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

    Neuronpedia

    INDEX
    Explanations

    the term "proper" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.88
     MotionEvent
    -0.72
    CPtr
    -0.72
    Geographie
    -0.71
    onAttach
    -0.70
    ReusableCell
    -0.70
    InjectAttribute
    -0.69
     cune
    -0.68
    SearchParams
    -0.67
     zda
    -0.67
    POSITIVE LOGITS
     properly
    2.98
    Proper
    2.96
     proper
    2.91
     Proper
    2.87
    proper
    2.82
    properly
    2.82
     PROPER
    2.73
     Properly
    2.64
     improper
    1.70
     improperly
    1.59
    Act Density 0.096%

    No Known Activations