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

    Neuronpedia

    INDEX
    Explanations

    number sequences or ordinal lists within the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     adal
    -1.01
     utop
    -0.98
     gesta
    -0.91
     franz
    -0.87
     anse
    -0.85
     erd
    -0.83
     meis
    -0.83
     zyn
    -0.83
     ché
    -0.83
     vola
    -0.81
    POSITIVE LOGITS
     unlaw
    1.05
     McLaugh
    0.94
     pamph
    0.90
     unwarran
    0.87
     philanth
    0.86
     unspeak
    0.81
     disagre
    0.81
     affor
    0.79
     Dijo
    0.77
     Qualquer
    0.77
    Act Density 0.431%

    No Known Activations