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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, regulations, and legal constraints

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.74
     Poe
    -0.64
    erva
    -0.64
     Rolls
    -0.63
     eyebrows
    -0.61
    aples
    -0.61
    guyen
    -0.59
    anmar
    -0.58
     proverb
    -0.57
     tales
    -0.57
    POSITIVE LOGITS
     whatsoever
    1.52
     imaginable
    1.26
    soever
    1.10
     resembling
    0.97
     except
    0.93
     conceivable
    0.85
     besides
    0.85
     shape
    0.83
     thereafter
    0.82
    wcsstore
    0.80
    Act Density 0.059%

    No Known Activations