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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    GTCX
    -0.51
    República
    -0.46
    Politique
    -0.46
    Donovan
    -0.43
    pegno
    -0.43
    ApiOperation
    -0.42
    OGRAPH
    -0.42
    ברס
    -0.42
    ageo
    -0.42
     שע
    -0.42
    POSITIVE LOGITS
     fit
    1.20
     Fit
    1.15
     fitter
    1.15
    fit
    1.14
     Fitting
    1.09
     FIT
    1.08
     Fits
    1.08
    Fit
    1.07
     fits
    1.06
    fits
    1.06
    Act Density 0.073%

    No Known Activations