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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    CLOSE
    -0.74
    ÃĽ
    -0.74
    OSS
    -0.72
    OIL
    -0.67
    Trend
    -0.67
    SEE
    -0.67
    Stud
    -0.66
    Russ
    -0.66
    WAYS
    -0.66
    OTH
    -0.64
    POSITIVE LOGITS
    self
    0.71
    poral
    0.71
     conscience
    0.68
     wills
    0.64
    nered
    0.64
    ional
    0.63
     Contra
    0.60
    selves
    0.60
    alian
    0.60
    ļéĨĴ
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.