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

    Neuronpedia

    INDEX
    Explanations

    terms related to political concepts

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal structures and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liga
    -0.87
    ikarp
    -0.87
    etts
    -0.78
    yip
    -0.77
    package
    -0.76
    creen
    -0.76
    DEN
    -0.75
    psons
    -0.74
    etsk
    -0.74
    cedented
    -0.73
    POSITIVE LOGITS
     supremacy
    1.09
    ism
    1.09
     conceptions
    1.06
     endeavors
    1.05
     institutions
    0.99
     contexts
    0.97
     truths
    0.97
     ideals
    0.97
     ideas
    0.95
     interventions
    0.94
    Act Density 0.419%

    No Known Activations