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

    Neuronpedia

    INDEX
    Explanations

    concepts and terminology related to reversibility and inverse relationships in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     بيها
    -0.68
     متحده
    -0.68
     يتيمه
    -0.59
    queryParams
    -0.59
     pulito
    -0.57
    ு
    -0.55
    riedenheit
    -0.55
     fæ
    -0.53
    скет
    -0.50
     européennes
    -0.50
    POSITIVE LOGITS
     reverse
    1.34
     inverse
    1.30
     invers
    1.28
     Reverse
    1.28
     invert
    1.25
     inversion
    1.22
     inver
    1.19
     reversed
    1.17
     inverted
    1.16
    Reverse
    1.15
    Act Density 0.350%

    No Known Activations