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

    Neuronpedia

    INDEX
    Explanations

    quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Innoc
    -0.17
    aran
    -0.17
    bane
    -0.15
    witch
    -0.15
    atan
    -0.15
    inp
    -0.15
    иÑģÑĮ
    -0.14
    insky
    -0.14
    uentes
    -0.14
    optgroup
    -0.14
    POSITIVE LOGITS
    avy
    0.18
    errer
    0.16
    ocos
    0.14
    azo
    0.14
    mand
    0.13
     اختص
    0.13
    urm
    0.13
    oga
    0.13
    MAND
    0.13
    Äįer
    0.13
    Act Density 0.034%

    No Known Activations