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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and phrases related to locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with geography and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.71
     centrif
    -0.69
    tein
    -0.68
    motion
    -0.65
     proxies
    -0.65
     segregated
    -0.63
    keyes
    -0.61
     indoctr
    -0.61
     elevation
    -0.60
     elev
    -0.60
    POSITIVE LOGITS
    å°Ĩ
    0.89
    estic
    0.78
    çĶŁ
    0.74
    itely
    0.74
    ÙĦ
    0.73
    ãĥ¼ãĥĨãĤ£
    0.72
    Ŀ
    0.70
    é¾įåĸļ士
    0.70
    rical
    0.69
    ãĥīãĥ©
    0.66
    Act Density 0.267%

    No Known Activations