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

    Neuronpedia

    INDEX
    Explanations

    references to dialogue quality and characteristics in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shapes
    -0.15
    elan
    -0.14
    éĽª
    -0.14
     pen
    -0.14
    ica
    -0.14
    egrity
    -0.13
    loh
    -0.13
     Pens
    -0.13
    egr
    -0.13
     Gim
    -0.13
    POSITIVE LOGITS
     adulte
    0.17
    azen
    0.15
    inter
    0.15
    λεκ
    0.14
    imestep
    0.14
    []=$
    0.14
    ảng
    0.14
    ktor
    0.14
     casting
    0.14
    865
    0.14
    Act Density 0.021%

    No Known Activations