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

    Neuronpedia

    INDEX
    Explanations

    references to conditional statements and theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⎨
    -0.56
     BorderRadius
    -0.54
    XmlAccessorType
    -0.53
    ]--;
    -0.51
     transfieras
    -0.50
    CreateMap
    -0.49
     otomatig
    -0.49
    EventLoop
    -0.47
    typeparam
    -0.47
    LocalizedString
    -0.45
    POSITIVE LOGITS
     relying
    1.56
     rely
    1.55
     relies
    1.54
     dependent
    1.52
     depend
    1.51
     depended
    1.50
     reliant
    1.49
     reliance
    1.46
     based
    1.41
     dependence
    1.38
    Act Density 0.551%

    No Known Activations