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

    Neuronpedia

    INDEX
    Explanations

    information or data that has been officially recorded or verified

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "documented."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awar
    -0.80
    NetMessage
    -0.79
    govtrack
    -0.77
    committee
    -0.76
    corn
    -0.76
    bit
    -0.74
    nir
    -0.73
    spr
    -0.70
    olean
    -0.69
    nel
    -0.69
    POSITIVE LOGITS
     documented
    0.91
    documented
    0.88
     documenting
    0.86
     documentation
    0.83
    urally
    0.75
     evid
    0.74
    ĸļ
    0.74
    rored
    0.73
     Koen
    0.72
    ocument
    0.71
    Act Density 0.023%

    No Known Activations