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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures, particularly focusing on a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "He."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dying
    -0.75
     Slayer
    -0.72
     Curious
    -0.72
     Millennium
    -0.70
     Unreal
    -0.68
     Leigh
    -0.67
     Drift
    -0.67
     Mortal
    -0.66
     Clever
    -0.65
     Pieces
    -0.64
    POSITIVE LOGITS
    zbollah
    1.32
     campaigned
    1.17
     appoint
    1.11
    'll
    1.07
    eded
    1.06
    'd
    1.05
     presided
    1.03
    announced
    1.01
     tweeted
    1.00
     vetoed
    0.99
    Act Density 0.218%

    No Known Activations