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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the beginning of sections or paragraphs in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.83
    RegressionTest
    -0.73
     nahilalakip
    -0.71
    Cyfeiriadau
    -0.66
     Chwiliwch
    -0.66
    ніципалі
    -0.65
     <<<<<<<<<<<<<<
    -0.65
    DockStyle
    -0.65
     disambiguazione
    -0.63
     autorytatywna
    -0.61
    POSITIVE LOGITS
     thesis
    0.65
     dissertation
    0.50
     Thesis
    0.50
    moire
    0.50
     AssemblyProduct
    0.49
    thesis
    0.45
     Dissertation
    0.45
     conclusão
    0.44
     study
    0.44
     studying
    0.43
    Act Density 0.052%

    No Known Activations