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

    Neuronpedia

    INDEX
    Explanations

    references to works or collections of various media forms, such as books, speeches, reports, and art

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    antha
    -0.76
    clad
    -0.76
     Adin
    -0.74
    odder
    -0.72
     Ukrain
    -0.68
    ĪĴ
    -0.65
    wcs
    -0.64
     Bots
    -0.64
     Pione
    -0.63
    cipled
    -0.63
    POSITIVE LOGITS
    hops
    1.42
    paces
    1.29
    heet
    0.98
    pace
    0.97
    hirt
    0.91
    icle
    0.89
    icles
    0.88
    esian
    0.88
    manship
    0.87
    works
    0.86
    Act Density 0.492%

    No Known Activations