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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names, specifically focusing on those related to politics, influence, and power

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to specific individuals or groups, particularly in complex or negative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.71
    opers
    -0.58
    ograp
    -0.58
    ppers
    -0.58
    ikh
    -0.58
     gears
    -0.57
    ngth
    -0.57
    oshenko
    -0.57
    ppa
    -0.56
     suppose
    -0.55
    POSITIVE LOGITS
    uary
    0.75
    ÃĽ
    0.74
    heid
    0.72
    afia
    0.70
    ILA
    0.70
    eki
    0.69
    uration
    0.69
    SourceFile
    0.68
    dash
    0.67
    lie
    0.65
    Act Density 0.058%

    No Known Activations