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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate alternatives or substitutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    POCH
    -0.16
    cope
    -0.16
    dni
    -0.15
     Bor
    -0.15
    ogl
    -0.15
    ittal
    -0.14
    isu
    -0.14
     sho
    -0.14
    din
    -0.14
    -gap
    -0.14
    POSITIVE LOGITS
    idual
    0.15
    instead
    0.15
    ĶåĽŀ
    0.15
    chaft
    0.15
     instead
    0.15
    touches
    0.14
     poly
    0.14
    vez
    0.14
    swick
    0.14
    holm
    0.14
    Act Density 0.014%

    No Known Activations