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

    Neuronpedia

    INDEX
    Explanations

    descriptions of challenging and rewarding work environments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     maksi
    -1.00
     silikon
    -0.93
     alkoh
    -0.91
     jaya
    -0.89
     keramik
    -0.89
     kosme
    -0.86
     optik
    -0.85
     akut
    -0.83
     makro
    -0.82
     protokol
    -0.79
    POSITIVE LOGITS
     seeing
    0.70
     watching
    0.63
     interacting
    0.62
     discovering
    0.60
     knowing
    0.58
     experiencing
    0.57
     hearing
    0.57
     being
    0.55
     feeling
    0.54
     doing
    0.52
    Act Density 0.494%

    No Known Activations