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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     challeng
    -0.81
     multif
    -0.77
    ŃĶ
    -0.73
     heav
    -0.70
     immersion
    -0.69
     dimensional
    -0.68
     aggress
    -0.68
    iqueness
    -0.66
    worms
    -0.65
    fulness
    -0.65
    POSITIVE LOGITS
     Photo
    1.64
     PHOTO
    1.46
     Courtesy
    1.46
     Photograph
    1.45
     Credit
    1.43
     REUTERS
    1.37
     Photographer
    1.36
     Picture
    1.35
     Image
    1.30
     Wikimedia
    1.20
    Act Density 0.405%

    No Known Activations