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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, including names of people and places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Pwr
    -1.09
    EStreamFrame
    -1.03
    axter
    -1.02
    milo
    -0.99
    ĪĴ
    -0.96
     immersion
    -0.94
     Marketable
    -0.94
     berth
    -0.92
     snag
    -0.92
    Kings
    -0.91
    POSITIVE LOGITS
    geist
    1.24
    é¾įåĸļ士
    1.13
    enthal
    1.12
    aiman
    1.09
    eller
    1.09
    know
    1.06
    achu
    1.05
    ocene
    1.02
    forum
    1.01
    avage
    1.00
    Act Density 1.090%

    No Known Activations