INDEX
Explanations
instances of the word "count" and its variations
New Auto-Interp
Negative Logits
ifax
-0.72
onne
-0.69
nesia
-0.69
lan
-0.69
stress
-0.68
OA
-0.67
ienne
-0.67
aunt
-0.66
••
-0.65
────
-0.62
POSITIVE LOGITS
%%
0.68
plum
0.67
ebus
0.66
raspberry
0.65
itself
0.62
yourself
0.59
utherford
0.58
tops
0.58
ppers
0.58
ighth
0.57
Activations Density 0.014%