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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Parables
    -0.76
     Blocks
    -0.73
    ylon
    -0.70
    auer
    -0.69
     Agric
    -0.68
     ath
    -0.67
     Creed
    -0.67
    aber
    -0.66
     este
    -0.65
    ás
    -0.64
    POSITIVE LOGITS
    bered
    0.86
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.79
     bonded
    0.70
    itored
    0.69
    âĹ¼
    0.69
    ////////////////////////////////
    0.69
    ivan
    0.66
     caravan
    0.65
     distilled
    0.65
    dated
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.