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

    Neuronpedia

    INDEX
    Explanations

    mathematical properties or conditions related to linearity and assumptions in theoretical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.57
    ecutive
    -0.54
    Autoritní
    -0.52
     EconPapers
    -0.52
    DockStyle
    -0.52
    astify
    -0.50
    poran
    -0.49
     utafitiHapana
    -0.49
     يتيمه
    -0.48
     otomatig
    -0.48
    POSITIVE LOGITS
     condition
    0.52
     conditions
    0.52
     condição
    0.52
     principle
    0.49
     principles
    0.47
     condición
    0.47
     assumption
    0.44
    Principle
    0.44
     condizioni
    0.43
     circonstances
    0.43
    Act Density 2.042%

    No Known Activations