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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     plur
    -0.78
    Accessory
    -0.74
     observable
    -0.71
    Consumer
    -0.70
    abulary
    -0.69
     shenan
    -0.68
    ables
    -0.65
     freezer
    -0.65
     pant
    -0.65
     neut
    -0.64
    POSITIVE LOGITS
    olulu
    0.92
     recruit
    0.75
    ieri
    0.66
    awa
    0.64
    uchi
    0.63
    hra
    0.62
    nikov
    0.62
     Ghana
    0.62
    thia
    0.61
    uba
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.