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

    Neuronpedia

    INDEX
    Explanations

    mentions of people who have shown courage or bravery

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with significant contributions or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reporting
    -0.77
     scheduling
    -0.72
    availability
    -0.72
     Inspection
    -0.70
     airing
    -0.68
     reservations
    -0.68
    Regarding
    -0.68
     Setup
    -0.67
    itant
    -0.67
    uming
    -0.67
    POSITIVE LOGITS
     overcame
    1.64
     sacrificed
    1.56
     died
    1.50
     perished
    1.49
     risked
    1.44
     defied
    1.43
     survived
    1.42
     fought
    1.35
     succeeded
    1.35
     deserved
    1.33
    Act Density 0.434%

    No Known Activations