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

    Neuronpedia

    INDEX
    Explanations

    terms related to winter and its conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     שוליים
    -0.77
    pernicus
    -0.77
    summ
    -0.75
    achella
    -0.74
     estoppel
    -0.73
     Cours
    -0.73
    eynman
    -0.73
     Shakspeare
    -0.73
     تضيفلها
    -0.73
    ckeye
    -0.73
    POSITIVE LOGITS
     Winters
    1.26
     Winter
    1.02
     WINTER
    0.91
    Winter
    0.86
    WINTER
    0.84
     winter
    0.82
     Wint
    0.81
     winters
    0.78
    wara
    0.75
    冬
    0.73
    Act Density 0.005%

    No Known Activations