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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oru
    -0.80
     Takeru
    -0.72
    akeru
    -0.72
     avatar
    -0.68
    ashington
    -0.68
     Reloaded
    -0.67
    mere
    -0.66
     Subaru
    -0.65
    irez
    -0.65
     Ik
    -0.62
    POSITIVE LOGITS
    dial
    0.68
    ĨĴ
    0.67
    sweet
    0.66
    ocally
    0.64
    icians
    0.62
    ampton
    0.62
     Dial
    0.62
    ophob
    0.62
     FIGHT
    0.61
     litter
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.