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

    Neuronpedia

    INDEX
    Explanations

    references to various principles in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    principle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    música
    -0.50
     Efq
    -0.49
     Wikimedijinoj
    -0.47
     Monfieur
    -0.47
    actéristi
    -0.46
     McNamara
    -0.46
    multer
    -0.45
     BorderSide
    -0.45
     nôtre
    -0.45
     McKin
    -0.44
    POSITIVE LOGITS
     principle
    1.48
     principles
    1.44
     Principles
    1.41
     Principle
    1.41
    Principle
    1.41
    Principles
    1.38
    principle
    1.35
     PRINCIPLES
    1.27
    principles
    1.27
     PRINCIP
    1.18
    Act Density 0.020%

    No Known Activations