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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and criticism about various topics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    é¾į
    -0.77
    uli
    -0.73
    Palest
    -0.70
    phabet
    -0.68
    nants
    -0.67
    untled
    -0.66
    iping
    -0.66
    TextColor
    -0.66
    76561
    -0.66
    CLASSIFIED
    -0.64
    POSITIVE LOGITS
     raining
    0.77
     Osw
    0.71
     Engels
    0.71
     Governments
    0.69
    ifiable
    0.67
    EC
    0.65
     Regulation
    0.63
     Miko
    0.63
     Instruments
    0.63
     underest
    0.63
    Act Density 14.300%

    No Known Activations