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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "flex" or its variants related to flexibility or flexing activities

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     flexibility
    -0.90
     flexible
    -0.87
    flexible
    -0.73
    Flexible
    -0.65
     Flexible
    -0.65
    rigid
    -0.59
    ix
    -0.55
     rigid
    -0.55
    Flexibility
    -0.55
     Flexibility
    -0.54
    POSITIVE LOGITS
     flex
    2.39
     Flex
    1.57
     flexing
    1.35
    Flex
    1.29
     flexion
    1.05
    flex
    0.74
    InjectAttribute
    0.69
     arşivlendi
    0.69
     متعلقه
    0.68
    σιμοποι
    0.68
    Act Density 0.002%

    No Known Activations