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

    Neuronpedia

    INDEX
    Explanations

    requests for comments or responses to requests for comments in text

    oai_token-act-pair · gpt-3.5-turbo

    references to requests for comments from various organizations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bey
    -0.78
    tail
    -0.72
    ln
    -0.70
    rip
    -0.70
    YP
    -0.69
    lett
    -0.66
    aez
    -0.65
    corn
    -0.64
    Ranked
    -0.62
    lein
    -0.62
    POSITIVE LOGITS
    ariat
    1.09
    uary
    0.81
     specifics
    0.80
     pending
    0.80
     regarding
    0.77
    arial
    0.76
    ivity
    0.76
    ature
    0.74
    ispers
    0.73
     comment
    0.73
    Act Density 0.035%

    No Known Activations