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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tanks
    -0.73
    ensation
    -0.68
    aca
    -0.68
    ORED
    -0.68
     Alloy
    -0.67
    Demon
    -0.67
    ifacts
    -0.66
    riott
    -0.64
    ailable
    -0.64
    ISM
    -0.62
    POSITIVE LOGITS
     reperto
    0.71
     awa
    0.69
    ser
    0.69
    conserv
    0.69
     ther
    0.66
     indo
    0.66
     alive
    0.66
    abella
    0.65
    nown
    0.64
     Osw
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.