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

    Neuronpedia

    INDEX
    Explanations

    occurrences of underscore-prefixed identifiers commonly used in programming or scripting contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -1.08
    <eos>
    -1.03
     
    -0.94
    ↵
    -0.91
    ↵↵
    -0.90
     (
    -0.85
     The
    -0.84
    '
    -0.79
    ).
    -0.79
     In
    -0.78
    POSITIVE LOGITS
     myſelf
    1.67
     Monfieur
    1.63
     itſelf
    1.60
     Majefty
    1.57
     Theſe
    1.54
     pleaſure
    1.54
     themſelves
    1.53
     ſeveral
    1.52
     Efq
    1.52
     ainfi
    1.50
    Act Density 0.180%

    No Known Activations