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

    Neuronpedia

    INDEX
    Explanations

    elements of doubt or contradiction in statements

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

    the neuron responds to capitalized tokens — i.e., proper names, section labels, and other tokens that begin with an uppercase letter.

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Negative Logits
    phemy
    -0.61
    pecker
    -0.58
     Inde
    -0.51
    colage
    -0.51
    rimi
    -0.50
    sists
    -0.50
     Clegg
    -0.49
     Vogt
    -0.49
    őle
    -0.48
    theless
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.88
    TestingModule
    0.85
     AssemblyCulture
    0.85
     Roskov
    0.78
    InvalidProtocol
    0.78
    AlterField
    0.78
    +#+#
    0.78
     EconPapers
    0.75
    richTextPanel
    0.70
    Jegyzetek
    0.66
    Act Density 0.410%

    No Known Activations