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

    Neuronpedia

    INDEX
    Explanations

    strings that indicate a numerical value followed by additional data

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and comparative amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bind
    -0.63
     bodies
    -0.58
    uti
    -0.58
     conversions
    -0.58
     journals
    -0.58
     comma
    -0.58
    ALSE
    -0.57
     platforms
    -0.57
    anos
    -0.57
     sig
    -0.57
    POSITIVE LOGITS
    Ô
    0.72
    pta
    0.69
    flix
    0.68
    ï¸ı
    0.67
     Bleach
    0.63
     UNITED
    0.62
    acements
    0.62
    DragonMagazine
    0.62
    ould
    0.61
    rahim
    0.61
    Act Density 0.206%

    No Known Activations