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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating improbability or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iska
    -0.16
    GED
    -0.15
    zá
    -0.14
    ULA
    -0.14
    ula
    -0.14
    akis
    -0.14
    Ậ
    -0.14
    adil
    -0.13
    orra
    -0.13
    _DST
    -0.13
    POSITIVE LOGITS
    dub
    0.16
    apor
    0.15
    erde
    0.15
    /ext
    0.14
    ugin
    0.13
    klä
    0.13
    erin
    0.13
    olo
    0.13
    _singleton
    0.13
    br
    0.13
    Act Density 0.003%

    No Known Activations