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

    Neuronpedia

    INDEX
    Explanations

    web links and file pathways

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     luxuriant
    -1.17
     unspeak
    -1.09
     ecru
    -1.09
     mossy
    -1.06
     melange
    -1.05
     sculptured
    -1.03
     tawny
    -1.03
     sceptre
    -1.02
     trefoil
    -1.02
     gaily
    -1.02
    POSITIVE LOGITS
     kosme
    1.02
     alkoh
    0.93
     silikon
    0.92
     kollek
    0.89
     kontinu
    0.88
     kompati
    0.87
     kön
    0.87
     solidar
    0.86
     makro
    0.86
     keramik
    0.84
    Act Density 0.126%

    No Known Activations