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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames or handles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    appropri
    -0.73
    ordinate
    -0.72
    icum
    -0.71
    ignty
    -0.69
     compens
    -0.69
    iola
    -0.68
    abal
    -0.67
    ciplinary
    -0.67
     nudity
    -0.67
     awakening
    -0.66
    POSITIVE LOGITS
     VIDEOS
    0.85
    ï¸ı
    0.76
     RT
    0.76
     TODAY
    0.76
     Rabbi
    0.74
     Vive
    0.73
     Ty
    0.73
    ————————
    0.73
    avanaugh
    0.72
     âĺ
    0.71
    Act Density 10.865%

    No Known Activations