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

    Neuronpedia

    INDEX
    Explanations

    interactions related to uncertainty and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inmiddels
    -0.74
    Cubit
    -0.74
    webElementXpaths
    -0.73
    createCanvas
    -0.69
    Datuak
    -0.64
     muualla
    -0.64
    ConstraintMaker
    -0.63
    htë
    -0.61
     vielä
    -0.60
    InstrumentedTest
    -0.59
    POSITIVE LOGITS
    RectangleBorder
    0.65
     Always
    0.63
    WebVitals
    0.60
    deauna
    0.59
    Always
    0.58
    ALWAYS
    0.54
     Never
    0.54
    always
    0.52
     Humb
    0.51
    expo
    0.50
    Act Density 0.123%

    No Known Activations