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

    Neuronpedia

    INDEX
    Explanations

    references to heroes and heroism in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jPanel
    -0.41
    hyp
    -0.38
    ensement
    -0.37
    TableHead
    -0.35
    hyper
    -0.35
    Tembelea
    -0.35
     Hyp
    -0.35
    withOpacity
    -0.34
     Hyper
    -0.34
    GOTREF
    -0.34
    POSITIVE LOGITS
     hero
    2.81
     Hero
    2.73
    Hero
    2.63
     heroes
    2.55
     HERO
    2.50
    hero
    2.48
     Heroes
    2.31
    HERO
    2.31
    Heroes
    2.19
     héroe
    2.11
    Act Density 0.556%

    No Known Activations