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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quot
    -0.17
    ÅĽÄĩ
    -0.15
     ÎĶημο
    -0.14
    rogram
    -0.14
    anzi
    -0.14
    99
    -0.14
     Nel
    -0.14
    perm
    -0.14
     addCriterion
    -0.14
    readcr
    -0.14
    POSITIVE LOGITS
     Cros
    0.16
    tu
    0.15
    برÛĮ
    0.14
    едеÑĢа
    0.14
    /respond
    0.14
    dra
    0.13
     Rodrigo
    0.13
    .pic
    0.13
    oxy
    0.13
    IW
    0.13
    Act Density 0.000%

    No Known Activations