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

    Neuronpedia

    INDEX
    Explanations

    instances of the start of new sections or paragraphs in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -0.88
    ↵↵
    -0.85
    (
    -0.83
    .
    -0.76
    [
    -0.75
    :
    -0.74
    @
    -0.68
    ;
    -0.67
    “
    -0.65
    on
    -0.64
    POSITIVE LOGITS
     pleaſure
    0.98
    ^(@)
    0.97
    NUMX
    0.93
     AssemblyCulture
    0.86
     greateſt
    0.84
    amaño
    0.84
     myſelf
    0.83
     Normdatei
    0.81
     tongs
    0.81
     leaſt
    0.77
    Act Density 0.374%

    No Known Activations