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

    Neuronpedia

    INDEX
    Explanations

    the presence of the character 's' in different contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     our
    -0.63
     Our
    -0.60
     biggest
    -0.60
     ‘
    -0.60
     The
    -0.57
    Our
    -0.56
    The
    -0.56
     smartest
    -0.55
    biggest
    -0.54
    s
    -0.54
    POSITIVE LOGITS
    AccessorTable
    0.81
     tabPage
    0.75
    存于互联网档案馆
    0.71
     विश्वसनीयता
    0.71
     createSlice
    0.70
     contd
    0.68
    prits
    0.67
     Beli
    0.66
     Joc
    0.66
     CreateTagHelper
    0.65
    Act Density 0.063%

    No Known Activations