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

    Neuronpedia

    INDEX
    Explanations

    terms related to visibility and exposure in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.76
     <=",
    -0.75
    TagMode
    -0.68
     تضيفلها
    -0.67
    DrawerToggle
    -0.64
    EndTag
    -0.62
    (!__
    -0.62
    MessageOf
    -0.61
    ConstraintMaker
    -0.61
    KURZBESCHREIBUNG
    -0.58
    POSITIVE LOGITS
     underlying
    0.88
    Underlying
    0.80
    underlying
    0.78
     Underlying
    0.77
     underneath
    0.72
    neath
    0.64
     exposed
    0.62
    exposed
    0.60
     Reveal
    0.59
     bare
    0.59
    Act Density 0.268%

    No Known Activations