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

    Neuronpedia

    INDEX
    Explanations

    paragraph breaks or section indicators within a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Datuak
    -0.81
    Portale
    -0.77
    nologue
    -0.70
     مرئيه
    -0.68
    Tazama
    -0.61
     يتيمه
    -0.60
    Gemeinden
    -0.60
     onCreateView
    -0.57
    yntaxException
    -0.56
    ditor
    -0.54
    POSITIVE LOGITS
     purpoſe
    0.66
     myſelf
    0.66
     poffe
    0.64
     ſche
    0.63
     againſt
    0.62
     auffi
    0.62
    ftance
    0.60
     himſelf
    0.60
     ſch
    0.60
    iffion
    0.59
    Act Density 0.006%

    No Known Activations