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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated formatting or punctuation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ناة
    -0.47
     Mar
    -0.46
     wi
    -0.41
     pre
    -0.40
     chỗ
    -0.39
     unteren
    -0.39
    inte
    -0.38
     Por
    -0.37
     Rom
    -0.37
     Bis
    -0.37
    POSITIVE LOGITS
     AssemblyCulture
    1.02
    évaluateur
    1.02
    Geplaatst
    1.01
    GEBURTSDATUM
    1.01
    fjspx
    1.00
     Exacts
    0.99
     مشين
    0.97
    tagHelperRunner
    0.96
     lenker
    0.96
    ConstraintMaker
    0.94
    Act Density 0.001%

    No Known Activations