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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and test structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilation
    -0.16
    osi
    -0.15
     Silent
    -0.15
     Sharp
    -0.14
     Harden
    -0.14
    ullo
    -0.14
    villa
    -0.13
    atan
    -0.13
    oya
    -0.13
    ahan
    -0.13
    POSITIVE LOGITS
    !=(
    0.15
    ispens
    0.14
    eÄį
    0.14
    .Output
    0.14
    edio
    0.13
    _dispatcher
    0.13
    Äįan
    0.13
    Ø´Ùĩ
    0.13
    smouth
    0.13
    ottle
    0.13
    Act Density 0.005%

    No Known Activations