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

    Neuronpedia

    INDEX
    Explanations

    mentions of a wide range of topics or issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    KK
    -0.71
    quez
    -0.71
    atown
    -0.70
    ifier
    -0.68
    istan
    -0.68
    few
    -0.68
    boxing
    -0.67
    dict
    -0.65
    ale
    -0.65
    uckle
    -0.65
    POSITIVE LOGITS
     viewpoints
    1.21
     disciplines
    1.19
     perspectives
    1.17
     configurations
    1.16
     styles
    1.15
     topics
    1.14
     scenarios
    1.13
     possibilities
    1.13
     formats
    1.13
     sorts
    1.12
    Act Density 0.097%

    No Known Activations