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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    raine
    -0.76
     Andrews
    -0.72
    iliated
    -0.67
    utan
    -0.67
     champagne
    -0.65
    velt
    -0.64
    Fle
    -0.64
     Fitzgerald
    -0.62
    rett
    -0.60
     pace
    -0.60
    POSITIVE LOGITS
    女
    1.04
    ä
    0.82
     âĶľâĶĢâĶĢ
    0.75
     inherit
    0.73
    çĶŁ
    0.71
    INESS
    0.71
    ãĥ¼ãĥ³
    0.69
    ocument
    0.69
    ãģ¦
    0.69
    æī
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.