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

    Neuronpedia

    INDEX
    Explanations

    locations and dates

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensor
    -0.65
    erence
    -0.64
    qv
    -0.59
    vation
    -0.59
    INAL
    -0.57
    athered
    -0.56
    iku
    -0.55
    escription
    -0.53
    erent
    -0.53
    uit
    -0.53
    POSITIVE LOGITS
    76561
    0.81
     etc
    0.64
     Kinnikuman
    0.59
     aka
    0.56
    åĮ
    0.54
     including
    0.52
     citing
    0.52
     Ltd
    0.51
    ktop
    0.50
     Calif
    0.50
    Act Density 1.445%

    No Known Activations