INDEX
Explanations
numerical values and references in the text
New Auto-Interp
Negative Logits
Sem
-0.55
RICAL
-0.53
icznej
-0.49
toallas
-0.49
Steinberg
-0.48
sem
-0.47
(!__
-0.47
rasco
-0.47
lü
-0.46
rgba
-0.46
POSITIVE LOGITS
myſelf
1.01
Majefty
0.97
Houſe
0.96
purpoſe
0.91
raiſ
0.89
pleaſure
0.89
itſelf
0.89
Monfieur
0.85
fubject
0.83
houſe
0.80
Activations Density 0.329%