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

    Neuronpedia

    INDEX
    Explanations

    common pronouns and determiners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.87
    ViewImports
    -0.86
    ształ
    -0.78
     Whigs
    -0.73
     Cadiz
    -0.71
     GoogleFonts
    -0.71
    BibitemShut
    -0.69
    Betyg
    -0.69
     Huguen
    -0.69
     виправивши
    -0.69
    POSITIVE LOGITS
     &___
    0.66
    del
    0.60
    D
    0.57
    min
    0.57
    C
    0.56
     min
    0.52
     Ho
    0.52
    bas
    0.51
    U
    0.50
    E
    0.50
    Act Density 0.464%

    No Known Activations