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

    Neuronpedia

    INDEX
    Explanations

    codes, symbols, and specific text formats

    oai_token-act-pair · gpt-3.5-turbo

    special characters and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibles
    -0.70
    Reviewer
    -0.70
     FAT
    -0.65
     negatives
    -0.63
    ifice
    -0.63
    sonian
    -0.62
     attendance
    -0.61
    agonist
    -0.60
    gencies
    -0.59
     experien
    -0.59
    POSITIVE LOGITS
    enza
    0.87
    ¯
    0.67
    ();
    0.67
    uph
    0.64
    rio
    0.64
    ear
    0.61
    (),
    0.61
    `.
    0.60
    +(
    0.60
    ç
    0.59
    Act Density 0.347%

    No Known Activations