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

    Neuronpedia

    INDEX
    Explanations

    discussions or mentions of societal issues and controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     shenan
    -1.13
     apprehen
    -1.02
     unspeak
    -1.02
     sophistic
    -0.92
     reluct
    -0.91
     depic
    -0.90
     impra
    -0.88
     cuck
    -0.86
     hentai
    -0.86
     pooh
    -0.85
    POSITIVE LOGITS
     Singapur
    0.78
     ideolog
    0.74
     democra
    0.71
     balon
    0.69
     impon
    0.69
    Composição
    0.68
     meras
    0.68
    asyarakat
    0.66
    Conteúdo
    0.66
     solidar
    0.65
    Act Density 0.301%

    No Known Activations