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

    Neuronpedia

    INDEX
    Explanations

    opinions on social dynamics and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rze
    -0.16
    ../../../../
    -0.15
    olina
    -0.15
    quila
    -0.15
    .GroupLayout
    -0.14
    ovny
    -0.14
    anko
    -0.14
    cmath
    -0.14
    ÙĩÙĨÚ¯
    -0.14
    stras
    -0.14
    POSITIVE LOGITS
     but
    0.18
     and
    0.15
    vik
    0.15
     yani
    0.15
     which
    0.14
     however
    0.14
    kir
    0.14
    mans
    0.13
    _
    0.13
    (
    0.13
    Act Density 0.867%

    No Known Activations