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

    Neuronpedia

    INDEX
    Explanations

    interactions between characters in social situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [js
    -0.15
    _NR
    -0.14
     æĽ
    -0.14
     dó
    -0.14
     Nam
    -0.14
    .throw
    -0.14
     globally
    -0.13
    meld
    -0.13
    AGES
    -0.13
    ija
    -0.13
    POSITIVE LOGITS
    xec
    0.15
    íı¬
    0.15
     Oro
    0.14
     EXEMPLARY
    0.14
    sti
    0.14
    åij¢
    0.14
    zb
    0.14
    Äł
    0.13
    azen
    0.13
    rans
    0.13
    Act Density 0.325%

    No Known Activations