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

    Neuronpedia

    INDEX
    Explanations

    references to constants and constant values in a mathematical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.73
     FLY
    -0.70
    lujah
    -0.69
    ChildScrollView
    -0.68
     Flying
    -0.67
     DELHI
    -0.67
    Flying
    -0.67
     незавершена
    -0.66
    Wies
    -0.66
    uride
    -0.66
    POSITIVE LOGITS
     Constant
    1.71
    Constant
    1.60
     CONSTANT
    1.60
     constants
    1.58
    CONSTANT
    1.56
     constant
    1.56
     Constants
    1.46
    constant
    1.42
     Konst
    1.36
     Constantin
    1.35
    Act Density 0.061%

    No Known Activations