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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a state of safety or clearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adders
    -0.15
    pekt
    -0.14
    currentColor
    -0.14
    lá
    -0.14
     Laure
    -0.14
    585
    -0.13
    uxe
    -0.13
    (compact
    -0.13
    ayne
    -0.13
    RuntimeObject
    -0.13
    POSITIVE LOGITS
     clear
    1.30
     Clear
    1.27
    Clear
    1.18
     clearing
    1.17
     cleared
    1.15
    -clear
    1.14
    clear
    1.13
     clears
    1.12
     clearance
    1.11
     CLEAR
    1.03
    Act Density 0.010%

    No Known Activations