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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical characteristics and attributes

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to physical subjects or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utics
    -0.59
    iatus
    -0.57
     Lanka
    -0.57
    outube
    -0.57
    DonaldTrump
    -0.57
    thood
    -0.55
    ushima
    -0.55
    abwe
    -0.54
    ilaterally
    -0.54
    amia
    -0.54
    POSITIVE LOGITS
    iest
    0.82
    ultimate
    0.70
    liest
    0.70
     element
    0.70
     equivalent
    0.69
     portion
    0.69
    osphere
    0.67
     operator
    0.66
     implication
    0.65
    hest
    0.65
    Act Density 0.976%

    No Known Activations