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

    Neuronpedia

    INDEX
    Explanations

    inquiries focused on consequences, values, or differentiations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ков
    -0.15
    abant
    -0.14
     Blasio
    -0.14
    brero
    -0.14
    ellan
    -0.14
    ypse
    -0.14
    еÑģÑı
    -0.14
    villa
    -0.14
     минÑĥ
    -0.14
    fillType
    -0.13
    POSITIVE LOGITS
    mploy
    0.15
     ul
    0.14
    OutOfBounds
    0.14
     êµ
    0.14
    ανά
    0.14
    avel
    0.14
    -archive
    0.14
     l
    0.14
     tbody
    0.14
    éº
    0.14
    Act Density 0.117%

    No Known Activations