Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hypothetical variables and their interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     v
    -0.45
    (
    -0.43
     my
    -0.41
     mon
    -0.40
     by
    -0.39
    .
    -0.38
     lateral
    -0.37
     it
    -0.36
     to
    -0.36
    \
    -0.35
    POSITIVE LOGITS
    Portail
    1.07
    1.06
     تضيفلها
    1.04
     صوتيه
    1.02
     للاسماء
    0.98
    CloseOperation
    0.95
    Datuak
    0.94
     незавершена
    0.93
     nahilalakip
    0.92
     Réponses
    0.91
    Act Density 0.870%

    No Known Activations