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

    Neuronpedia

    INDEX
    Explanations

    references to power dynamics and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     doubtnut
    -0.99
     дописавши
    -0.98
     للاسماء
    -0.93
    Rüyada
    -0.92
     Monks
    -0.92
     GLS
    -0.91
     Jams
    -0.90
     betweenstory
    -0.89
     diphtheria
    -0.89
     dieß
    -0.88
    POSITIVE LOGITS
     Power
    1.59
     power
    1.49
    Power
    1.46
     POWER
    1.42
    POWER
    1.41
     Powers
    1.40
    power
    1.35
    Powers
    1.28
     powers
    1.28
    powers
    1.27
    Act Density 0.072%

    No Known Activations