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

    Neuronpedia

    INDEX
    Explanations

    quantitative values and measurements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     marié
    -0.77
     unwarran
    -0.69
     medesimo
    -0.69
     pamph
    -0.67
     occupe
    -0.65
     Whigs
    -0.65
     mécanisme
    -0.64
     déclarations
    -0.64
     accueille
    -0.64
     obligé
    -0.63
    POSITIVE LOGITS
     reputa
    0.70
     lega
    0.66
     vola
    0.66
     lomb
    0.66
    pexpr
    0.66
     beren
    0.65
    SneakyThrows
    0.64
     bont
    0.63
     tota
    0.63
     vernac
    0.62
    Act Density 0.358%

    No Known Activations