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

    Neuronpedia

    INDEX
    Explanations

    text flagged with the character sequence "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    sections or statements with specific legal or formal documentation formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.73
     Reincarnated
    -0.72
    utical
    -0.64
     outwe
    -0.63
     imperson
    -0.62
    athe
    -0.61
     Lit
    -0.61
    naissance
    -0.60
     hust
    -0.58
    itters
    -0.58
    POSITIVE LOGITS
    ³³³³
    1.12
    ³³³³³³³³³³³³³³³³
    1.11
    ³³³
    1.02
    ³³³³³³³³
    1.01
    ³³
    0.91
    posted
    0.80
    Posted
    0.75
    ↵Âł
    0.72
    Figure
    0.72
    Trivia
    0.72
    Act Density 0.520%

    No Known Activations