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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ende
    -0.69
     intimid
    -0.67
     hurd
    -0.67
     aur
    -0.62
     tac
    -0.61
    ä¼
    -0.58
    pport
    -0.57
     translate
    -0.57
     anat
    -0.57
     guidance
    -0.57
    POSITIVE LOGITS
    Done
    0.74
     Bloom
    0.72
    ||||
    0.71
    ³³
    0.71
     Âł Âł
    0.70
    married
    0.70
    Rich
    0.68
    achine
    0.68
    uel
    0.67
    bilt
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.