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

    Neuronpedia

    INDEX
    Explanations

    mentions of fictional battles and confrontations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.19
     tenda
    -0.78
    Попис
    -0.76
     ados
    -0.74
     fides
    -0.72
     roba
    -0.71
     poliuret
    -0.70
     lampa
    -0.67
     sement
    -0.66
     roj
    -0.65
    POSITIVE LOGITS
     McLaugh
    1.06
     McInt
    0.99
     disreg
    0.99
     Vaugh
    0.95
     reluct
    0.94
     Rine
    0.94
     unspeak
    0.92
     Gorb
    0.90
     indestru
    0.90
     impra
    0.90
    Act Density 0.244%

    No Known Activations