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

    Neuronpedia

    INDEX
    Explanations

    numeric values and punctuation, indicating its focus on structured data or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    trap
    -0.16
    erus
    -0.15
    kin
    -0.15
    altar
    -0.15
    plash
    -0.15
    gid
    -0.14
    itra
    -0.14
    .TestTools
    -0.14
    FRING
    -0.14
     crossorigin
    -0.13
    POSITIVE LOGITS
    ιά
    0.16
    arrison
    0.15
    dana
    0.15
    iah
    0.15
    ovah
    0.15
    .Exists
    0.14
    á»ģn
    0.14
    üç
    0.14
    ials
    0.14
    овÑĸ
    0.14
    Act Density 0.002%

    No Known Activations