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

    Neuronpedia

    INDEX
    Explanations

    words made up of repetitive letters

    oai_token-act-pair · gpt-3.5-turbo

    instances of music performance or orchestral settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.84
    osition
    -0.83
    errilla
    -0.77
    ablishment
    -0.75
    iage
    -0.74
    oka
    -0.71
    itionally
    -0.71
    encia
    -0.70
    farious
    -0.69
    berra
    -0.69
    POSITIVE LOGITS
    ORN
    0.71
    Pont
    0.68
     Hath
    0.66
     Drunk
    0.66
    BuyableInstoreAndOnline
    0.66
    WIND
    0.65
    Ped
    0.65
    Pass
    0.65
     Phen
    0.64
    LESS
    0.64
    Act Density 0.114%

    No Known Activations