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

    Neuronpedia

    INDEX
    Explanations

    words related to politics, government, and policies

    oai_token-act-pair · gpt-3.5-turbo

    prominent figures and institutions in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.54
    steamapps
    -0.54
    ¶æ
    -0.54
    }\
    -0.51
    ķ
    -0.50
    berra
    -0.48
    )).
    -0.48
    ij
    -0.48
    Joined
    -0.47
    Īè
    -0.47
    POSITIVE LOGITS
    ':
    0.56
     dilemma
    0.52
     shenan
    0.51
    undrum
    0.50
    !:
    0.50
    ukong
    0.49
     understatement
    0.49
    speak
    0.49
     proverb
    0.48
     predicament
    0.48
    Act Density 1.881%

    No Known Activations