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

    Neuronpedia

    INDEX
    Explanations

    mathematical function symbols, particularly involving calculus and probability

    oai_token-act-pair · gpt-3.5-turbo

    vertical bars in various contexts, likely used for formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesday
    -0.89
     Beir
    -0.86
    ateurs
    -0.79
     Canter
    -0.78
    itionally
    -0.78
    chenko
    -0.75
    anium
    -0.74
     Shroud
    -0.72
    urally
    -0.71
    ijah
    -0.70
    POSITIVE LOGITS
    cffffcc
    0.99
    76561
    0.85
    Vi
    0.76
    NW
    0.74
     |--
    0.73
    Pg
    0.73
    cffff
    0.72
    hl
    0.72
    λ
    0.72
    cule
    0.72
    Act Density 0.008%

    No Known Activations