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

    Neuronpedia

    INDEX
    Explanations

    expressions related to ratings and scoring systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dese
    -0.15
    isel
    -0.15
    Sea
    -0.14
    LEAN
    -0.14
    toa
    -0.14
    ÑģпÑĸлÑĮ
    -0.13
     cork
    -0.13
    -regexp
    -0.13
    ootball
    -0.13
    ÑĤÑİ
    -0.13
    POSITIVE LOGITS
     scores
    0.19
     score
    0.16
     ratings
    0.15
     Scores
    0.15
     rating
    0.14
    orthand
    0.14
    aternity
    0.14
    lant
    0.14
    rating
    0.14
    _scheme
    0.14
    Act Density 0.087%

    No Known Activations