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

    Neuronpedia

    INDEX
    Explanations

    references to academic publication metrics and bibliographic details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Half
    -0.16
    353
    -0.14
    inger
    -0.14
     Secret
    -0.14
     bir
    -0.14
    gard
    -0.14
     Line
    -0.13
     half
    -0.13
    Half
    -0.13
     Eins
    -0.13
    POSITIVE LOGITS
    Integral
    0.17
    ebo
    0.15
    CTYPE
    0.15
    quette
    0.15
    YRO
    0.15
    rico
    0.14
    ISO
    0.14
    .getOwnProperty
    0.14
    luk
    0.14
    ì§ľ
    0.14
    Act Density 0.004%

    No Known Activations