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

    Neuronpedia

    INDEX
    Explanations

    conditional statements indicating a hypothetical scenario

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.85
    ibur
    -0.77
    vantage
    -0.77
    ÙĴ
    -0.73
    etts
    -0.71
    ée
    -0.70
    asus
    -0.69
    yna
    -0.69
    Republic
    -0.68
    oeuv
    -0.68
    POSITIVE LOGITS
     technically
    0.94
     they
    0.88
     outnumbered
    0.75
     admittedly
    0.73
     it
    0.73
     THEY
    0.72
     SOME
    0.71
     theoretically
    0.68
     ostensibly
    0.67
     hindsight
    0.67
    Act Density 0.093%

    No Known Activations