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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements in text

    oai_token-act-pair · gpt-3.5-turbo

    statistical measures and metrics related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.66
    cients
    -0.63
    URI
    -0.61
     unsus
    -0.60
    Mand
    -0.59
     pharm
    -0.59
    ather
    -0.58
    izoph
    -0.58
    insula
    -0.58
     whence
    -0.57
    POSITIVE LOGITS
    ĸļ
    0.95
     Kills
    0.70
    isSpecialOrderable
    0.68
    rez
    0.67
     Transmission
    0.67
    к
    0.66
     Converted
    0.65
    cro
    0.64
     Crimes
    0.64
     Percent
    0.64
    Act Density 0.221%

    No Known Activations