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

    Neuronpedia

    INDEX
    Explanations

    names and labels that signify important concepts, entities, or numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    slu
    -0.16
     wre
    -0.15
    Late
    -0.15
    udic
    -0.14
    ahu
    -0.14
    alez
    -0.14
    exo
    -0.14
    ucceed
    -0.14
    cre
    -0.14
    ereco
    -0.13
    POSITIVE LOGITS
    hetto
    0.15
     Cruiser
    0.14
    릿
    0.14
    Ð¤ÐĽ
    0.13
     Pet
    0.13
    ünd
    0.13
    uzz
    0.13
    .crt
    0.12
    _residual
    0.12
    plotlib
    0.12
    Act Density 0.015%

    No Known Activations