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

    Neuronpedia

    INDEX
    Explanations

    keywords related to a specific abbreviation, "NS" (with various numerical suffixes) and a few instances of "CIS"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or entities, particularly those abbreviated as "NS" or "CIS."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬âĸ¬
    -0.82
    about
    -0.73
    icago
    -0.70
    heit
    -0.69
    ously
    -0.69
    oise
    -0.68
    iences
    -0.68
    iens
    -0.68
    debian
    -0.66
    bugs
    -0.66
    POSITIVE LOGITS
     NS
    1.16
    FW
    1.04
     ns
    0.83
    IJ
    0.80
    BM
    0.78
    AAF
    0.78
     concess
    0.76
    FG
    0.75
    NN
    0.74
    NS
    0.73
    Act Density 0.004%

    No Known Activations