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

    Neuronpedia

    INDEX
    Explanations

    references to time or length scales beyond a certain threshold

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.81
    ArrowToggle
    -0.80
    はじめに
    -0.66
     الحره
    -0.56
    وردار
    -0.56
     Paglinawan
    -0.55
    mitian
    -0.55
    UNGEN
    -0.54
    verständlich
    -0.53
    errHandler
    -0.52
    POSITIVE LOGITS
     marquées
    0.62
    enumi
    0.55
     fondament
    0.55
     extérieures
    0.52
     pescoço
    0.52
     connues
    0.52
     réguli
    0.51
     !!}
    0.51
    BagLayout
    0.51
    just
    0.50
    Act Density 0.087%

    No Known Activations