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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal and procedural questions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    abestanden
    -0.66
    NOPQRST
    -0.66
     '\\;'
    -0.59
    lorin
    -0.59
     szól
    -0.58
    Obrázky
    -0.58
    Kanpo
    -0.57
    Pratique
    -0.57
     فريبيس
    -0.56
    estero
    -0.56
    POSITIVE LOGITS
    jstor
    0.70
    TestingModule
    0.60
    suo
    0.60
    chakra
    0.60
    fromLTRB
    0.60
     Packer
    0.57
     rov
    0.56
    packer
    0.56
    oporosis
    0.55
     WHETHER
    0.55
    Act Density 0.012%

    No Known Activations