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

    Neuronpedia

    INDEX
    Explanations

    power dynamics, political maneuvers, and social issues in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate manipulation and exploitation for personal or political gain

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.68
    tackle
    -0.67
     Explore
    -0.63
    webkit
    -0.63
     Methodist
    -0.63
     Crusher
    -0.63
    "}],"
    -0.62
     surveyed
    -0.61
     Alloy
    -0.61
     Loving
    -0.61
    POSITIVE LOGITS
     agendas
    0.97
     pretext
    0.97
     blackmail
    0.95
     profit
    0.95
     agenda
    0.93
     nefarious
    0.88
     revenge
    0.88
     advantage
    0.87
     predetermined
    0.87
     profits
    0.85
    Act Density 0.735%

    No Known Activations