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

    Neuronpedia

    INDEX
    Explanations

    symbols used as separators in text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ozyg
    -0.79
     gobl
    -0.71
    ikuman
    -0.69
     defe
    -0.65
     cellar
    -0.64
    emaker
    -0.64
     estab
    -0.63
    idth
    -0.63
     aborted
    -0.62
     involuntary
    -0.62
    POSITIVE LOGITS
     Both
    1.21
     These
    1.21
     Also
    1.20
     Together
    1.18
     Additionally
    1.16
     Each
    1.14
     Basically
    1.11
     They
    1.10
     Those
    1.06
     respectively
    1.03
    Act Density 0.603%

    No Known Activations