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

    Neuronpedia

    INDEX
    Explanations

    key attributes or features regarding software versions and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     this
    -3.41
    this
    -2.67
     these
    -2.44
     этого
    -2.07
    these
    -2.03
     này
    -1.97
     THIS
    -1.96
     questa
    -1.89
     questo
    -1.88
     этой
    -1.88
    POSITIVE LOGITS
    Hauptartikel
    0.56
    ੱਕ
    0.48
    раздо
    0.46
    ękuję
    0.45
    BSITE
    0.43
    aphthalene
    0.43
    eriks
    0.42
    iston
    0.41
    razione
    0.41
    äki
    0.40
    Act Density 1.185%

    No Known Activations