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

    Neuronpedia

    INDEX
    Explanations

    information related to historical places, countries, and notable firsts

    oai_token-act-pair · gpt-3.5-turbo

    statements about unique geographical or historical facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĪĴ
    -0.60
    ĺħ
    -0.59
    tnc
    -0.54
    arrell
    -0.52
    ¬¼
    -0.50
    ĺ
    -0.48
    ãĤ´ãĥ³
    -0.47
    ancies
    -0.47
    ¢
    -0.47
    ãĥĥ
    -0.47
    POSITIVE LOGITS
     ever
    0.63
     EVER
    0.63
    ever
    0.53
     available
    0.48
    behind
    0.47
     imaginable
    0.46
     currently
    0.45
     circulating
    0.44
    hesive
    0.43
    liest
    0.42
    Act Density 0.732%

    No Known Activations