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

    Neuronpedia

    INDEX
    Explanations

    instances of formatting or structural irregularities in legal texts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     FileReader
    -0.82
     Valverde
    -0.80
    mybatisplus
    -0.79
     Valladolid
    -0.74
     fallu
    -0.72
     Dryer
    -0.72
     désol
    -0.72
     Picchu
    -0.72
    viens
    -0.71
     igenom
    -0.71
    POSITIVE LOGITS
     Colman
    0.89
    ‹
    0.75
    awtextra
    0.63
     Colette
    0.63
    ing
    0.63
     kolik
    0.63
    FIF
    0.61
    Lö
    0.60
    ;&
    0.60
     sot
    0.59
    Act Density 0.000%

    No Known Activations