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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Temper
    -0.62
     Jagu
    -0.58
    NRS
    -0.56
     Kev
    -0.50
     Pag
    -0.50
     Coffin
    -0.50
     Inquisition
    -0.49
     Flores
    -0.48
     Sob
    -0.47
     Serie
    -0.47
    POSITIVE LOGITS
     sore
    0.57
    uthor
    0.52
     respawn
    0.51
     spr
    0.49
    emon
    0.48
     pret
    0.48
     redist
    0.44
    emic
    0.44
     authent
    0.44
     democrat
    0.43
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.