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

    Neuronpedia

    INDEX
    Explanations

    instructions or commands related to enabling and disabling features or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.72
     CreateTagHelper
    -0.70
     gitti
    -0.69
     fjor
    -0.67
    følgelig
    -0.65
     DMT
    -0.65
     votos
    -0.64
    AndEndTag
    -0.63
     AssemblyProduct
    -0.62
    ItemBackground
    -0.62
    POSITIVE LOGITS
     OnEnable
    0.77
    ../
    0.74
     Enables
    0.73
    abling
    0.71
    abler
    0.69
    ../../
    0.68
     disables
    0.68
     Enable
    0.66
    isDisabled
    0.65
     disable
    0.65
    Act Density 0.071%

    No Known Activations