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

    Neuronpedia

    INDEX
    Explanations

    numeric values and statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igar
    -0.17
    oldt
    -0.17
    adium
    -0.15
    mares
    -0.14
     Parm
    -0.14
    laus
    -0.14
     perfection
    -0.14
     Sno
    -0.14
    eto
    -0.14
    pto
    -0.14
    POSITIVE LOGITS
    IID
    0.15
    زار
    0.15
    esser
    0.15
    ANDLE
    0.14
    redient
    0.14
    ryn
    0.14
    .inline
    0.14
    ãĥ¥ãĥ¼
    0.14
    UNT
    0.14
    odash
    0.13
    Act Density 0.031%

    No Known Activations