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

    Neuronpedia

    INDEX
    Explanations

    references to moral concepts and Buddhist teachings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ***!
    -0.71
     Championnat
    -0.68
     scorso
    -0.67
     giù
    -0.67
    calciatore
    -0.66
     Unito
    -0.66
     interag
    -0.66
     Venise
    -0.65
    DoubleQuotes
    -0.64
    hoeddwyd
    -0.64
    POSITIVE LOGITS
     McLaugh
    0.94
     McInt
    0.89
     Daven
    0.80
     Bartholo
    0.80
    <^
    0.79
     Harms
    0.74
     Cuth
    0.73
     Thier
    0.73
     Immig
    0.69
     Rine
    0.69
    Act Density 0.414%

    No Known Activations