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

    Neuronpedia

    INDEX
    Explanations

    terms related to attributes in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.54
     actionMode
    -0.52
    хьтан
    -0.51
    AndEndTag
    -0.51
     Exacts
    -0.50
    ynia
    -0.48
     transfieras
    -0.47
     BoxFit
    -0.47
    lub
    -0.47
     IBOutlet
    -0.47
    POSITIVE LOGITS
    Attribute
    1.06
     Attribute
    0.99
     attribute
    0.96
    Attributes
    0.93
    attribute
    0.93
    attributes
    0.92
    ATTRIBUTE
    0.86
     attributes
    0.85
     Attributes
    0.83
     atributo
    0.68
    Act Density 0.184%

    No Known Activations