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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Patriot
    -0.78
     Shake
    -0.67
    avorite
    -0.67
     Flavoring
    -0.66
     scrimmage
    -0.64
    ames
    -0.64
     Presbyter
    -0.63
     kickoff
    -0.63
    gradation
    -0.61
    assian
    -0.61
    POSITIVE LOGITS
    ãĥ¥
    0.72
    chell
    0.68
    ocr
    0.66
     Chi
    0.66
    âĨ
    0.65
    ther
    0.64
    ©¶æ¥µ
    0.64
    oult
    0.63
    xi
    0.63
    />
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.