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

    Neuronpedia

    INDEX
    Explanations

    structured language and references to categorical organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olle
    -0.17
    ima
    -0.16
    AMA
    -0.14
    innacle
    -0.14
     Carpenter
    -0.14
    wil
    -0.14
     funny
    -0.14
    ighb
    -0.14
    IMA
    -0.13
     Worker
    -0.13
    POSITIVE LOGITS
    pped
    0.16
    _VALIDATE
    0.16
    iec
    0.15
    à¥įयत
    0.15
    æ¡£
    0.14
    straint
    0.14
    ستر
    0.14
    .Doc
    0.14
    eyn
    0.14
    adeon
    0.14
    Act Density 0.042%

    No Known Activations