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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically the names of places, people, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "St," likely identifying instances related to "street" or "saint."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.66
    gee
    -0.62
    hower
    -0.60
     absor
    -0.59
    ãĤĭ
    -0.59
     thumbs
    -0.58
    manship
    -0.57
     deaf
    -0.57
     constitu
    -0.56
     registry
    -0.56
    POSITIVE LOGITS
    uart
    1.44
    upid
    1.28
    rict
    1.26
    ructure
    1.24
    adium
    1.20
    arters
    1.20
    aples
    1.19
    ories
    1.17
    unning
    1.16
    opping
    1.15
    Act Density 0.017%

    No Known Activations