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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Uriel
    -0.69
     forwarding
    -0.65
     Zionism
    -0.65
     Franco
    -0.65
    ${
    -0.63
    ithmetic
    -0.63
    ously
    -0.63
    antically
    -0.62
     JPMorgan
    -0.62
     Constantine
    -0.61
    POSITIVE LOGITS
    ĪĴ
    0.94
    ciating
    0.85
    yip
    0.81
    immune
    0.70
    ethnic
    0.69
    sed
    0.66
    士
    0.64
    animal
    0.64
    trial
    0.63
    cemic
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.