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

    Neuronpedia

    INDEX
    Explanations

    references to superheroes

    oai_token-act-pair · gpt-3.5-turbo

    references to superheroes and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Byrd
    -0.75
     latch
    -0.70
     Welch
    -0.68
     ACC
    -0.67
     faculty
    -0.67
     defect
    -0.65
     refin
    -0.64
     Schl
    -0.64
     associate
    -0.63
     Ampl
    -0.62
    POSITIVE LOGITS
    hero
    4.40
    Hero
    2.29
    HER
    1.84
     Hero
    1.64
     hero
    1.59
     HERO
    1.53
     heroes
    1.49
     heroine
    1.38
     heroism
    1.26
    agonist
    1.26
    Act Density 0.011%

    No Known Activations