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

    Neuronpedia

    INDEX
    Explanations

    references to being "blind" or "blindness" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.81
    cshtml
    -0.79
    HasAnnotation
    -0.74
    tagHelperRunner
    -0.70
    FormTagHelper
    -0.68
    ConstraintMaker
    -0.67
     MainAxisSize
    -0.66
     jPanel
    -0.64
    TagMode
    -0.62
    AndEndTag
    -0.62
    POSITIVE LOGITS
    folded
    0.82
    Blind
    0.80
     Blind
    0.70
     blind
    0.67
    blind
    0.66
    folds
    0.65
    sided
    0.63
    fold
    0.60
     Blinds
    0.55
     blinds
    0.55
    Act Density 0.119%

    No Known Activations