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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "full" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.87
    +#+
    -0.76
     ConstraintSet
    -0.70
    WireFormatLite
    -0.68
     Efq
    -0.68
    principalTable
    -0.67
    rrggbb
    -0.66
     AssemblyProduct
    -0.66
    InputTagHelper
    -0.64
     altogether
    -0.64
    POSITIVE LOGITS
     full
    1.30
     Full
    1.27
    Full
    1.17
     FULL
    1.12
    FULL
    1.10
    full
    1.09
    fledged
    0.98
     blown
    0.91
     fled
    0.83
    blown
    0.83
    Act Density 0.095%

    No Known Activations