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

    Neuronpedia

    INDEX
    Explanations

    locations or geographical names related to cities or countries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    isner
    -0.66
    opol
    -0.64
    uve
    -0.63
     Fey
    -0.62
    ittees
    -0.61
    ibling
    -0.61
     Cly
    -0.61
     Dise
    -0.61
    haps
    -0.61
    pmwiki
    -0.60
    POSITIVE LOGITS
    alore
    1.27
    kok
    1.05
    Bang
    1.00
    adesh
    0.97
     bang
    0.96
    lihood
    0.95
    bang
    0.94
     Bang
    0.94
    ularity
    0.88
    sticks
    0.79
    Act Density 0.078%

    No Known Activations