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

    Neuronpedia

    INDEX
    Explanations

    descriptions of technical details related to different topics, ranging from video games to health issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     rgb
    -0.61
    ¥
    -0.59
    ãĥĢ
    -0.59
    rehens
    -0.57
    ¬¼
    -0.57
     jew
    -0.56
     veter
    -0.56
     breathe
    -0.56
     coats
    -0.56
     dexterity
    -0.54
    POSITIVE LOGITS
     Unch
    0.76
    fman
    0.67
     Lank
    0.67
     Ago
    0.65
     Wem
    0.65
     Peterson
    0.65
     Schw
    0.62
    pread
    0.61
     affected
    0.61
    DonaldTrump
    0.60
    Act Density 1.349%

    No Known Activations