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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing negative or challenging situations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Points
    -1.01
    facts
    -1.00
    events
    -0.98
    issues
    -0.97
    points
    -0.96
    things
    -0.94
    rises
    -0.93
    deals
    -0.93
    acts
    -0.93
    stories
    -0.93
    POSITIVE LOGITS
     populace
    1.31
     electorate
    1.19
     economy
    1.09
     fanbase
    1.08
     audience
    1.06
     workforce
    1.05
     environment
    1.04
     swath
    1.00
     bunch
    0.97
     population
    0.97
    Act Density 0.233%

    No Known Activations