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

    Neuronpedia

    INDEX
    Explanations

    terms related to public opinion and politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     contracting
    -0.54
     Bohem
    -0.52
     Household
    -0.52
     contracted
    -0.52
     Hots
    -0.50
     Entry
    -0.50
    Parts
    -0.50
     subsidized
    -0.49
     consortium
    -0.48
     Compass
    -0.48
    POSITIVE LOGITS
     cynicism
    0.69
    ctor
    0.66
     fallacy
    0.62
    nat
    0.61
     rhetorical
    0.61
    uned
    0.60
     sarc
    0.60
     metaphors
    0.60
    ="#
    0.59
     hindsight
    0.59
    Act Density 0.460%

    No Known Activations