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

    Neuronpedia

    INDEX
    Explanations

    references to champions or championship-related concepts

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

    champion or champ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.47
    Autoritní
    -0.45
     informée
    -0.45
     autorytatywna
    -0.43
    Scary
    -0.40
    OGND
    -0.39
    snowy
    -0.35
    swire
    -0.34
     illeg
    -0.34
    все
    -0.33
    POSITIVE LOGITS
     champion
    1.62
    Champion
    1.59
     Champion
    1.59
    champion
    1.52
     CHAMPION
    1.50
     champions
    1.48
     Champions
    1.31
    Champions
    1.30
    champions
    1.24
     championed
    1.17
    Act Density 0.005%

    No Known Activations