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

    Neuronpedia

    INDEX
    Explanations

    uniquely numerical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     susun
    -0.90
     sarili
    -0.86
     tanong
    -0.83
     kafe
    -0.79
     bawat
    -0.78
     seksi
    -0.72
     pagkak
    -0.72
     Himo
    -0.71
     betweenstory
    -0.71
     panahon
    -0.69
    POSITIVE LOGITS
     apprehen
    0.96
     intersper
    0.92
     gaily
    0.76
     strick
    0.76
     endeavouring
    0.74
     prolly
    0.74
     impelled
    0.72
     definately
    0.72
     ineffec
    0.71
     guarante
    0.70
    Act Density 0.170%

    No Known Activations