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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates, particularly the month of January

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     apar
    -0.63
     isto
    -0.63
     mus
    -0.61
    uter
    -0.58
    gan
    -0.57
    lar
    -0.57
     mak
    -0.56
     jad
    -0.55
     hat
    -0.54
    into
    -0.54
    POSITIVE LOGITS
    œ
    1.23
    ьаж
    1.03
     Roskov
    0.94
     kaarangay
    0.93
    ustimmung
    0.91
    تقاوى
    0.89
    Viitteet
    0.88
     gawas
    0.87
    tagext
    0.86
    titleMargin
    0.86
    Act Density 0.000%

    No Known Activations