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

    Neuronpedia

    INDEX
    Explanations

    words related to programming constructs and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctp
    -0.16
    ucz
    -0.15
    __;
    -0.14
    ecure
    -0.13
    ÑĤин
    -0.13
    wang
    -0.13
    ôi
    -0.13
    loser
    -0.13
    abilities
    -0.13
    едак
    -0.13
    POSITIVE LOGITS
    ration
    0.18
    als
    0.17
    alse
    0.17
    ulers
    0.15
    ivas
    0.14
    FUN
    0.14
    izer
    0.14
    ÙĬار
    0.13
    phis
    0.13
    лÑı
    0.13
    Act Density 0.001%

    No Known Activations