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

    Neuronpedia

    INDEX
    Explanations

    percentage values related to statistics or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (
    -0.16
     skinny
    -0.15
     somehow
    -0.14
    m
    -0.14
    ↵
    -0.14
     Progressive
    -0.14
    (?:
    -0.14
    memberof
    -0.13
     rencont
    -0.13
    bies
    -0.13
    POSITIVE LOGITS
     percent
    0.23
    twenty
    0.22
     νεÏĨοκάλÏħÏĪηÏĤ
    0.20
    ile
    0.19
    emsp
    0.19
    tile
    0.18
     chance
    0.18
    raquo
    0.17
    percent
    0.17
     Percent
    0.17
    Act Density 0.056%

    No Known Activations