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

    Neuronpedia

    INDEX
    Explanations

    common agreements or points of consensus among individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating consensus or agreement on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lans
    -0.72
     resil
    -0.70
    ificial
    -0.69
    gallery
    -0.69
     Fior
    -0.67
    interrupted
    -0.66
    backs
    -0.65
     Laksh
    -0.63
     Loaded
    -0.63
     unsuspecting
    -0.63
    POSITIVE LOGITS
     tenets
    0.99
     principle
    0.97
     principles
    0.92
     terms
    0.91
     creed
    0.88
     disagree
    0.87
     doctrines
    0.84
     direction
    0.84
     philosophies
    0.82
     propositions
    0.81
    Act Density 0.291%

    No Known Activations