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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual usage in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //{{
    -0.17
    veis
    -0.15
    Ñİк
    -0.15
    gesi
    -0.14
    gili
    -0.14
    ventario
    -0.14
    ái
    -0.14
    /rss
    -0.13
    /fa
    -0.13
    Äįen
    -0.13
    POSITIVE LOGITS
    acre
    0.16
    usat
    0.15
    ac
    0.15
    aci
    0.15
    345
    0.15
    omes
    0.14
    _pb
    0.14
    es
    0.14
     Hem
    0.14
    ilit
    0.14
    Act Density 0.102%

    No Known Activations