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

    Neuronpedia

    INDEX
    Explanations

    statistical proportions or percentages within populations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "made up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ait
    -0.68
    jah
    -0.64
    gee
    -0.63
    rouse
    -0.63
     awa
    -0.61
    opened
    -0.60
     Motors
    -0.60
    aim
    -0.59
    otin
    -0.59
     paraly
    -0.58
    POSITIVE LOGITS
    skirts
    0.72
    landish
    0.70
    lund
    0.65
    swing
    0.62
     arrangements
    0.61
    iframe
    0.60
    lesiastical
    0.60
     tents
    0.59
     arrang
    0.58
     Radiant
    0.58
    Act Density 0.021%

    No Known Activations