INDEX
Explanations
the word "ones" in various contexts
phrases that refer to individuals or groups as "the ones" in various contexts
New Auto-Interp
Negative Logits
osponsors
-0.71
ITED
-0.63
ORY
-0.62
SEA
-0.61
SOC
-0.60
anyahu
-0.60
Consent
-0.59
Thumbnail
-0.59
CDC
-0.59
Cl
-0.58
POSITIVE LOGITS
hots
1.02
eyed
0.80
omething
0.76
elf
0.74
Hundred
0.73
oxide
0.73
Obi
0.71
cott
0.69
hon
0.68
hot
0.68
Activations Density 0.013%