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

    Neuronpedia

    INDEX
    Explanations

    academic references and scientific research information

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    kov
    -0.95
    xious
    -0.94
    isec
    -0.92
    omore
    -0.91
    rovers
    -0.91
    ythm
    -0.90
    akra
    -0.87
    onite
    -0.86
    place
    -0.86
    kaya
    -0.86
    POSITIVE LOGITS
     IMAGES
    1.09
     PDF
    1.07
    PDF
    1.06
     pdf
    1.04
     embed
    0.99
    pdf
    0.99
     transcript
    0.98
     Download
    0.96
    >>>>
    0.96
     download
    0.89
    Act Density 1.488%

    No Known Activations