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

    Neuronpedia

    INDEX
    Explanations

    instances of specific abbreviations or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wins
    -0.17
     Literal
    -0.17
    IAL
    -0.15
    .scalablytyped
    -0.15
    uegos
    -0.15
    кон
    -0.15
    ãģįãģŁ
    -0.15
    oppable
    -0.15
    clair
    -0.15
    ivial
    -0.15
    POSITIVE LOGITS
    ies
    0.19
    rence
    0.18
    onder
    0.18
    ry
    0.17
    arrants
    0.17
    itzer
    0.17
    ett
    0.16
    renc
    0.16
    ishment
    0.16
    ropa
    0.16
    Act Density 0.432%

    No Known Activations