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

    Neuronpedia

    INDEX
    Explanations

    references to code or programming-related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    aeper
    -1.25
    awks
    -1.07
    Ħ¢
    -1.07
    achine
    -1.07
    ellen
    -1.05
    wagen
    -1.04
    andel
    -1.02
    eer
    -0.96
    nesday
    -0.96
    eneg
    -0.95
    POSITIVE LOGITS
     sources
    1.33
    Fed
    1.31
    books
    1.26
    source
    1.25
     whence
    1.23
     Sources
    1.21
     source
    1.15
    book
    1.12
    ources
    1.09
    finding
    1.05
    Act Density 1.055%

    No Known Activations