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

    Neuronpedia

    INDEX
    Explanations

    social and news-related content

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ¯¯
    -0.84
    Allah
    -0.84
    ikan
    -0.81
    peat
    -0.80
    MODE
    -0.78
    ENCY
    -0.78
    Champ
    -0.77
    acter
    -0.77
    ,,,,,,,,
    -0.75
    gebra
    -0.75
    POSITIVE LOGITS
     behalf
    1.56
     Youtube
    1.07
    demand
    1.07
    site
    1.04
     eBay
    1.03
     YouTube
    1.03
     Github
    1.03
    shore
    1.01
    erous
    1.00
    screen
    0.99
    Act Density 0.776%

    No Known Activations