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

    Neuronpedia

    INDEX
    Explanations

    names of places or locations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that feature the abbreviation "St." followed by a location or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.68
    wcsstore
    -0.65
    SpaceEngineers
    -0.64
    shi
    -0.63
    ical
    -0.62
     centrif
    -0.61
    sts
    -0.61
     solicit
    -0.59
    ãĥ¼ãĤ¯
    -0.58
    ption
    -0.58
    POSITIVE LOGITS
     Petersburg
    1.27
     Clair
    1.13
     Louis
    1.13
     Jude
    1.03
     Augustine
    1.00
    rict
    0.94
    Louis
    0.93
     Germ
    0.92
     Laurent
    0.92
     Cloud
    0.90
    Act Density 0.018%

    No Known Activations