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

    Neuronpedia

    INDEX
    Explanations

    words indicating commonality or standardization

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

    usual, typical, standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.80
     AssemblyCulture
    -0.68
    #+#
    -0.63
     ligiloj
    -0.59
    帖最后由
    -0.54
    GOTREF
    -0.49
    complexContent
    -0.49
     henvisninger
    -0.48
     kasarigan
    -0.48
     дописавши
    -0.48
    POSITIVE LOGITS
     typical
    0.57
     usual
    0.56
     standard
    0.52
     pinulongan
    0.51
     customary
    0.51
     traditional
    0.49
    Usual
    0.49
     klasik
    0.47
     classiques
    0.46
     stereotypical
    0.46
    Act Density 0.056%

    No Known Activations