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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Smy
    -0.89
     Noon
    -0.79
     Olympia
    -0.73
     TAM
    -0.72
     Racer
    -0.70
     Rampage
    -0.69
     Madness
    -0.67
     Rats
    -0.67
     Swim
    -0.66
     Shoals
    -0.66
    POSITIVE LOGITS
    urs
    0.78
    xus
    0.77
    uci
    0.76
    ounter
    0.76
    overs
    0.75
    idious
    0.75
    gur
    0.74
    ossibility
    0.74
    anners
    0.73
    orest
    0.73
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.