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

    Neuronpedia

    INDEX
    Explanations

    articles and determiners in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ViewImports
    -0.63
    стоян
    -0.53
    ൾ
    -0.52
    ześnie
    -0.49
    IQR
    -0.48
    mancy
    -0.47
    fxml
    -0.47
    há
    -0.46
    unanje
    -0.46
    CardHeader
    -0.45
    POSITIVE LOGITS
     reç
    0.65
     архивлан
    0.64
     fraî
    0.63
    celine
    0.61
    ьаж
    0.60
    avadoc
    0.60
    fraz
    0.57
    — 
    0.57
    GEBURTSDATUM
    0.57
    FORMANCE
    0.57
    Act Density 0.071%

    No Known Activations