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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures and their impact on belief systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows words like "as", "like", "up", or "least"

    np_acts-logits-general · gemini-2.0-flash

    hero

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adpleegd
    -0.63
     }{@
    -0.60
     autorytatywna
    -0.60
    SharedCtor
    -0.59
    expandindo
    -0.58
    agisse
    -0.58
    Indented
    -0.56
     Exactos
    -0.54
     numerus
    -0.54
     виправивши
    -0.53
    POSITIVE LOGITS
     hero
    1.98
     heroes
    1.92
    hero
    1.68
     HERO
    1.65
     Hero
    1.54
    Hero
    1.52
     Heroes
    1.51
     héroes
    1.50
    heroes
    1.48
     héros
    1.48
    Act Density 0.197%

    No Known Activations