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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kear
    -0.75
    Native
    -0.74
     Cary
    -0.73
     Goat
    -0.68
    Meat
    -0.65
     Avery
    -0.65
     Parenthood
    -0.65
     Midwest
    -0.65
     Liver
    -0.63
    Load
    -0.63
    POSITIVE LOGITS
     Jinping
    1.11
    enei
    1.01
     supporters
    0.91
     confid
    0.78
    orsi
    0.78
    isma
    0.76
     campaigned
    0.76
     impeachment
    0.75
    ovich
    0.74
     appoint
    0.74
    Act Density 0.062%

    No Known Activations