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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arta
    -0.96
     Fenrir
    -0.73
     Empires
    -0.68
     Surv
    -0.67
     Furious
    -0.66
    Joined
    -0.65
     CODE
    -0.65
    Shield
    -0.65
     Barbarian
    -0.64
    >>>>>>>>
    -0.63
    POSITIVE LOGITS
    zn
    0.75
    boy
    0.73
    ãĤ¤ãĥĪ
    0.72
    owners
    0.72
    chev
    0.72
    ury
    0.69
    uy
    0.69
    psc
    0.69
    weet
    0.69
    kid
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.