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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Schneider
    -0.16
    ozo
    -0.15
     Ich
    -0.15
    ptal
    -0.14
    ãĥ¼ãĥ
    -0.14
    -old
    -0.14
    apon
    -0.14
    sez
    -0.14
    ics
    -0.13
    AZE
    -0.13
    POSITIVE LOGITS
    TOTYPE
    0.18
    omba
    0.16
    ald
    0.15
     vari
    0.15
    ivet
    0.14
    elry
    0.14
    364
    0.14
    pared
    0.13
    /Peak
    0.13
    ffe
    0.13
    Act Density 0.142%

    No Known Activations