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

    Neuronpedia

    INDEX
    Explanations

    references to power and its various forms and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.99
     дописавши
    -0.95
     doubtnut
    -0.95
     Monks
    -0.91
    Parcelize
    -0.91
     Jams
    -0.91
     betweenstory
    -0.89
    Rüyada
    -0.88
    thâu
    -0.88
     dieß
    -0.86
    POSITIVE LOGITS
     Power
    2.01
     power
    2.00
    Power
    1.90
    power
    1.83
    POWER
    1.81
     POWER
    1.77
     Powers
    1.67
     powers
    1.65
    powers
    1.59
    Powers
    1.53
    Act Density 0.062%

    No Known Activations