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

    Neuronpedia

    INDEX
    Explanations

    keywords related to compatibility or suitability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fitting."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doc
    -0.85
    md
    -0.80
    iac
    -0.76
    opa
    -0.66
    ousands
    -0.65
    gm
    -0.62
    antis
    -0.61
     Monitor
    -0.59
    dn
    -0.59
    ilot
    -0.59
    POSITIVE LOGITS
     fitting
    4.02
    fitting
    2.71
     fit
    1.78
     fitted
    1.63
     fitt
    1.60
    fit
    1.58
    fits
    1.46
     fits
    1.39
    fitted
    1.36
     Fit
    1.19
    Act Density 0.012%

    No Known Activations