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

    Neuronpedia

    INDEX
    Explanations

    terms related to voting, elections, and public opinion

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    RAW
    -0.69
    RAG
    -0.69
    =-=-
    -0.67
    omething
    -0.63
    ür
    -0.61
    ilk
    -0.61
    ĸļ
    -0.60
    alon
    -0.59
    agher
    -0.59
     diplom
    -0.58
    POSITIVE LOGITS
    izing
    1.30
    ization
    1.29
    izations
    1.27
    isation
    1.24
    ized
    1.22
    isations
    1.22
    ity
    1.20
    izers
    1.19
    ised
    1.17
    izer
    1.12
    Act Density 0.027%

    No Known Activations