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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or responses to challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apos
    -0.16
    errick
    -0.15
    çŃĭ
    -0.15
    zioni
    -0.14
    fern
    -0.14
    bos
    -0.14
    TOTYPE
    -0.14
    terra
    -0.13
    isset
    -0.13
    ustin
    -0.13
    POSITIVE LOGITS
    cente
    0.16
     Gros
    0.14
    mlink
    0.14
     Dün
    0.14
    igo
    0.14
    H
    0.13
    CBC
    0.13
     occasion
    0.13
    ipeg
    0.13
     Giang
    0.13
    Act Density 2.369%

    No Known Activations