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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases related to medical conditions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols that might indicate questions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilee
    -0.70
     Gur
    -0.67
     treasury
    -0.66
    itiz
    -0.64
    jong
    -0.63
     contrace
    -0.63
    ified
    -0.61
    ework
    -0.61
     hasht
    -0.59
     predec
    -0.59
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.76
     Unloaded
    0.75
    RESULTS
    0.73
    è¦ļéĨĴ
    0.72
    20439
    0.72
     Characters
    0.72
    âķ
    0.71
    EStream
    0.69
    SELECT
    0.69
    ï¸
    0.69
    Act Density 0.073%

    No Known Activations