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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cedented
    -0.69
    raq
    -0.66
    ACTED
    -0.65
    izont
    -0.64
     PID
    -0.64
    >[
    -0.64
     horizont
    -0.64
    irth
    -0.64
    ÃĤ
    -0.63
    FREE
    -0.62
    POSITIVE LOGITS
     Khal
    0.77
     Barg
    0.69
     Harrison
    0.67
    raid
    0.65
     Decoder
    0.65
     Raiders
    0.65
    eal
    0.62
    Ont
    0.62
     Transportation
    0.61
    acci
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.