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

    Neuronpedia

    INDEX
    Explanations

    terms related to power and its measurements or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.15
     mergeFrom
    -1.02
    Tembelea
    -1.01
     متعلقه
    -0.99
     CreateTagHelper
    -0.92
    ]--;
    -0.88
    BufferException
    -0.85
    OGND
    -0.84
    Diweddarwch
    -0.83
    (!__
    -0.80
    POSITIVE LOGITS
     power
    2.77
    power
    2.52
    Power
    2.34
     Power
    2.33
    POWER
    2.21
     POWER
    2.14
     powers
    2.03
     pow
    1.91
    powers
    1.88
    pow
    1.82
    Act Density 0.156%

    No Known Activations