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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.74
    ijn
    -0.65
     sampled
    -0.65
    FOX
    -0.64
    EV
    -0.63
    Cos
    -0.62
    lik
    -0.61
    redit
    -0.60
    antine
    -0.60
    SIM
    -0.59
    POSITIVE LOGITS
    ertodd
    0.82
     sacrific
    0.76
    ettings
    0.71
     Seah
    0.70
     EntityItem
    0.70
    hander
    0.69
    sov
    0.69
     Siber
    0.69
     Totem
    0.69
     Crate
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.