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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     arr
    -0.74
    ROR
    -0.68
     NTS
    -0.67
     rpm
    -0.66
     Trotsky
    -0.64
     RPM
    -0.64
    ]=
    -0.63
     Rochester
    -0.59
    Heart
    -0.59
     Refugee
    -0.59
    POSITIVE LOGITS
    xual
    0.89
    amily
    0.78
    dullah
    0.76
    utic
    0.75
    heses
    0.75
    gged
    0.74
    ilon
    0.74
    orem
    0.73
    auri
    0.73
    vertisements
    0.72
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.