INDEX
Explanations
terms related to a specific name, "alf"
references to the character Gandalf from fantasy literature
New Auto-Interp
Negative Logits
Exhibit
-0.71
MIT
-0.69
receptive
-0.66
culture
-0.65
inventive
-0.59
bub
-0.58
Syndicate
-0.58
perme
-0.58
TPP
-0.57
SPONSORED
-0.57
POSITIVE LOGITS
alf
1.73
onso
1.21
unction
1.06
ornia
1.02
ieri
0.97
eatures
0.96
roth
0.94
sson
0.94
ilst
0.92
urion
0.89
Activations Density 0.006%