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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their positions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ñ
    -0.15
     audition
    -0.15
    fig
    -0.15
     brief
    -0.15
    -0.14
    !
    -0.14
    áb
    -0.14
     Peoples
    -0.13
    ä¼
    -0.13
     donc
    -0.13
    POSITIVE LOGITS
    enment
    0.17
    VISIBLE
    0.16
    visible
    0.15
    .credit
    0.15
    Ñľ
    0.14
    ilan
    0.14
    pling
    0.14
     Credit
    0.14
    aval
    0.14
     credit
    0.14
    Act Density 0.033%

    No Known Activations