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

    Neuronpedia

    INDEX
    Explanations

    occurrences of HTML-like angle brackets and their patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with generics/templates

    np_acts-logits-general · gemini-2.0-flash

    detected String objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -1.03
     he
    -0.90
    .
    -0.88
     is
    -0.87
    ,
    -0.87
     to
    -0.87
     in
    -0.86
     of
    -0.83
     The
    -0.79
     A
    -0.78
    POSITIVE LOGITS
     myſelf
    1.81
     itſelf
    1.73
     Efq
    1.70
     Monfieur
    1.67
     auffi
    1.64
     purpoſe
    1.63
     pleaſure
    1.62
     poffible
    1.56
     Majefty
    1.55
     reaſon
    1.54
    Act Density 0.054%

    No Known Activations