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

    Neuronpedia

    INDEX
    Explanations

    news or updates from different sources or platforms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    marked
    -0.83
    esm
    -0.77
    rarily
    -0.76
    teenth
    -0.73
    pering
    -0.69
    velt
    -0.69
    ardless
    -0.69
    meric
    -0.68
    stained
    -0.67
    plin
    -0.65
    POSITIVE LOGITS
     Dates
    0.68
     Date
    0.67
    irement
    0.67
     INFORMATION
    0.65
     07
    0.64
     Explan
    0.64
     Coverage
    0.63
     Mara
    0.62
     RELEASE
    0.62
     06
    0.62
    Act Density 0.018%

    No Known Activations