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

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions, allowing, and enabling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.48
    astéro
    -0.48
    AddHtmlAttribute
    -0.47
    UTERS
    -0.46
    reco
    -0.45
     Wegen
    -0.45
     Mota
    -0.44
    addObject
    -0.44
    пати
    -0.43
    fries
    -0.43
    POSITIVE LOGITS
     allowed
    1.49
     Allow
    1.33
     Allowed
    1.32
     Allowing
    1.31
     allow
    1.31
     allowing
    1.28
     permitted
    1.27
     ALLOW
    1.26
    Allow
    1.24
    allowed
    1.18
    Act Density 0.387%

    No Known Activations