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

    Neuronpedia

    INDEX
    Explanations

    actions related to the approval or cancelation of processes and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enu
    -0.19
    ATED
    -0.17
    ATING
    -0.16
    oad
    -0.15
    isé
    -0.15
    ont
    -0.15
    CID
    -0.14
     LENG
    -0.14
    finder
    -0.14
    enaire
    -0.14
    POSITIVE LOGITS
    ment
    0.40
    ance
    0.35
    iture
    0.29
    ances
    0.28
    als
    0.28
    rence
    0.27
    ption
    0.27
    ments
    0.26
    MENT
    0.26
    edException
    0.22
    Act Density 0.046%

    No Known Activations