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

    Neuronpedia

    INDEX
    Explanations

    terms related to government, economics, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to socioeconomic factors and structural issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.83
    enegger
    -0.83
     Vaugh
    -0.72
     Moroc
    -0.65
     Seym
    -0.65
    âĸ¬
    -0.63
     Noon
    -0.61
    avorite
    -0.60
    pex
    -0.58
     thous
    -0.58
    POSITIVE LOGITS
    \":
    0.64
     ][
    0.62
    )?
    0.56
    ileaks
    0.55
     ]
    0.51
    âĢIJ
    0.51
     seism
    0.50
     ):
    0.50
    Elsa
    0.49
    clinton
    0.49
    Act Density 0.702%

    No Known Activations