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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or personal belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aight
    -0.15
    ĤŃ
    -0.15
    á»ĭnh
    -0.14
    iers
    -0.14
    ants
    -0.14
    bilder
    -0.14
    ksi
    -0.14
    ka
    -0.14
    abor
    -0.14
    imum
    -0.13
    POSITIVE LOGITS
    .NewRequest
    0.16
    TU
    0.16
    agate
    0.16
    edla
    0.15
    zik
    0.15
    fen
    0.15
    oose
    0.15
    ingleton
    0.15
    addock
    0.15
    usan
    0.15
    Act Density 0.017%

    No Known Activations