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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to programming and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    woff
    -0.17
    ONTAL
    -0.16
     Gors
    -0.15
    pong
    -0.15
    loo
    -0.15
    olis
    -0.15
    Courier
    -0.15
    aned
    -0.15
    iloc
    -0.15
     è¯
    -0.15
    POSITIVE LOGITS
    ADR
    0.15
    nah
    0.14
    semble
    0.14
    WH
    0.14
    wh
    0.14
    zman
    0.14
    apı
    0.14
    shot
    0.14
    sem
    0.13
    Ïĥαν
    0.13
    Act Density 0.001%

    No Known Activations