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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Behavior
    -0.06
    Behavior
    -0.06
     fell
    -0.06
    oe
    -0.06
     Sent
    -0.05
    ckett
    -0.05
    èĪ
    -0.05
     all
    -0.05
    lena
    -0.05
     Levy
    -0.05
    POSITIVE LOGITS
    icari
    0.08
    UrlParser
    0.07
    ioxide
    0.07
    ниÑģÑĤ
    0.07
    ibir
    0.07
    ellij
    0.07
    gesi
    0.07
    ToSelector
    0.07
    ĮĴ
    0.07
    ược
    0.07
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.