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

    Neuronpedia

    INDEX
    Explanations

    references indicated by the word "See"

    oai_token-act-pair · gpt-3.5-turbo

    references to other sources or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.88
    EStreamFrame
    -0.79
    ascal
    -0.74
    intendent
    -0.69
    operated
    -0.69
    aced
    -0.67
    icum
    -0.67
    ivari
    -0.66
    purpose
    -0.65
     whistle
    -0.64
    POSITIVE LOGITS
     supra
    0.85
    KER
    0.76
     Also
    0.75
    urat
    0.71
     below
    0.70
     ALSO
    0.69
    hen
    0.69
     Sick
    0.68
    hee
    0.68
    lights
    0.68
    Act Density 0.045%

    No Known Activations