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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ouses
    -0.77
    anqu
    -0.75
     MPG
    -0.73
    \'
    -0.72
    views
    -0.71
    YC
    -0.70
    geist
    -0.69
     Logged
    -0.69
     Nost
    -0.69
    anish
    -0.69
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.80
    vable
    0.76
    ãĤŃ
    0.72
    itely
    0.70
    colored
    0.67
    âĹ¼
    0.66
     mathemat
    0.65
    coded
    0.65
     guessed
    0.64
    translation
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.