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

    Neuronpedia

    INDEX
    Explanations

    situations involving debates or discussions surrounding societal issues or controversial topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Derp
    -0.95
    Lma
    -0.89
    Cringe
    -0.89
    Yess
    -0.87
    Yeet
    -0.81
    Noice
    -0.79
    Fuckin
    -0.79
    Oof
    -0.77
    Whoo
    -0.77
     shenan
    -0.76
    POSITIVE LOGITS
     paradiso
    0.88
     palio
    0.85
     torba
    0.81
    pendente
    0.81
     riva
    0.81
     bronzo
    0.78
     virtù
    0.77
     Settembre
    0.76
     sopr
    0.76
     Ottobre
    0.76
    Act Density 0.400%

    No Known Activations