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

    Neuronpedia

    INDEX
    Explanations

    numerical values in the context of measurements or rankings

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arial
    -0.88
    boarding
    -0.77
    mast
    -0.74
    antha
    -0.73
    many
    -0.72
    moon
    -0.71
    warts
    -0.70
    istically
    -0.68
    board
    -0.66
    igans
    -0.65
    POSITIVE LOGITS
    é¾
    0.77
    uador
    0.77
    lectic
    0.75
    stasy
    0.74
    女
    0.72
    TION
    0.72
    borg
    0.69
    æ©Ł
    0.67
    SHIP
    0.64
     Fuk
    0.64
    Act Density 0.042%

    No Known Activations