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

    Neuronpedia

    INDEX
    Explanations

    terms indicating inclusivity across various categories or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antu
    -0.15
    æ°Ĺ
    -0.15
    ARED
    -0.14
    ajas
    -0.14
    été
    -0.14
    aret
    -0.14
     inherent
    -0.14
    etre
    -0.13
    iscopal
    -0.13
    oul
    -0.13
    POSITIVE LOGITS
    clair
    0.15
    edes
    0.15
    achine
    0.15
    _shortcode
    0.14
    Delegate
    0.14
     spect
    0.14
     Matchers
    0.14
    ucker
    0.14
    smouth
    0.14
    elles
    0.14
    Act Density 0.087%

    No Known Activations