INDEX
Explanations
references to nostalgia and memories
New Auto-Interp
Negative Logits
witness
-0.16
bef
-0.14
Silence
-0.14
&#
-0.13
stu
-0.13
utorial
-0.13
mk
-0.13
509
-0.13
ano
-0.13
learn
-0.13
POSITIVE LOGITS
memories
0.41
nostalgia
0.39
fond
0.39
nostalg
0.37
nostalgic
0.34
Memories
0.34
nost
0.32
memory
0.32
reminis
0.32
Fond
0.31
Activations Density 0.144%