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

    Neuronpedia

    INDEX
    Explanations

    elements related to categories, conditions, and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     birçok
    -0.73
     wielu
    -0.70
     berbagai
    -0.70
     многих
    -0.68
     pelbagai
    -0.66
     vieler
    -0.65
     רבים
    -0.65
     centaines
    -0.63
     många
    -0.63
     muitas
    -0.63
    POSITIVE LOGITS
     namely
    1.10
    分别是
    1.00
    分別
    0.97
     apiece
    0.97
    namely
    0.88
     respectively
    0.86
     each
    0.82
     successively
    0.82
    分别
    0.81
     consecutively
    0.81
    Act Density 1.051%

    No Known Activations