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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ouble
    -0.85
     streng
    -0.75
    killed
    -0.71
     handshake
    -0.69
    etheless
    -0.67
    Downloadha
    -0.67
     confir
    -0.67
     bom
    -0.66
    emort
    -0.66
    itially
    -0.66
    POSITIVE LOGITS
    apolis
    0.78
     Gat
    0.76
     Nanto
    0.68
     Janeiro
    0.68
     Pont
    0.68
     psi
    0.67
    atos
    0.67
     Pand
    0.66
    oto
    0.65
     sidx
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.