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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    igi
    -0.81
    bidden
    -0.79
    alf
    -0.74
    gil
    -0.73
    imens
    -0.72
    ãĥŁ
    -0.71
    reetings
    -0.71
    ãĤŃ
    -0.71
    76561
    -0.71
    ":["
    -0.69
    POSITIVE LOGITS
     simulator
    0.66
    onement
    0.62
     layered
    0.62
     rehe
    0.62
    thing
    0.62
    wallet
    0.60
    ther
    0.59
     CET
    0.58
     oven
    0.58
     CV
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.