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

    Neuronpedia

    INDEX
    Explanations

    definite articles and other contextual phrases indicating specific items or concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Lordships
    -0.64
    kháu
    -0.57
    دانشنامهٔ
    -0.51
    uurs
    -0.51
     mał
    -0.49
    TypedDataSet
    -0.48
    usaha
    -0.47
    ראו
    -0.47
    satunya
    -0.47
     grafic
    -0.47
    POSITIVE LOGITS
    +#+#
    0.85
    ++];
    0.66
    awtextra
    0.63
    RegistryLite
    0.60
     MAG
    0.60
    AutoresizingMask
    0.57
     wikipagina
    0.57
    Externé
    0.57
    posedge
    0.56
    .*")]
    0.56
    Act Density 0.011%

    No Known Activations