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

    Neuronpedia

    INDEX
    Explanations

    strings with equal signs

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting symbols commonly used in structured data or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !'
    -1.18
    .'
    -1.17
    ?'
    -1.16
    ,'
    -1.08
    )'
    -0.92
    '.
    -0.89
    .'"
    -0.87
    ?'"
    -0.82
    !'"
    -0.82
    »
    -0.81
    POSITIVE LOGITS
     "
    2.10
     "'
    1.87
     "-
    1.85
     "...
    1.83
     "[
    1.77
     ".
    1.73
     "(
    1.73
     "_
    1.69
     "#
    1.65
     "+
    1.63
    Act Density 0.183%

    No Known Activations