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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving different formatting styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tempel
    -0.51
     CHAPITRE
    -0.50
     Kitchener
    -0.49
    rospy
    -0.48
    Joining
    -0.48
     nonatomic
    -0.47
     TÉCN
    -0.47
     Mémoires
    -0.46
     Soyez
    -0.46
    SUFFIX
    -0.46
    POSITIVE LOGITS
    MLLoader
    0.69
    SequentialGroup
    0.68
    ViewImports
    0.65
    UnusedPrivate
    0.61
    tvguidetime
    0.56
     {
    0.54
    mnar
    0.54
     الرياضيه
    0.50
    InjectAttribute
    0.49
    ConstraintMaker
    0.49
    Act Density 0.106%

    No Known Activations