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

    Neuronpedia

    INDEX
    Explanations

    words related to corruption, immoral actions, and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to corruption and social injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    requisite
    -0.88
    foreseen
    -0.87
    ailable
    -0.85
    agree
    -0.81
    significant
    -0.79
    breaker
    -0.79
    amaz
    -0.75
    avia
    -0.74
    available
    -0.73
    inarily
    -0.73
    POSITIVE LOGITS
     policies
    1.06
     ideology
    1.01
     notions
    0.96
     smear
    0.96
     ideologies
    0.95
     bureaucracy
    0.95
     witch
    0.93
     practices
    0.93
     notion
    0.93
     attitudes
    0.91
    Act Density 0.165%

    No Known Activations