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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and geographical locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     defect
    -1.24
    ĪĴ
    -1.22
     variance
    -1.07
    ItemThumbnailImage
    -1.05
     tremend
    -1.03
     srfAttach
    -1.02
    assetsadobe
    -1.01
     specificity
    -0.99
    Spread
    -0.97
    ADRA
    -0.97
    POSITIVE LOGITS
    emp
    1.25
    merce
    1.23
    lein
    1.07
    riks
    1.03
    rencies
    1.02
    etus
    1.00
    cki
    1.00
    lla
    1.00
    fest
    0.99
    ás
    0.99
    Act Density 2.853%

    No Known Activations