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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases that indicate actions or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lyph
    -0.17
    OMPI
    -0.17
    ampo
    -0.17
    inston
    -0.16
    漫
    -0.16
    овиÑĩ
    -0.16
    lyn
    -0.15
    é©ļ
    -0.15
    owi
    -0.15
    æ¬ł
    -0.15
    POSITIVE LOGITS
    /docs
    0.15
    .config
    0.15
     jam
    0.14
    puted
    0.14
    er
    0.14
    216
    0.14
    hq
    0.14
    ars
    0.14
    avel
    0.14
    elter
    0.14
    Act Density 0.030%

    No Known Activations