.072
Downloadha-0.066
 manoeuv-0.065
everal-0.064
Token stock
Token ID4283
Feature activation-4.62e+00

Pos logit contributions
llan+0.023
 Luthor+0.022
oid+0.021
+0.020
exclusive+0.020
Neg logit contributions
atorium-0.022
ratulations-0.020
Downloadha-0.019
 manoeuv-0.018
 scrape-0.018
Token options
Token ID3689
Feature activation+2.96e-01

Pos logit contributions
atorium+3.574
ratulations+3.142
 manoeuv+3.122
 scrape+2.879
 rese+2.865
Neg logit contributions
llan-3.777
 Luthor-3.558
oid-3.447
-3.247
exclusive-3.221
Token available
Token ID1695
Feature activation-1.33e-01

Pos logit contributions
llan+0.200
 Luthor+0.191
oid+0.180
+0.166
exclusive+0.163
Neg logit contributions
atorium-0.271
ratulations-0.248
 manoeuv-0.236
Downloadha-0.231
 scrape-0.228
Token to
Token ID284
Feature activation+2.30e-01

Pos logit contributions
atorium+0.122
ratulations+0.112
 manoeuv+0.107
Downloadha+0.103
 scrape+0.103
Neg logit contributions
llan-0.091
 Luthor-0.086
oid-0.082
-0.076
exclusive-0.075
Token corporate
Token ID6355
Feature activation-6.49e-01

Pos logit contributions
llan+0.188
 Luthor+0.180
oid+0.173
+0.162
exclusive+0.160
Neg logit contributions
atorium-0.179
ratulations-0.163
Downloadha-0.150
 manoeuv-0.148
acebook-0.144
Token executives
Token ID12353
Feature activation-5.93e-02

Pos logit contributions
atorium+0.534
ratulations+0.484
 manoeuv+0.458
Downloadha+0.445
 scrape+0.441
Neg logit contributions
llan-0.501
 Luthor-0.478
oid-0.457
-0.428
exclusive-0.422
Token shows
Token ID2523
Feature activation+8.42e-02

Pos logit contributions
llan+0.660
 Luthor+0.626
oid+0.601
+0.555
exclusive+0.547
Neg logit contributions
atorium-0.826
ratulations-0.756
 manoeuv-0.722
Downloadha-0.695
 scrape-0.688
Token she
Token ID673
Feature activation-1.32e+00

Pos logit contributions
llan+0.064
 Luthor+0.061
oid+0.058
+0.055
exclusive+0.054
Neg logit contributions
atorium-0.070
ratulations-0.064
 manoeuv-0.061
Downloadha-0.058
 scrape-0.058
Token owns
Token ID12216
Feature activation-8.19e-01

Pos logit contributions
atorium+1.149
ratulations+1.047
 manoeuv+1.004
Downloadha+0.964
 scrape+0.962
Neg logit contributions
llan-0.953
 Luthor-0.904
oid-0.862
-0.807
exclusive-0.795
Token bank
Token ID3331
Feature activation+3.17e-01

Pos logit contributions
atorium+0.691
ratulations+0.629
 manoeuv+0.600
Downloadha+0.577
 scrape+0.572
Neg logit contributions
llan-0.618
 Luthor-0.589
oid-0.561
-0.527
exclusive-0.520
Token and
Token ID290
Feature activation+4.81e-01

Pos logit contributions
llan+0.261
 Luthor+0.249
oid+0.239
+0.226
exclusive+0.223
Neg logit contributions
atorium-0.245
ratulations-0.220
 manoeuv-0.210
Downloadha-0.201
 scrape-0.199
Token stock
Token ID4283
Feature activation-4.52e+00

Pos logit contributions
llan+0.387
 Luthor+0.370
oid+0.351
exclusive+0.326
+0.324
Neg logit contributions
atorium-0.384
ratulations-0.349
 manoeuv-0.328
Downloadha-0.316
everal-0.309
Token funds
Token ID5153
Feature activation-6.13e-01

Pos logit contributions
atorium+3.498
ratulations+3.104
 manoeuv+3.031
 scrape+2.862
 rese+2.847
Neg logit contributions
llan-3.644
 Luthor-3.448
oid-3.339
-3.190
essim-3.127
Token worth
Token ID2861
Feature activation-1.39e+00

Pos logit contributions
atorium+0.574
ratulations+0.525
 manoeuv+0.507
Downloadha+0.487
 scrape+0.487
Neg logit contributions
llan-0.404
 Luthor-0.381
oid-0.361
-0.336
exclusive-0.330
Token as
Token ID355
Feature activation-1.55e-02

Pos logit contributions
atorium+1.242
ratulations+1.134
 manoeuv+1.089
Downloadha+1.047
 scrape+1.044
Neg logit contributions
llan-0.976
 Luthor-0.926
oid-0.881
-0.823
exclusive-0.810
Token much
Token ID881
Feature activation-1.96e-01

Pos logit contributions
atorium+0.013
ratulations+0.012
 manoeuv+0.012
Downloadha+0.011
 scrape+0.011
Neg logit contributions
llan-0.011
 Luthor-0.011
oid-0.010
-0.010
exclusive-0.009
Token as
Token ID355
Feature activation-3.13e-01

Pos logit contributions
atorium+0.188
ratulations+0.174
 manoeuv+0.166
Downloadha+0.161
acebook+0.159
Neg logit contributions
llan-0.126
 Luthor-0.119
oid-0.112
-0.103
exclusive-0.101
Token basically
Token ID6209
Feature activation+5.08e-01

Pos logit contributions
atorium+0.070
ratulations+0.064
Downloadha+0.060
 manoeuv+0.059
everal+0.058
Neg logit contributions
llan-0.065
 Luthor-0.062
oid-0.060
-0.055
exclusive-0.054
Token ready
Token ID3492
Feature activation+8.69e-01

Pos logit contributions
llan+0.386
 Luthor+0.374
oid+0.359
+0.327
exclusive+0.326
Neg logit contributions
atorium-0.419
ratulations-0.381
Downloadha-0.358
 manoeuv-0.347
everal-0.346
Token.
Token ID13
Feature activation-3.45e-01

Pos logit contributions
llan+0.582
 Luthor+0.551
oid+0.525
+0.484
exclusive+0.475
Neg logit contributions
atorium-0.803
ratulations-0.736
 manoeuv-0.703
Downloadha-0.686
 scrape-0.677
Token We
Token ID775
Feature activation+1.42e-01

Pos logit contributions
atorium+0.315
ratulations+0.291
 manoeuv+0.278
Downloadha+0.269
 scrape+0.267
Neg logit contributions
llan-0.235
 Luthor-0.223
oid-0.212
-0.197
exclusive-0.193
Token will
Token ID481
Feature activation-3.20e-01

Pos logit contributions
llan+0.106
 Luthor+0.100
oid+0.097
+0.088
exclusive+0.088
Neg logit contributions
atorium-0.121
ratulations-0.111
Downloadha-0.104
 manoeuv-0.103
everal-0.101
Token try
Token ID1949
Feature activation-4.50e+00

Pos logit contributions
atorium+0.260
ratulations+0.240
Downloadha+0.227
acebook+0.219
everal+0.218
Neg logit contributions
llan-0.249
 Luthor-0.238
oid-0.229
-0.211
exclusive-0.209
Token to
Token ID284
Feature activation-9.61e-01

Pos logit contributions
atorium+3.777
ratulations+3.397
 manoeuv+3.351
 scrape+3.163
 rese+3.093
Neg logit contributions
llan-3.348
 Luthor-3.181
oid-3.026
-2.892
exclusive-2.853
Token find
Token ID1064
Feature activation+8.38e-02

Pos logit contributions
atorium+0.800
ratulations+0.739
Downloadha+0.696
acebook+0.672
everal+0.669
Neg logit contributions
llan-0.730
 Luthor-0.700
oid-0.676
-0.619
essim-0.608
Token bits
Token ID10340
Feature activation-6.90e-01

Pos logit contributions
llan+0.065
 Luthor+0.062
oid+0.059
+0.055
exclusive+0.054
Neg logit contributions
atorium-0.068
ratulations-0.063
Downloadha-0.058
 manoeuv-0.057
brance-0.057
Token and
Token ID290
Feature activation-7.49e-01

Pos logit contributions
atorium+0.646
ratulations+0.593
 manoeuv+0.571
Downloadha+0.549
 scrape+0.549
Neg logit contributions
llan-0.454
 Luthor-0.429
oid-0.407
-0.378
exclusive-0.372
Token pieces
Token ID5207
Feature activation-9.18e-01

Pos logit contributions
atorium+0.563
ratulations+0.505
 manoeuv+0.466
Downloadha+0.457
acebook+0.444
Neg logit contributions
llan-0.637
 Luthor-0.613
oid-0.590
-0.553
exclusive-0.546
TokenAt
Token ID2953
Feature activation-1.10e+00

Pos logit contributions
llan+0.251
 Luthor+0.236
oid+0.230
exclusive+0.212
+0.212
Neg logit contributions
atorium-0.296
ratulations-0.274
 manoeuv-0.262
 scrape-0.253
Downloadha-0.252
Token the
Token ID262
Feature activation+2.51e-01

Pos logit contributions
atorium+0.877
ratulations+0.792
 manoeuv+0.757
Downloadha+0.722
 scrape+0.722
Neg logit contributions
llan-0.871
 Luthor-0.830
oid-0.796
-0.750
exclusive-0.740
Token Crescent
Token ID36398
Feature activation+2.46e-01

Pos logit contributions
llan+0.194
 Luthor+0.188
oid+0.178
+0.166
exclusive+0.164
Neg logit contributions
atorium-0.207
ratulations-0.189
 manoeuv-0.176
Downloadha-0.174
 scrape-0.168
Token Heights
Token ID20365
Feature activation-6.57e-01

Pos logit contributions
llan+0.184
 Luthor+0.174
oid+0.167
+0.156
exclusive+0.154
Neg logit contributions
atorium-0.208
ratulations-0.190
 manoeuv-0.182
Downloadha-0.175
 scrape-0.174
Token Social
Token ID5483
Feature activation-1.67e-01

Pos logit contributions
atorium+0.516
ratulations+0.467
 manoeuv+0.443
Downloadha+0.428
 scrape+0.421
Neg logit contributions
llan-0.531
 Luthor-0.509
oid-0.486
-0.457
exclusive-0.451
Token Justice
Token ID4796
Feature activation+2.52e+00

Pos logit contributions
atorium+0.187
ratulations+0.170
 manoeuv+0.165
 scrape+0.160
acebook+0.157
Neg logit contributions
llan-0.083
 Luthor-0.075
oid-0.071
-0.064
exclusive-0.063
Token Magnet
Token ID32079
Feature activation-2.40e-01

Pos logit contributions
llan+1.808
 Luthor+1.732
oid+1.642
+1.518
exclusive+1.504
Neg logit contributions
atorium-2.157
ratulations-2.015
 manoeuv-1.898
Downloadha-1.890
 scrape-1.820
Token School
Token ID3961
Feature activation-9.10e-01

Pos logit contributions
atorium+0.160
ratulations+0.141
 manoeuv+0.133
Downloadha+0.125
 scrape+0.125
Neg logit contributions
llan-0.223
 Luthor-0.214
oid-0.207
-0.197
exclusive-0.195
Token in
Token ID287
Feature activation+6.53e-01

Pos logit contributions
atorium+0.783
ratulations+0.711
 manoeuv+0.682
 scrape+0.653
Downloadha+0.651
Neg logit contributions
llan-0.669
 Luthor-0.636
oid-0.606
-0.570
exclusive-0.560
Token Los
Token ID5401
Feature activation+8.19e-01

Pos logit contributions
llan+0.499
 Luthor+0.477
oid+0.454
+0.422
exclusive+0.419
Neg logit contributions
atorium-0.546
ratulations-0.497
 manoeuv-0.471
Downloadha-0.457
 scrape-0.449
Token Angeles
Token ID5652
Feature activation+1.32e+00

Pos logit contributions
llan+0.352
 Luthor+0.324
oid+0.297
exclusive+0.251
+0.247
Neg logit contributions
atorium-0.949
ratulations-0.913
 manoeuv-0.873
Downloadha-0.862
everal-0.855
Token--
Token ID438
Feature activation-3.64e-01

Pos logit contributions
atorium+0.563
ratulations+0.525
everal+0.498
 manoeuv+0.497
Downloadha+0.491
Neg logit contributions
llan-0.398
 Luthor-0.372
oid-0.359
exclusive-0.327
-0.325
Token Start
Token ID7253
Feature activation+1.20e+00

Pos logit contributions
atorium+0.295
ratulations+0.267
 manoeuv+0.255
Downloadha+0.245
 scrape+0.244
Neg logit contributions
llan-0.285
 Luthor-0.271
oid-0.260
-0.244
exclusive-0.241
Token of
Token ID286
Feature activation-2.90e-01

Pos logit contributions
llan+0.663
 Luthor+0.614
oid+0.593
exclusive+0.514
+0.512
Neg logit contributions
atorium-1.254
ratulations-1.195
everal-1.137
Downloadha-1.115
acebook-1.113
Token read
Token ID1100
Feature activation+3.20e-01

Pos logit contributions
atorium+0.264
ratulations+0.243
 manoeuv+0.239
 scrape+0.230
 rese+0.225
Neg logit contributions
llan-0.197
 Luthor-0.186
oid-0.174
-0.165
exclusive-0.162
Token()
Token ID3419
Feature activation+1.66e+00

Pos logit contributions
llan+0.200
 Luthor+0.186
oid+0.181
exclusive+0.164
+0.162
Neg logit contributions
atorium-0.309
ratulations-0.294
everal-0.276
 manoeuv-0.275
Downloadha-0.271
Token'
Token ID6
Feature activation+2.61e+00

Pos logit contributions
llan+1.210
 Luthor+1.141
oid+1.098
exclusive+0.994
+0.988
Neg logit contributions
atorium-1.433
ratulations-1.354
everal-1.292
Downloadha-1.263
acebook-1.250
Tokens
Token ID82
Feature activation-4.36e-01

Pos logit contributions
llan+1.110
 Luthor+0.979
oid+0.952
exclusive+0.796
+0.764
Neg logit contributions
atorium-3.055
ratulations-2.959
everal-2.881
acebook-2.771
Downloadha-2.768
Token frame
Token ID5739
Feature activation-3.89e-01

Pos logit contributions
atorium+0.335
ratulations+0.305
 manoeuv+0.280
Downloadha+0.280
everal+0.276
Neg logit contributions
llan-0.363
 Luthor-0.346
oid-0.336
-0.311
exclusive-0.308
Token |
Token ID930
Feature activation+2.01e-01

Pos logit contributions
atorium+0.334
ratulations+0.312
everal+0.290
 manoeuv+0.290
Downloadha+0.287
Neg logit contributions
llan-0.287
 Luthor-0.273
oid-0.263
-0.240
exclusive-0.240
Token size
Token ID2546
Feature activation-2.03e-02

Pos logit contributions
llan+0.161
 Luthor+0.154
oid+0.147
+0.139
exclusive+0.137
Neg logit contributions
atorium-0.159
ratulations-0.144
 manoeuv-0.137
 scrape-0.131
Downloadha-0.131
Token_
Token ID62
Feature activation+1.39e+00

Pos logit contributions
atorium+0.022
ratulations+0.021
 manoeuv+0.020
everal+0.020
Downloadha+0.020
Neg logit contributions
llan-0.010
 Luthor-0.009
oid-0.009
-0.008
exclusive-0.008
Token.
Token ID13
Feature activation+1.60e-01

Pos logit contributions
atorium+0.052
ratulations+0.047
 manoeuv+0.044
Downloadha+0.044
 scrape+0.043
Neg logit contributions
llan-0.053
 Luthor-0.051
oid-0.049
-0.046
exclusive-0.045
TokenJ
Token ID41
Feature activation+5.32e-01

Pos logit contributions
llan+0.116
 Luthor+0.111
oid+0.105
+0.098
exclusive+0.097
Neg logit contributions
atorium-0.139
ratulations-0.129
 manoeuv-0.122
Downloadha-0.118
 scrape-0.117
Token'
Token ID6
Feature activation+3.72e+00

Pos logit contributions
llan+0.425
 Luthor+0.400
oid+0.393
+0.360
exclusive+0.360
Neg logit contributions
atorium-0.425
ratulations-0.383
 manoeuv-0.363
Downloadha-0.354
 scrape-0.352
Tokenai
Token ID1872
Feature activation-5.90e-01

Pos logit contributions
llan+2.850
oid+2.641
 Luthor+2.626
exclusive+2.471
essim+2.404
Neg logit contributions
atorium-3.018
ratulations-2.746
 manoeuv-2.601
 scrape-2.559
Downloadha-2.548
Token l
Token ID300
Feature activation+3.98e-01

Pos logit contributions
atorium+0.458
ratulations+0.413
 manoeuv+0.388
Downloadha+0.380
 scrape+0.371
Neg logit contributions
llan-0.485
 Luthor-0.460
oid-0.443
-0.413
exclusive-0.413
Token'
Token ID6
Feature activation+2.96e+00

Pos logit contributions
llan+0.302
 Luthor+0.282
oid+0.277
exclusive+0.255
essim+0.252
Neg logit contributions
atorium-0.330
ratulations-0.302
 manoeuv-0.286
Downloadha-0.285
 scrape-0.280
Tokenhon
Token ID24130
Feature activation+3.65e-01

Pos logit contributions
llan+2.266
 Luthor+2.130
oid+2.115
exclusive+1.979
essim+1.931
Neg logit contributions
atorium-2.391
ratulations-2.161
 manoeuv-2.057
 scrape-2.033
Downloadha-2.007
Tokenne
Token ID710
Feature activation-2.17e-01

Pos logit contributions
llan+0.273
 Luthor+0.257
oid+0.252
+0.235
exclusive+0.231
Neg logit contributions
atorium-0.305
ratulations-0.281
 manoeuv-0.264
Downloadha-0.258
 scrape-0.256
Tokenur
Token ID333
Feature activation+1.13e+00

Pos logit contributions
atorium+0.165
ratulations+0.150
 manoeuv+0.140
Downloadha+0.138
 scrape+0.135
Neg logit contributions
llan-0.182
 Luthor-0.173
oid-0.166
-0.157
exclusive-0.155
Token d
Token ID288
Feature activation-2.52e-01

Pos logit contributions
llan+0.924
 Luthor+0.882
oid+0.854
+0.799
exclusive+0.788
Neg logit contributions
atorium-0.862
ratulations-0.780
 manoeuv-0.726
Downloadha-0.719
 scrape-0.699
Token'
Token ID6
Feature activation+3.66e+00

Pos logit contributions
atorium+0.203
ratulations+0.185
 manoeuv+0.177
Downloadha+0.171
 scrape+0.169
Neg logit contributions
llan-0.199
 Luthor-0.188
oid-0.182
exclusive-0.168
-0.168
Token aspects
Token ID7612
Feature activation-2.77e-01

Pos logit contributions
llan+0.007
 Luthor+0.006
oid+0.006
+0.006
exclusive+0.006
Neg logit contributions
atorium-0.006
ratulations-0.005
 manoeuv-0.005
Downloadha-0.005
 scrape-0.005
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
atorium+0.240
ratulations+0.218
 manoeuv+0.211
Downloadha+0.201
 scrape+0.201
Neg logit contributions
llan-0.201
 Luthor-0.191
oid-0.181
-0.171
exclusive-0.169
Token They
Token ID1119
Feature activation-1.98e-01

Pos logit contributions
llan+0.077
 Luthor+0.074
oid+0.070
+0.064
exclusive+0.064
Neg logit contributions
atorium-0.101
ratulations-0.095
 manoeuv-0.090
everal-0.087
Downloadha-0.086
Token deserve
Token ID10925
Feature activation+5.74e-02

Pos logit contributions
atorium+0.166
ratulations+0.152
Downloadha+0.140
 manoeuv+0.140
everal+0.137
Neg logit contributions
llan-0.151
 Luthor-0.144
oid-0.139
-0.126
exclusive-0.125
Token our
Token ID674
Feature activation+9.28e-02

Pos logit contributions
llan+0.044
 Luthor+0.042
oid+0.040
+0.037
exclusive+0.037
Neg logit contributions
atorium-0.048
ratulations-0.043
 manoeuv-0.041
Downloadha-0.040
everal-0.039
Token respect
Token ID2461
Feature activation+3.51e+00

Pos logit contributions
llan+0.081
 Luthor+0.079
oid+0.076
exclusive+0.071
+0.070
Neg logit contributions
atorium-0.067
ratulations-0.059
Downloadha-0.056
 manoeuv-0.056
everal-0.053
Token and
Token ID290
Feature activation+5.14e-01

Pos logit contributions
llan+2.433
 Luthor+2.271
oid+2.236
+1.980
exclusive+1.968
Neg logit contributions
atorium-3.131
ratulations-2.890
 manoeuv-2.757
Downloadha-2.703
everal-2.654
Token admiration
Token ID28506
Feature activation+1.38e+00

Pos logit contributions
llan+0.438
 Luthor+0.420
oid+0.403
exclusive+0.376
+0.374
Neg logit contributions
atorium-0.381
ratulations-0.342
 manoeuv-0.322
Downloadha-0.317
everal-0.308
Token.
Token ID13
Feature activation-2.62e-01

Pos logit contributions
llan+1.012
 Luthor+0.957
oid+0.922
+0.846
exclusive+0.837
Neg logit contributions
atorium-1.185
ratulations-1.082
 manoeuv-1.030
Downloadha-0.998
 scrape-0.986
Token If
Token ID1002
Feature activation-1.56e-01

Pos logit contributions
atorium+0.237
ratulations+0.220
 manoeuv+0.209
Downloadha+0.201
 scrape+0.201
Neg logit contributions
llan-0.183
 Luthor-0.174
oid-0.165
-0.153
exclusive-0.151
Token my
Token ID616
Feature activation-2.65e-01

Pos logit contributions
atorium+0.145
ratulations+0.133
 manoeuv+0.126
Downloadha+0.124
 scrape+0.122
Neg logit contributions
llan-0.105
 Luthor-0.100
oid-0.095
-0.086
exclusive-0.085
Token (
Token ID357
Feature activation+1.20e+00

Pos logit contributions
llan+0.560
 Luthor+0.527
oid+0.510
+0.459
exclusive+0.458
Neg logit contributions
atorium-0.775
ratulations-0.732
everal-0.684
 manoeuv-0.684
Downloadha-0.675
Token0
Token ID15
Feature activation+1.01e-01

Pos logit contributions
llan+0.815
 Luthor+0.777
oid+0.726
+0.681
essim+0.662
Neg logit contributions
atorium-1.090
ratulations-0.996
 manoeuv-0.961
 scrape-0.927
Downloadha-0.924
Token,
Token ID11
Feature activation+4.19e-01

Pos logit contributions
llan+0.072
 Luthor+0.067
oid+0.065
+0.059
exclusive+0.059
Neg logit contributions
atorium-0.091
ratulations-0.085
everal-0.080
 manoeuv-0.080
Downloadha-0.078
Token($
Token ID16763
Feature activation+1.25e+00

Pos logit contributions
llan+0.302
 Luthor+0.287
oid+0.271
+0.255
essim+0.249
Neg logit contributions
atorium-0.365
ratulations-0.333
 manoeuv-0.318
Downloadha-0.309
 scrape-0.308
Tokeni
Token ID72
Feature activation-2.01e-01

Pos logit contributions
llan+0.655
 Luthor+0.618
oid+0.563
+0.517
exclusive+0.504
Neg logit contributions
atorium-1.333
ratulations-1.237
 manoeuv-1.195
 scrape-1.160
Downloadha-1.156
Token*
Token ID9
Feature activation+4.11e+00

Pos logit contributions
atorium+0.174
ratulations+0.160
 manoeuv+0.153
Downloadha+0.147
 scrape+0.146
Neg logit contributions
llan-0.147
 Luthor-0.139
oid-0.130
-0.124
exclusive-0.120
Token$
Token ID3
Feature activation+1.25e+00

Pos logit contributions
llan+2.976
 Luthor+2.769
oid+2.699
+2.515
exclusive+2.493
Neg logit contributions
atorium-3.588
ratulations-3.276
 manoeuv-3.108
Downloadha-2.987
 scrape-2.956
TokenFontSize
Token ID38160
Feature activation+7.19e-01

Pos logit contributions
llan+1.043
 Luthor+0.992
oid+0.958
+0.905
exclusive+0.893
Neg logit contributions
atorium-0.958
ratulations-0.861
 manoeuv-0.820
Downloadha-0.781
 scrape-0.779
Token*
Token ID9
Feature activation+2.94e+00

Pos logit contributions
llan+0.505
 Luthor+0.478
oid+0.455
+0.425
exclusive+0.418
Neg logit contributions
atorium-0.642
ratulations-0.587
 manoeuv-0.563
Downloadha-0.541
 scrape-0.540
Token2
Token ID17
Feature activation-4.64e-01

Pos logit contributions
llan+2.043
 Luthor+1.914
oid+1.839
+1.708
exclusive+1.693
Neg logit contributions
atorium-2.644
ratulations-2.438
 manoeuv-2.316
 scrape-2.221
Downloadha-2.218
Token +
Token ID1343
Feature activation-1.01e+00

Pos logit contributions
atorium+0.418
ratulations+0.382
 manoeuv+0.368
Downloadha+0.353
 scrape+0.352
Neg logit contributions
llan-0.321
 Luthor-0.304
oid-0.289
-0.270
exclusive-0.265
Token catastrophic
Token ID22694
Feature activation+1.27e+00

Pos logit contributions
atorium+0.139
ratulations+0.127
 manoeuv+0.120
Downloadha+0.116
 scrape+0.114
Neg logit contributions
llan-0.125
 Luthor-0.120
oid-0.114
-0.107
exclusive-0.105
Token.
Token ID13
Feature activation-6.86e-02

Pos logit contributions
llan+0.932
 Luthor+0.883
oid+0.848
+0.794
exclusive+0.776
Neg logit contributions
atorium-1.088
ratulations-0.991
 manoeuv-0.944
Downloadha-0.912
 scrape-0.902
Token The
Token ID383
Feature activation-6.92e-03

Pos logit contributions
atorium+0.064
ratulations+0.060
 manoeuv+0.057
everal+0.055
Downloadha+0.055
Neg logit contributions
llan-0.045
 Luthor-0.044
oid-0.041
-0.038
exclusive-0.037
Token main
Token ID1388
Feature activation-8.74e-01

Pos logit contributions
atorium+0.006
ratulations+0.005
 manoeuv+0.005
Downloadha+0.005
 scrape+0.005
Neg logit contributions
llan-0.005
 Luthor-0.005
oid-0.005
-0.005
exclusive-0.004
Token thing
Token ID1517
Feature activation+1.27e-01

Pos logit contributions
atorium+0.725
ratulations+0.659
 manoeuv+0.626
Downloadha+0.605
 scrape+0.598
Neg logit contributions
llan-0.668
 Luthor-0.638
oid-0.611
-0.573
exclusive-0.562
Token is
Token ID318
Feature activation+2.48e-01

Pos logit contributions
llan+0.085
 Luthor+0.080
oid+0.077
+0.071
exclusive+0.069
Neg logit contributions
atorium-0.119
ratulations-0.109
 manoeuv-0.105
Downloadha-0.101
 scrape-0.100
Token avoid
Token ID3368
Feature activation+1.40e+00

Pos logit contributions
llan+0.176
 Luthor+0.167
oid+0.159
+0.148
exclusive+0.145
Neg logit contributions
atorium-0.220
ratulations-0.201
 manoeuv-0.192
Downloadha-0.185
 scrape-0.184
Token the
Token ID262
Feature activation+3.48e-01

Pos logit contributions
llan+1.121
 Luthor+1.072
oid+1.037
+0.966
essim+0.951
Neg logit contributions
atorium-1.094
ratulations-0.996
 manoeuv-0.936
Downloadha-0.913
 scrape-0.888
Token catastrophic
Token ID22694
Feature activation+3.63e-01

Pos logit contributions
llan+0.268
 Luthor+0.261
oid+0.249
+0.232
exclusive+0.227
Neg logit contributions
atorium-0.284
ratulations-0.260
 manoeuv-0.241
Downloadha-0.239
everal-0.231
Token events
Token ID2995
Feature activation+6.88e-01

Pos logit contributions
llan+0.290
 Luthor+0.281
oid+0.273
+0.253
essim+0.248
Neg logit contributions
atorium-0.286
ratulations-0.261
 manoeuv-0.240
Downloadha-0.239
everal-0.231
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
llan+0.485
 Luthor+0.460
oid+0.443
+0.407
exclusive+0.397
Neg logit contributions
atorium-0.614
ratulations-0.565
 manoeuv-0.535
Downloadha-0.519
 scrape-0.512
Token crying
Token ID13774
Feature activation+9.22e-01

Pos logit contributions
llan+0.421
 Luthor+0.400
oid+0.383
+0.360
exclusive+0.355
Neg logit contributions
atorium-0.476
ratulations-0.433
 manoeuv-0.410
Downloadha-0.398
 scrape-0.393
Token alone
Token ID3436
Feature activation-2.00e+00

Pos logit contributions
llan+0.675
 Luthor+0.641
oid+0.613
+0.572
exclusive+0.563
Neg logit contributions
atorium-0.795
ratulations-0.726
 manoeuv-0.691
Downloadha-0.666
 scrape-0.661
Token into
Token ID656
Feature activation+2.15e-01

Pos logit contributions
atorium+1.676
ratulations+1.521
 manoeuv+1.460
Downloadha+1.397
 scrape+1.397
Neg logit contributions
llan-1.512
 Luthor-1.442
oid-1.376
-1.293
exclusive-1.279
Token a
Token ID257
Feature activation+1.99e-01

Pos logit contributions
llan+0.165
 Luthor+0.157
oid+0.151
+0.141
exclusive+0.139
Neg logit contributions
atorium-0.178
ratulations-0.162
 manoeuv-0.154
Downloadha-0.148
 scrape-0.147
Token pint
Token ID35245
Feature activation+6.54e-01

Pos logit contributions
llan+0.160
 Luthor+0.153
oid+0.146
+0.138
exclusive+0.135
Neg logit contributions
atorium-0.156
ratulations-0.143
 manoeuv-0.134
Downloadha-0.129
 scrape-0.127
Token of
Token ID286
Feature activation+1.43e-01

Pos logit contributions
llan+0.448
 Luthor+0.423
oid+0.403
+0.375
exclusive+0.369
Neg logit contributions
atorium-0.594
ratulations-0.545
 manoeuv-0.523
Downloadha-0.503
 scrape-0.501
Token Ben
Token ID3932
Feature activation-7.15e-01

Pos logit contributions
llan+0.107
 Luthor+0.102
oid+0.097
+0.091
exclusive+0.089
Neg logit contributions
atorium-0.122
ratulations-0.111
 manoeuv-0.106
Downloadha-0.102
 scrape-0.101
Token and
Token ID290
Feature activation+5.31e-01

Pos logit contributions
atorium+0.642
ratulations+0.583
 manoeuv+0.562
 scrape+0.540
Downloadha+0.538
Neg logit contributions
llan-0.501
 Luthor-0.471
oid-0.447
-0.418
exclusive-0.413
Token Jerry
Token ID13075
Feature activation-8.03e-01

Pos logit contributions
llan+0.440
 Luthor+0.427
oid+0.407
+0.385
exclusive+0.378
Neg logit contributions
atorium-0.403
ratulations-0.368
 manoeuv-0.343
Downloadha-0.333
acebook-0.324
Token
Token ID447
Feature activation-5.81e-01

Pos logit contributions
atorium+0.670
ratulations+0.606
 manoeuv+0.585
 scrape+0.560
Downloadha+0.554
Neg logit contributions
llan-0.612
 Luthor-0.580
oid-0.552
-0.519
exclusive-0.512
Token
Token ID247
Feature activation-1.13e-01

Pos logit contributions
atorium+0.534
ratulations+0.487
 manoeuv+0.466
 scrape+0.452
Downloadha+0.449
Neg logit contributions
llan-0.392
 Luthor-0.370
oid-0.353
-0.327
exclusive-0.325
Token for
Token ID329
Feature activation+2.33e-01

Pos logit contributions
atorium+0.115
ratulations+0.105
 manoeuv+0.102
 scrape+0.097
Downloadha+0.097
Neg logit contributions
llan-0.082
 Luthor-0.078
oid-0.074
-0.069
exclusive-0.067
Token the
Token ID262
Feature activation+1.61e-01

Pos logit contributions
llan+0.179
 Luthor+0.172
oid+0.164
+0.151
exclusive+0.150
Neg logit contributions
atorium-0.193
ratulations-0.176
 manoeuv-0.165
Downloadha-0.162
 scrape-0.160
Token authorities
Token ID4773
Feature activation-5.20e-01

Pos logit contributions
llan+0.114
 Luthor+0.110
oid+0.105
+0.096
exclusive+0.095
Neg logit contributions
atorium-0.141
ratulations-0.129
 manoeuv-0.122
Downloadha-0.120
 scrape-0.118
Token to
Token ID284
Feature activation+1.19e-01

Pos logit contributions
atorium+0.448
ratulations+0.407
 manoeuv+0.395
 scrape+0.379
Downloadha+0.373
Neg logit contributions
llan-0.377
 Luthor-0.358
oid-0.340
-0.323
exclusive-0.318
Token call
Token ID869
Feature activation-6.60e-02

Pos logit contributions
llan+0.092
 Luthor+0.088
oid+0.085
+0.077
exclusive+0.076
Neg logit contributions
atorium-0.097
ratulations-0.090
Downloadha-0.085
everal-0.082
acebook-0.081
Token it
Token ID340
Feature activation+4.07e-01

Pos logit contributions
atorium+0.057
ratulations+0.052
 manoeuv+0.049
Downloadha+0.048
 scrape+0.047
Neg logit contributions
llan-0.048
 Luthor-0.047
oid-0.044
-0.041
exclusive-0.040
Token a
Token ID257
Feature activation-1.14e-02

Pos logit contributions
llan+0.315
 Luthor+0.303
oid+0.290
+0.270
exclusive+0.267
Neg logit contributions
atorium-0.332
ratulations-0.304
 manoeuv-0.286
Downloadha-0.277
 scrape-0.273
Token terrorist
Token ID7417
Feature activation+3.69e-01

Pos logit contributions
atorium+0.010
ratulations+0.009
 manoeuv+0.008
Downloadha+0.008
 scrape+0.008
Neg logit contributions
llan-0.008
 Luthor-0.008
oid-0.008
-0.007
exclusive-0.007
Token attack
Token ID1368
Feature activation-9.86e-01

Pos logit contributions
llan+0.337
 Luthor+0.326
oid+0.318
+0.299
exclusive+0.295
Neg logit contributions
atorium-0.247
ratulations-0.222
 manoeuv-0.205
Downloadha-0.200
 scrape-0.193
Token,
Token ID11
Feature activation-9.18e-03

Pos logit contributions
atorium+0.826
ratulations+0.747
 manoeuv+0.720
 scrape+0.689
Downloadha+0.685
Neg logit contributions
llan-0.744
 Luthor-0.705
oid-0.671
-0.637
exclusive-0.629
Token for
Token ID329
Feature activation+3.33e-02

Pos logit contributions
atorium+0.007
ratulations+0.006
 manoeuv+0.006
Downloadha+0.006
 scrape+0.006
Neg logit contributions
llan-0.007
 Luthor-0.007
oid-0.007
-0.006
exclusive-0.006
Token friends
Token ID2460
Feature activation-1.74e+00

Pos logit contributions
atorium+0.152
ratulations+0.136
 manoeuv+0.128
Downloadha+0.127
brance+0.121
Neg logit contributions
llan-0.163
 Luthor-0.157
oid-0.152
-0.142
exclusive-0.140
Token to
Token ID284
Feature activation+1.90e-01

Pos logit contributions
atorium+1.514
ratulations+1.381
 manoeuv+1.329
 scrape+1.278
Downloadha+1.269
Neg logit contributions
llan-1.247
 Luthor-1.184
oid-1.125
-1.057
exclusive-1.044
Token the
Token ID262
Feature activation+2.37e-01

Pos logit contributions
llan+0.154
 Luthor+0.150
oid+0.143
+0.134
exclusive+0.131
Neg logit contributions
atorium-0.147
ratulations-0.136
Downloadha-0.126
 manoeuv-0.123
brance-0.120
Token web
Token ID3992
Feature activation+7.53e-01

Pos logit contributions
llan+0.193
 Luthor+0.185
oid+0.177
exclusive+0.166
+0.165
Neg logit contributions
atorium-0.185
ratulations-0.169
 manoeuv-0.156
Downloadha-0.156
brance-0.151
Token page
Token ID2443
Feature activation+1.09e+00

Pos logit contributions
llan+0.552
 Luthor+0.522
oid+0.502
+0.469
exclusive+0.464
Neg logit contributions
atorium-0.650
ratulations-0.594
 manoeuv-0.567
Downloadha-0.549
 scrape-0.539
Token where
Token ID810
Feature activation+5.65e-01

Pos logit contributions
llan+0.739
 Luthor+0.706
oid+0.675
+0.617
exclusive+0.612
Neg logit contributions
atorium-1.002
ratulations-0.922
 manoeuv-0.875
Downloadha-0.859
brance-0.835
Token making
Token ID1642
Feature activation+4.28e-01

Pos logit contributions
llan+0.376
 Luthor+0.357
oid+0.338
+0.312
exclusive+0.310
Neg logit contributions
atorium-0.523
ratulations-0.479
 manoeuv-0.460
Downloadha-0.450
 scrape-0.441
Token donations
Token ID10976
Feature activation+1.87e+00

Pos logit contributions
llan+0.328
 Luthor+0.315
oid+0.299
+0.278
exclusive+0.278
Neg logit contributions
atorium-0.358
ratulations-0.321
 manoeuv-0.306
Downloadha-0.300
brance-0.290
Token is
Token ID318
Feature activation-5.73e-02

Pos logit contributions
llan+1.308
 Luthor+1.253
oid+1.201
+1.095
exclusive+1.082
Neg logit contributions
atorium-1.664
ratulations-1.532
 manoeuv-1.427
Downloadha-1.420
everal-1.387
Token as
Token ID355
Feature activation+3.88e-01

Pos logit contributions
atorium+0.048
ratulations+0.044
 manoeuv+0.042
Downloadha+0.041
 scrape+0.040
Neg logit contributions
llan-0.043
 Luthor-0.041
oid-0.039
-0.037
exclusive-0.036
Token intuitive
Token ID19933
Feature activation-5.60e-01

Pos logit contributions
llan+0.277
 Luthor+0.263
oid+0.250
+0.232
exclusive+0.230
Neg logit contributions
atorium-0.342
ratulations-0.314
 manoeuv-0.298
Downloadha-0.289
 scrape-0.286
Token,
Token ID11
Feature activation-8.36e-04

Pos logit contributions
atorium+0.309
ratulations+0.278
 manoeuv+0.267
 scrape+0.256
Downloadha+0.254
Neg logit contributions
llan-0.295
 Luthor-0.279
oid-0.267
-0.253
exclusive-0.251
Token people
Token ID661
Feature activation-6.12e-01

Pos logit contributions
atorium+0.001
ratulations+0.001
 manoeuv+0.001
Downloadha+0.001
 scrape+0.001
Neg logit contributions
llan-0.001
 Luthor-0.001
oid-0.001
-0.001
exclusive-0.001
Token started
Token ID2067
Feature activation+3.16e-01

Pos logit contributions
atorium+0.522
ratulations+0.476
 manoeuv+0.449
Downloadha+0.437
 scrape+0.428
Neg logit contributions
llan-0.456
 Luthor-0.439
oid-0.420
-0.387
exclusive-0.383
Token tweeting
Token ID28990
Feature activation-9.74e-01

Pos logit contributions
llan+0.250
 Luthor+0.244
oid+0.233
+0.217
exclusive+0.213
Neg logit contributions
atorium-0.252
ratulations-0.230
 manoeuv-0.213
Downloadha-0.209
acebook-0.204
Token about
Token ID546
Feature activation+7.39e-01

Pos logit contributions
atorium+0.879
ratulations+0.803
 manoeuv+0.772
Downloadha+0.742
 scrape+0.740
Neg logit contributions
llan-0.674
 Luthor-0.639
oid-0.608
-0.567
exclusive-0.558
Token a
Token ID257
Feature activation+6.06e-01

Pos logit contributions
llan+0.569
 Luthor+0.550
oid+0.522
+0.488
exclusive+0.483
Neg logit contributions
atorium-0.605
ratulations-0.552
 manoeuv-0.523
Downloadha-0.504
 scrape-0.497
Token Detroit
Token ID8488
Feature activation-6.03e-01

Pos logit contributions
llan+0.489
 Luthor+0.470
oid+0.448
+0.422
exclusive+0.417
Neg logit contributions
atorium-0.476
ratulations-0.432
 manoeuv-0.409
Downloadha-0.394
 scrape-0.388
Token Pur
Token ID9330
Feature activation-3.97e-01

Pos logit contributions
atorium+0.383
ratulations+0.335
 manoeuv+0.317
 scrape+0.298
Downloadha+0.297
Neg logit contributions
llan-0.580
 Luthor-0.557
oid-0.538
-0.513
exclusive-0.507
Tokenge
Token ID469
Feature activation-7.40e-01

Pos logit contributions
atorium+0.230
ratulations+0.202
 manoeuv+0.189
Downloadha+0.182
 scrape+0.176
Neg logit contributions
llan-0.401
 Luthor-0.386
oid-0.374
-0.357
exclusive-0.355
Token.
Token ID13
Feature activation+3.41e-01

Pos logit contributions
atorium+0.617
ratulations+0.559
 manoeuv+0.535
Downloadha+0.512
 scrape+0.512
Neg logit contributions
llan-0.564
 Luthor-0.537
oid-0.513
-0.482
exclusive-0.475
Token Such
Token ID8013
Feature activation+6.83e-01

Pos logit contributions
llan+0.236
 Luthor+0.227
oid+0.214
+0.199
exclusive+0.195
Neg logit contributions
atorium-0.308
ratulations-0.287
 manoeuv-0.273
Downloadha-0.263
 scrape-0.261
TokenPan
Token ID15730
Feature activation-8.41e-01

Pos logit contributions
llan+0.085
 Luthor+0.081
oid+0.078
+0.073
exclusive+0.071
Neg logit contributions
atorium-0.093
ratulations-0.086
 manoeuv-0.082
Downloadha-0.078
 scrape-0.078
Token
Token ID198
Feature activation-1.12e+00

Pos logit contributions
atorium+0.721
ratulations+0.653
 manoeuv+0.628
Downloadha+0.602
 scrape+0.601
Neg logit contributions
llan-0.621
 Luthor-0.589
oid-0.559
-0.527
exclusive-0.519
Token
Token ID198
Feature activation-9.68e-01

Pos logit contributions
atorium+0.990
ratulations+0.927
everal+0.869
 manoeuv+0.866
Downloadha+0.850
Neg logit contributions
llan-0.809
 Luthor-0.762
oid-0.735
-0.671
exclusive-0.671
TokenAdvertisement
Token ID4723
Feature activation-8.53e-01

Pos logit contributions
atorium+0.924
ratulations+0.849
 manoeuv+0.818
Downloadha+0.788
 scrape+0.787
Neg logit contributions
llan-0.621
 Luthor-0.585
oid-0.555
-0.514
exclusive-0.506
Token
Token ID198
Feature activation-7.23e-01

Pos logit contributions
atorium+0.740
ratulations+0.687
 manoeuv+0.647
everal+0.632
Downloadha+0.628
Neg logit contributions
llan-0.625
 Luthor-0.590
oid-0.566
-0.524
exclusive-0.519
Token
Token ID198
Feature activation-5.93e-01

Pos logit contributions
atorium+0.640
ratulations+0.602
everal+0.566
 manoeuv+0.563
Downloadha+0.552
Neg logit contributions
llan-0.518
 Luthor-0.489
oid-0.470
-0.430
exclusive-0.428
TokenAs
Token ID1722
Feature activation+3.67e-01

Pos logit contributions
atorium+0.507
ratulations+0.465
 manoeuv+0.445
 scrape+0.426
Downloadha+0.425
Neg logit contributions
llan-0.440
 Luthor-0.417
oid-0.400
-0.374
exclusive-0.369
Token you
Token ID345
Feature activation-1.14e+00

Pos logit contributions
llan+0.271
 Luthor+0.259
oid+0.249
+0.231
exclusive+0.227
Neg logit contributions
atorium-0.313
ratulations-0.286
 manoeuv-0.273
 scrape-0.262
Downloadha-0.262
Token might
Token ID1244
Feature activation-6.35e-01

Pos logit contributions
atorium+0.988
ratulations+0.905
 manoeuv+0.839
Downloadha+0.839
acebook+0.823
Neg logit contributions
llan-0.841
 Luthor-0.798
oid-0.768
-0.706
exclusive-0.690
Token imagine
Token ID5967
Feature activation-1.78e+00

Pos logit contributions
atorium+0.538
ratulations+0.486
 manoeuv+0.466
Downloadha+0.452
 scrape+0.442
Neg logit contributions
llan-0.476
 Luthor-0.454
oid-0.436
-0.404
exclusive-0.398
Token,
Token ID11
Feature activation-2.74e-01

Pos logit contributions
atorium+1.408
ratulations+1.276
 manoeuv+1.221
Downloadha+1.177
 scrape+1.173
Neg logit contributions
llan-1.407
 Luthor-1.329
oid-1.259
exclusive-1.212
-1.210
Token fuel
Token ID5252
Feature activation-7.71e-02

Pos logit contributions
llan+0.051
 Luthor+0.048
oid+0.046
+0.043
exclusive+0.042
Neg logit contributions
atorium-0.064
ratulations-0.059
 manoeuv-0.056
Downloadha-0.054
 scrape-0.054
Token.
Token ID13
Feature activation+5.68e-01

Pos logit contributions
atorium+0.066
ratulations+0.060
 manoeuv+0.057
Downloadha+0.055
 scrape+0.055
Neg logit contributions
llan-0.057
 Luthor-0.054
oid-0.052
-0.049
exclusive-0.048
Token You
Token ID921
Feature activation-3.10e-01

Pos logit contributions
llan+0.410
 Luthor+0.389
oid+0.372
+0.346
exclusive+0.342
Neg logit contributions
atorium-0.496
ratulations-0.459
 manoeuv-0.434
Downloadha-0.419
 scrape-0.417
Token will
Token ID481
Feature activation+2.48e-01

Pos logit contributions
atorium+0.261
ratulations+0.239
 manoeuv+0.225
Downloadha+0.218
acebook+0.215
Neg logit contributions
llan-0.235
 Luthor-0.221
oid-0.214
-0.199
exclusive-0.196
Token always
Token ID1464
Feature activation-1.15e+00

Pos logit contributions
llan+0.181
 Luthor+0.172
oid+0.165
+0.151
exclusive+0.150
Neg logit contributions
atorium-0.214
ratulations-0.198
 manoeuv-0.185
Downloadha-0.184
acebook-0.181
Token naturally
Token ID8752
Feature activation-8.72e-01

Pos logit contributions
atorium+0.948
ratulations+0.866
 manoeuv+0.814
Downloadha+0.799
acebook+0.778
Neg logit contributions
llan-0.888
 Luthor-0.846
oid-0.814
-0.758
exclusive-0.746
Token eat
Token ID4483
Feature activation-7.34e-01

Pos logit contributions
atorium+0.689
ratulations+0.634
 manoeuv+0.585
Downloadha+0.583
acebook+0.565
Neg logit contributions
llan-0.700
 Luthor-0.668
oid-0.648
-0.601
exclusive-0.591
Token the
Token ID262
Feature activation-3.11e-02

Pos logit contributions
atorium+0.631
ratulations+0.577
 manoeuv+0.548
Downloadha+0.531
 scrape+0.524
Neg logit contributions
llan-0.541
 Luthor-0.515
oid-0.493
-0.458
exclusive-0.451
Token lowest
Token ID9016
Feature activation+3.75e-01

Pos logit contributions
atorium+0.028
ratulations+0.026
 manoeuv+0.025
Downloadha+0.024
 scrape+0.024
Neg logit contributions
llan-0.021
 Luthor-0.020
oid-0.019
-0.018
exclusive-0.017
Token calories
Token ID14653
Feature activation+1.08e+00

Pos logit contributions
llan+0.318
 Luthor+0.304
oid+0.292
+0.276
exclusive+0.272
Neg logit contributions
atorium-0.280
ratulations-0.252
 manoeuv-0.238
Downloadha-0.227
 scrape-0.226
Token when
Token ID618
Feature activation-1.07e-01

Pos logit contributions
llan+0.792
 Luthor+0.750
oid+0.718
+0.662
exclusive+0.649
Neg logit contributions
atorium-0.943
ratulations-0.868
 manoeuv-0.815
Downloadha-0.798
 scrape-0.778
Token up
Token ID510
Feature activation-3.30e-01

Pos logit contributions
atorium+0.055
ratulations+0.050
 manoeuv+0.047
Downloadha+0.046
 scrape+0.045
Neg logit contributions
llan-0.053
 Luthor-0.050
oid-0.048
-0.045
exclusive-0.045
Token stakes
Token ID21147
Feature activation+1.34e-01

Pos logit contributions
atorium+0.268
ratulations+0.244
 manoeuv+0.233
Downloadha+0.224
 scrape+0.221
Neg logit contributions
llan-0.259
 Luthor-0.247
oid-0.237
-0.221
exclusive-0.220
Token and
Token ID290
Feature activation+1.68e-01

Pos logit contributions
llan+0.094
 Luthor+0.088
oid+0.084
+0.079
exclusive+0.077
Neg logit contributions
atorium-0.120
ratulations-0.110
 manoeuv-0.105
Downloadha-0.101
 scrape-0.101
Token start
Token ID923
Feature activation+8.72e-01

Pos logit contributions
llan+0.138
 Luthor+0.133
oid+0.126
+0.119
exclusive+0.117
Neg logit contributions
atorium-0.128
ratulations-0.120
Downloadha-0.109
 manoeuv-0.108
brance-0.105
Token his
Token ID465
Feature activation+2.87e-01

Pos logit contributions
llan+0.709
 Luthor+0.678
oid+0.649
+0.610
essim+0.599
Neg logit contributions
atorium-0.683
ratulations-0.620
 manoeuv-0.579
Downloadha-0.566
acebook-0.553
Token franchise
Token ID8663
Feature activation-1.55e-01

Pos logit contributions
llan+0.231
 Luthor+0.220
oid+0.210
+0.198
exclusive+0.196
Neg logit contributions
atorium-0.227
ratulations-0.206
 manoeuv-0.195
Downloadha-0.188
 scrape-0.186
Token
Token ID447
Feature activation+1.02e-01

Pos logit contributions
atorium+0.136
ratulations+0.125
 manoeuv+0.119
Downloadha+0.115
 scrape+0.114
Neg logit contributions
llan-0.111
 Luthor-0.105
oid-0.100
-0.094
exclusive-0.092
Token
Token ID247
Feature activation+2.42e-01

Pos logit contributions
llan+0.061
 Luthor+0.057
oid+0.054
+0.050
exclusive+0.048
Neg logit contributions
atorium-0.101
ratulations-0.094
 manoeuv-0.091
Downloadha-0.088
 scrape-0.087
Tokens
Token ID82
Feature activation-2.40e-01

Pos logit contributions
llan+0.127
 Luthor+0.117
oid+0.110
+0.100
exclusive+0.098
Neg logit contributions
atorium-0.259
ratulations-0.241
 manoeuv-0.233
Downloadha-0.226
 scrape-0.225
Token title
Token ID3670
Feature activation-2.07e-01

Pos logit contributions
atorium+0.191
ratulations+0.173
 manoeuv+0.164
Downloadha+0.158
 scrape+0.156
Neg logit contributions
llan-0.193
 Luthor-0.184
oid-0.176
-0.165
exclusive-0.164
Token defense
Token ID3761
Feature activation-1.70e+00

Pos logit contributions
atorium+0.168
ratulations+0.152
 manoeuv+0.145
Downloadha+0.139
 scrape+0.138
Neg logit contributions
llan-0.162
 Luthor-0.155
oid-0.148
-0.140
exclusive-0.138
Token workforce
Token ID16433
Feature activation+1.26e+00

Pos logit contributions
llan+0.024
 Luthor+0.023
oid+0.022
+0.020
exclusive+0.020
Neg logit contributions
atorium-0.028
ratulations-0.026
 manoeuv-0.024
Downloadha-0.023
 scrape-0.023
Token than
Token ID621
Feature activation+6.63e-01

Pos logit contributions
llan+0.880
 Luthor+0.819
oid+0.795
+0.722
exclusive+0.711
Neg logit contributions
atorium-1.143
ratulations-1.055
 manoeuv-0.991
Downloadha-0.966
acebook-0.955
Token other
Token ID584
Feature activation+1.58e+00

Pos logit contributions
llan+0.511
 Luthor+0.488
oid+0.469
+0.438
exclusive+0.431
Neg logit contributions
atorium-0.543
ratulations-0.497
 manoeuv-0.466
Downloadha-0.453
 scrape-0.443
Token college
Token ID4152
Feature activation-1.16e+00

Pos logit contributions
llan+1.183
 Luthor+1.124
oid+1.092
+1.005
exclusive+0.984
Neg logit contributions
atorium-1.325
ratulations-1.215
 manoeuv-1.137
Downloadha-1.108
brance-1.097
Token-
Token ID12
Feature activation+2.79e-01

Pos logit contributions
atorium+0.970
ratulations+0.880
 manoeuv+0.845
 scrape+0.809
Downloadha+0.806
Neg logit contributions
llan-0.878
 Luthor-0.836
oid-0.796
-0.749
exclusive-0.739
Tokeneducated
Token ID27317
Feature activation-7.85e-01

Pos logit contributions
llan+0.143
 Luthor+0.133
oid+0.125
+0.112
exclusive+0.112
Neg logit contributions
atorium-0.301
ratulations-0.280
 manoeuv-0.271
Downloadha-0.263
 scrape-0.262
Token prime
Token ID6994
Feature activation+4.92e-01

Pos logit contributions
atorium+0.600
ratulations+0.541
 manoeuv+0.511
Downloadha+0.491
 scrape+0.485
Neg logit contributions
llan-0.654
 Luthor-0.624
oid-0.602
-0.566
exclusive-0.558
Token-
Token ID12
Feature activation+7.54e-01

Pos logit contributions
llan+0.358
 Luthor+0.340
oid+0.325
+0.304
exclusive+0.299
Neg logit contributions
atorium-0.426
ratulations-0.387
 manoeuv-0.371
Downloadha-0.357
 scrape-0.355
Tokenage
Token ID496
Feature activation+1.83e+00

Pos logit contributions
llan+0.617
 Luthor+0.594
oid+0.574
+0.540
exclusive+0.534
Neg logit contributions
atorium-0.579
ratulations-0.523
 manoeuv-0.497
Downloadha-0.474
 scrape-0.471
Token workers
Token ID3259
Feature activation+8.76e-01

Pos logit contributions
llan+1.502
 Luthor+1.437
oid+1.395
+1.302
exclusive+1.272
Neg logit contributions
atorium-1.413
ratulations-1.281
 manoeuv-1.195
Downloadha-1.163
brance-1.143
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
llan+0.640
 Luthor+0.604
oid+0.583
+0.542
exclusive+0.532
Neg logit contributions
atorium-0.761
ratulations-0.696
 manoeuv-0.661
Downloadha-0.635
 scrape-0.628
Token outcomes
Token ID10906
Feature activation+1.12e+00

Pos logit contributions
atorium+0.268
ratulations+0.242
 manoeuv+0.228
Downloadha+0.223
brance+0.218
Neg logit contributions
llan-0.258
 Luthor-0.247
oid-0.237
-0.219
exclusive-0.218
Token.
Token ID13
Feature activation-3.83e-01

Pos logit contributions
llan+0.705
 Luthor+0.663
oid+0.629
+0.579
exclusive+0.569
Neg logit contributions
atorium-1.078
ratulations-0.990
 manoeuv-0.952
Downloadha-0.920
 scrape-0.917
Token Ad
Token ID1215
Feature activation+1.24e+00

Pos logit contributions
atorium+0.330
ratulations+0.302
 manoeuv+0.289
Downloadha+0.277
 scrape+0.276
Neg logit contributions
llan-0.281
 Luthor-0.267
oid-0.255
-0.238
exclusive-0.235
Token Policy
Token ID7820
Feature activation-1.76e+00

Pos logit contributions
llan+0.950
 Luthor+0.904
oid+0.866
+0.810
exclusive+0.803
Neg logit contributions
atorium-1.028
ratulations-0.932
 manoeuv-0.893
Downloadha-0.858
 scrape-0.855
Token Click
Token ID6914
Feature activation+2.96e-01

Pos logit contributions
atorium+1.451
ratulations+1.317
 manoeuv+1.254
 scrape+1.207
Downloadha+1.203
Neg logit contributions
llan-1.344
 Luthor-1.284
oid-1.220
-1.148
exclusive-1.132
Token here
Token ID994
Feature activation-5.37e-01

Pos logit contributions
llan+0.189
 Luthor+0.177
oid+0.168
+0.156
exclusive+0.153
Neg logit contributions
atorium-0.284
ratulations-0.261
 manoeuv-0.250
Downloadha-0.243
 scrape-0.240
Token to
Token ID284
Feature activation+1.96e-02

Pos logit contributions
atorium+0.477
ratulations+0.433
 manoeuv+0.416
 scrape+0.403
Downloadha+0.399
Neg logit contributions
llan-0.380
 Luthor-0.361
oid-0.341
-0.322
exclusive-0.316
Token help
Token ID1037
Feature activation+2.55e-01

Pos logit contributions
llan+0.014
 Luthor+0.014
oid+0.013
+0.012
exclusive+0.012
Neg logit contributions
atorium-0.017
ratulations-0.016
 manoeuv-0.015
Downloadha-0.014
everal-0.014
Token prevent
Token ID2948
Feature activation+1.21e+00

Pos logit contributions
llan+0.201
 Luthor+0.193
oid+0.186
+0.173
exclusive+0.169
Neg logit contributions
atorium-0.206
ratulations-0.187
 manoeuv-0.175
Downloadha-0.172
brance-0.167
Token disenfranch
Token ID41307
Feature activation-1.85e+00

Pos logit contributions
llan+0.938
 Luthor+0.903
oid+0.859
+0.798
exclusive+0.793
Neg logit contributions
atorium-0.988
ratulations-0.887
 manoeuv-0.842
Downloadha-0.825
 scrape-0.807
Tokenis
Token ID271
Feature activation-1.09e+00

Pos logit contributions
atorium+1.540
ratulations+1.396
 manoeuv+1.336
Downloadha+1.279
 scrape+1.277
Neg logit contributions
llan-1.416
 Luthor-1.347
oid-1.288
-1.211
exclusive-1.194
Token has
Token ID468
Feature activation-1.70e-02

Pos logit contributions
atorium+0.352
ratulations+0.323
 manoeuv+0.306
Downloadha+0.297
 scrape+0.294
Neg logit contributions
llan-0.295
 Luthor-0.280
oid-0.269
-0.249
exclusive-0.245
Token also
Token ID635
Feature activation+1.08e+00

Pos logit contributions
atorium+0.015
ratulations+0.014
 manoeuv+0.013
Downloadha+0.013
acebook+0.013
Neg logit contributions
llan-0.012
 Luthor-0.012
oid-0.011
-0.010
exclusive-0.010
Token upset
Token ID9247
Feature activation+9.23e-03

Pos logit contributions
llan+0.779
 Luthor+0.745
oid+0.717
+0.646
exclusive+0.642
Neg logit contributions
atorium-0.947
ratulations-0.876
 manoeuv-0.813
Downloadha-0.809
acebook-0.797
Token defenders
Token ID16355
Feature activation-2.32e+00

Pos logit contributions
llan+0.008
 Luthor+0.007
oid+0.007
+0.006
exclusive+0.006
Neg logit contributions
atorium-0.007
ratulations-0.007
 manoeuv-0.006
Downloadha-0.006
 scrape-0.006
Token of
Token ID286
Feature activation-8.71e-02

Pos logit contributions
atorium+2.033
ratulations+1.843
 manoeuv+1.801
Downloadha+1.743
 scrape+1.714
Neg logit contributions
llan-1.608
 Luthor-1.553
oid-1.436
exclusive-1.383
-1.339
Token wom
Token ID1116
Feature activation-2.75e+00

Pos logit contributions
atorium+0.070
ratulations+0.064
 manoeuv+0.061
Downloadha+0.059
 scrape+0.058
Neg logit contributions
llan-0.068
 Luthor-0.065
oid-0.063
-0.059
exclusive-0.058
Tokenens
Token ID641
Feature activation-1.15e+00

Pos logit contributions
atorium+2.325
ratulations+2.083
 manoeuv+1.996
 scrape+1.891
brance+1.890
Neg logit contributions
llan-2.079
 Luthor-1.969
oid-1.859
-1.780
essim-1.726
Token
Token ID447
Feature activation-2.79e-01

Pos logit contributions
atorium+0.895
ratulations+0.796
 manoeuv+0.763
 scrape+0.726
Downloadha+0.721
Neg logit contributions
llan-0.949
 Luthor-0.908
oid-0.864
-0.823
exclusive-0.806
Token
Token ID247
Feature activation-3.53e-02

Pos logit contributions
atorium+0.264
ratulations+0.243
 manoeuv+0.234
Downloadha+0.226
 scrape+0.225
Neg logit contributions
llan-0.181
 Luthor-0.171
oid-0.162
-0.150
exclusive-0.148
Token rights
Token ID2489
Feature activation-6.05e-01

Pos logit contributions
atorium+0.036
ratulations+0.033
 manoeuv+0.032
 scrape+0.031
Downloadha+0.031
Neg logit contributions
llan-0.020
 Luthor-0.019
oid-0.017
-0.016
exclusive-0.016
Token in
Token ID287
Feature activation-3.85e-01

Pos logit contributions
atorium+0.523
ratulations+0.476
 manoeuv+0.455
Downloadha+0.437
 scrape+0.436
Neg logit contributions
llan-0.443
 Luthor-0.420
oid-0.402
-0.376
exclusive-0.370
Token settings
Token ID6460
Feature activation-5.19e-01

Pos logit contributions
llan+0.346
 Luthor+0.324
oid+0.312
+0.287
exclusive+0.285
Neg logit contributions
atorium-0.418
ratulations-0.382
 manoeuv-0.358
Downloadha-0.357
everal-0.347
Token to
Token ID284
Feature activation+8.12e-01

Pos logit contributions
atorium+0.450
ratulations+0.409
 manoeuv+0.386
Downloadha+0.379
 scrape+0.372
Neg logit contributions
llan-0.383
 Luthor-0.363
oid-0.347
-0.322
exclusive-0.317
Token be
Token ID307
Feature activation+5.88e-01

Pos logit contributions
llan+0.642
 Luthor+0.616
oid+0.591
+0.548
essim+0.532
Neg logit contributions
atorium-0.657
ratulations-0.611
Downloadha-0.568
everal-0.543
acebook-0.543
Token able
Token ID1498
Feature activation-1.73e+00

Pos logit contributions
llan+0.471
 Luthor+0.454
oid+0.430
+0.403
exclusive+0.402
Neg logit contributions
atorium-0.467
ratulations-0.427
Downloadha-0.394
 manoeuv-0.381
everal-0.379
Token to
Token ID284
Feature activation-8.66e-01

Pos logit contributions
atorium+1.631
ratulations+1.510
 manoeuv+1.416
Downloadha+1.399
everal+1.397
Neg logit contributions
llan-1.147
 Luthor-1.073
oid-1.025
-0.936
exclusive-0.924
Token post
Token ID1281
Feature activation-3.14e+00

Pos logit contributions
atorium+0.695
ratulations+0.641
Downloadha+0.595
everal+0.576
acebook+0.573
Neg logit contributions
llan-0.691
 Luthor-0.661
oid-0.638
-0.588
exclusive-0.577
Token such
Token ID884
Feature activation+2.40e-01

Pos logit contributions
atorium+2.513
ratulations+2.270
 manoeuv+2.166
Downloadha+2.073
 scrape+2.067
Neg logit contributions
llan-2.493
 Luthor-2.376
oid-2.277
-2.146
exclusive-2.116
Token quick
Token ID2068
Feature activation-1.06e+00

Pos logit contributions
llan+0.178
 Luthor+0.169
oid+0.161
+0.148
exclusive+0.148
Neg logit contributions
atorium-0.206
ratulations-0.188
Downloadha-0.174
 manoeuv-0.173
 scrape-0.169
Token times
Token ID1661
Feature activation-3.54e-01

Pos logit contributions
atorium+0.855
ratulations+0.773
 manoeuv+0.720
Downloadha+0.710
 scrape+0.695
Neg logit contributions
llan-0.849
 Luthor-0.803
oid-0.775
-0.724
exclusive-0.714
Token.
Token ID13
Feature activation-1.34e-01

Pos logit contributions
atorium+0.305
ratulations+0.278
 manoeuv+0.262
Downloadha+0.255
 scrape+0.252
Neg logit contributions
llan-0.263
 Luthor-0.249
oid-0.239
-0.222
exclusive-0.218
Token He
Token ID679
Feature activation+1.44e-02

Pos logit contributions
atorium+0.120
ratulations+0.111
 manoeuv+0.105
Downloadha+0.102
 scrape+0.101
Neg logit contributions
llan-0.094
 Luthor-0.090
oid-0.085
-0.080
exclusive-0.078
Token plans
Token ID3352
Feature activation+9.48e-01

Pos logit contributions
llan+0.455
 Luthor+0.433
oid+0.417
+0.377
exclusive+0.377
Neg logit contributions
atorium-0.548
ratulations-0.509
 manoeuv-0.475
Downloadha-0.474
everal-0.467
Token to
Token ID284
Feature activation+1.67e-02

Pos logit contributions
llan+0.668
 Luthor+0.636
oid+0.603
+0.566
exclusive+0.555
Neg logit contributions
atorium-0.850
ratulations-0.771
 manoeuv-0.743
Downloadha-0.710
 scrape-0.710
Token begin
Token ID2221
Feature activation-2.83e-01

Pos logit contributions
llan+0.013
 Luthor+0.013
oid+0.012
+0.011
exclusive+0.011
Neg logit contributions
atorium-0.013
ratulations-0.012
Downloadha-0.012
everal-0.011
acebook-0.011
Token a
Token ID257
Feature activation+1.12e-01

Pos logit contributions
atorium+0.216
ratulations+0.196
 manoeuv+0.183
Downloadha+0.180
 scrape+0.175
Neg logit contributions
llan-0.236
 Luthor-0.224
oid-0.216
-0.201
exclusive-0.200
Token "
Token ID366
Feature activation+2.43e-01

Pos logit contributions
llan+0.096
 Luthor+0.091
oid+0.088
+0.082
exclusive+0.082
Neg logit contributions
atorium-0.083
ratulations-0.076
 manoeuv-0.070
Downloadha-0.068
 scrape-0.066
Tokenpublic
Token ID11377
Feature activation-2.73e+00

Pos logit contributions
llan+0.183
 Luthor+0.172
oid+0.166
+0.155
exclusive+0.154
Neg logit contributions
atorium-0.205
ratulations-0.187
 manoeuv-0.179
 scrape-0.172
Downloadha-0.171
Token dialogue
Token ID10721
Feature activation-3.49e-02

Pos logit contributions
atorium+2.243
ratulations+2.032
 manoeuv+1.944
Downloadha+1.861
 scrape+1.856
Neg logit contributions
llan-2.107
 Luthor-2.005
oid-1.920
-1.805
exclusive-1.780
Token"
Token ID1
Feature activation-1.37e+00

Pos logit contributions
atorium+0.026
ratulations+0.023
 manoeuv+0.022
Downloadha+0.021
 scrape+0.021
Neg logit contributions
llan-0.030
 Luthor-0.028
oid-0.027
-0.026
exclusive-0.025
Token surrounding
Token ID7346
Feature activation-5.01e-01

Pos logit contributions
atorium+1.260
ratulations+1.161
 manoeuv+1.105
Downloadha+1.076
 scrape+1.065
Neg logit contributions
llan-0.919
 Luthor-0.868
oid-0.827
-0.760
exclusive-0.752
Token lowering
Token ID21683
Feature activation-4.70e-01

Pos logit contributions
atorium+0.400
ratulations+0.363
 manoeuv+0.344
Downloadha+0.331
 scrape+0.330
Neg logit contributions
llan-0.400
 Luthor-0.381
oid-0.365
-0.341
exclusive-0.339
Token nicotine
Token ID21856
Feature activation+1.72e+00

Pos logit contributions
atorium+0.378
ratulations+0.340
 manoeuv+0.326
 scrape+0.311
Downloadha+0.311
Neg logit contributions
llan-0.371
 Luthor-0.354
oid-0.339
-0.321
exclusive-0.315
Token years
Token ID812
Feature activation+8.47e-01

Pos logit contributions
llan+0.540
 Luthor+0.514
oid+0.493
+0.462
exclusive+0.457
Neg logit contributions
atorium-0.552
ratulations-0.501
 manoeuv-0.475
Downloadha-0.456
 scrape-0.455
Token built
Token ID3170
Feature activation+1.46e+00

Pos logit contributions
llan+0.636
 Luthor+0.604
oid+0.579
exclusive+0.531
+0.529
Neg logit contributions
atorium-0.721
ratulations-0.662
 manoeuv-0.616
Downloadha-0.603
acebook-0.592
Token upon
Token ID2402
Feature activation+5.92e-01

Pos logit contributions
llan+1.117
 Luthor+1.063
oid+1.023
+0.956
exclusive+0.939
Neg logit contributions
atorium-1.196
ratulations-1.091
 manoeuv-1.031
Downloadha-1.004
 scrape-0.995
Token the
Token ID262
Feature activation+7.00e-03

Pos logit contributions
llan+0.452
 Luthor+0.433
oid+0.414
+0.385
exclusive+0.382
Neg logit contributions
atorium-0.491
ratulations-0.448
 manoeuv-0.422
Downloadha-0.411
 scrape-0.405
Token ratio
Token ID8064
Feature activation-5.38e-01

Pos logit contributions
llan+0.005
 Luthor+0.005
oid+0.005
+0.005
exclusive+0.005
Neg logit contributions
atorium-0.006
ratulations-0.005
 manoeuv-0.005
Downloadha-0.005
 scrape-0.005
Token stock
Token ID4283
Feature activation-3.37e+00

Pos logit contributions
atorium+0.511
ratulations+0.470
 manoeuv+0.450
Downloadha+0.435
 scrape+0.434
Neg logit contributions
llan-0.349
 Luthor-0.328
oid-0.313
-0.288
exclusive-0.284
Token/
Token ID14
Feature activation+9.42e-01

Pos logit contributions
atorium+2.989
ratulations+2.721
 manoeuv+2.641
 scrape+2.501
Downloadha+2.492
Neg logit contributions
llan-2.370
 Luthor-2.252
oid-2.125
-2.004
exclusive-1.978
Token (
Token ID357
Feature activation+2.92e-01

Pos logit contributions
llan+0.705
 Luthor+0.665
oid+0.641
+0.599
exclusive+0.593
Neg logit contributions
atorium-0.798
ratulations-0.730
 manoeuv-0.696
Downloadha-0.669
 scrape-0.667
Tokenyear
Token ID1941
Feature activation-1.18e-01

Pos logit contributions
llan+0.216
 Luthor+0.204
oid+0.196
+0.184
exclusive+0.182
Neg logit contributions
atorium-0.251
ratulations-0.229
 manoeuv-0.219
Downloadha-0.210
 scrape-0.210
Tokenly
Token ID306
Feature activation+1.19e+00

Pos logit contributions
atorium+0.103
ratulations+0.094
 manoeuv+0.090
Downloadha+0.086
 scrape+0.086
Neg logit contributions
llan-0.086
 Luthor-0.081
oid-0.078
-0.073
exclusive-0.072
Token absorption
Token ID24774
Feature activation+3.68e-01

Pos logit contributions
llan+0.907
 Luthor+0.857
oid+0.826
+0.771
exclusive+0.760
Neg logit contributions
atorium-0.985
ratulations-0.899
 manoeuv-0.845
Downloadha-0.823
 scrape-0.810
Token tele
Token ID5735
Feature activation+1.77e-01

Pos logit contributions
llan+2.064
 Luthor+1.970
oid+1.873
+1.747
exclusive+1.719
Neg logit contributions
atorium-2.408
ratulations-2.199
 manoeuv-2.105
Downloadha-2.037
 scrape-2.002
TokenS
Token ID50
Feature activation+4.73e-01

Pos logit contributions
llan+0.133
 Luthor+0.126
oid+0.121
+0.113
exclusive+0.112
Neg logit contributions
atorium-0.149
ratulations-0.136
 manoeuv-0.130
Downloadha-0.124
 scrape-0.124
TokenUR
Token ID4261
Feature activation+1.05e+00

Pos logit contributions
llan+0.451
 Luthor+0.428
oid+0.420
+0.395
exclusive+0.394
Neg logit contributions
atorium-0.304
ratulations-0.270
 manoeuv-0.253
Downloadha-0.243
 scrape-0.238
Token English
Token ID3594
Feature activation+7.41e-01

Pos logit contributions
llan+0.822
 Luthor+0.780
oid+0.755
+0.706
exclusive+0.699
Neg logit contributions
atorium-0.852
ratulations-0.777
 manoeuv-0.743
Downloadha-0.712
 scrape-0.705
Token (@
Token ID4275
Feature activation-5.82e-01

Pos logit contributions
llan+0.594
 Luthor+0.566
oid+0.545
+0.511
exclusive+0.504
Neg logit contributions
atorium-0.585
ratulations-0.532
 manoeuv-0.508
Downloadha-0.488
 scrape-0.483
Tokentel
Token ID37524
Feature activation-2.90e+00

Pos logit contributions
atorium+0.449
ratulations+0.404
 manoeuv+0.385
 scrape+0.367
Downloadha+0.367
Neg logit contributions
llan-0.480
 Luthor-0.458
oid-0.440
-0.416
exclusive-0.411
Tokenes
Token ID274
Feature activation+1.55e+00

Pos logit contributions
atorium+2.668
ratulations+2.421
 manoeuv+2.332
Downloadha+2.256
 scrape+2.233
Neg logit contributions
llan-1.954
 Luthor-1.863
oid-1.740
-1.637
exclusive-1.602
Tokenure
Token ID495
Feature activation-3.95e-01

Pos logit contributions
llan+1.334
 Luthor+1.264
oid+1.231
+1.159
exclusive+1.150
Neg logit contributions
atorium-1.138
ratulations-1.021
 manoeuv-0.970
 scrape-0.924
Downloadha-0.922
Tokenng
Token ID782
Feature activation-4.70e-01

Pos logit contributions
atorium+0.338
ratulations+0.307
 manoeuv+0.294
Downloadha+0.283
 scrape+0.281
Neg logit contributions
llan-0.290
 Luthor-0.278
oid-0.264
-0.248
exclusive-0.243
Tokenlish
Token ID1836
Feature activation-7.98e-01

Pos logit contributions
atorium+0.407
ratulations+0.371
 manoeuv+0.357
 scrape+0.342
Downloadha+0.342
Neg logit contributions
llan-0.343
 Luthor-0.321
oid-0.311
-0.288
exclusive-0.286
Token)
Token ID8
Feature activation+1.21e+00

Pos logit contributions
atorium+0.653
ratulations+0.586
 manoeuv+0.559
Downloadha+0.536
 scrape+0.534
Neg logit contributions
llan-0.615
 Luthor-0.601
oid-0.562
-0.534
exclusive-0.521