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

    Neuronpedia

    INDEX
    Explanations

    references to action figures and popular culture characters

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     akut
    -0.99
     Muhamma
    -0.87
     maksi
    -0.85
     kontinu
    -0.85
     kemer
    -0.82
     praktik
    -0.81
     panik
    -0.81
     territo
    -0.80
     ekos
    -0.80
     makro
    -0.79
    POSITIVE LOGITS
    Realistic
    0.66
     cgi
    0.63
     époux
    0.63
     Realistic
    0.59
     scp
    0.57
     héri
    0.57
    Modelling
    0.56
     Seigneur
    0.55
     Chinois
    0.55
     vga
    0.55
    Act Density 0.379%

    No Known Activations