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

    Neuronpedia

    INDEX
    Explanations

    references to scientific articles and studies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    canon
    -1.13
    Versions
    -0.96
    heit
    -0.95
    agra
    -0.92
    oaded
    -0.92
    netflix
    -0.92
    onite
    -0.90
    âĹ¼
    -0.90
    VALUE
    -0.89
    Reviewer
    -0.89
    POSITIVE LOGITS
    .,
    1.12
    ullivan
    1.11
     KL
    1.10
     et
    1.01
    engu
    1.01
    JM
    1.00
    ĪĴ
    0.99
     Kau
    0.98
    ipe
    0.97
    .;
    0.95
    Act Density 0.455%

    No Known Activations