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

    Neuronpedia

    INDEX
    Explanations

    This neuron appears inactive — it does not reliably respond to any tokens in these examples.

    oai_token-act-pair · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Negative Logits
     Efq
    -0.68
     Majefty
    -0.63
     Eſ
    -0.63
     varandra
    -0.62
     enfans
    -0.62
     BeautifulSoup
    -0.61
     Anſ
    -0.59
     Reſ
    -0.59
     ſeveral
    -0.57
    AsUp
    -0.56
    POSITIVE LOGITS
    Portale
    0.68
     MainAxisSize
    0.67
     not
    0.56
    ******/
    0.52
    msgSender
    0.50
    /******/
    0.49
     fun
    0.48
     Piping
    0.47
    (.)
    0.47
    Categoría
    0.47
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.