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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ospons
    -0.71
    theless
    -0.69
    irtual
    -0.69
    udi
    -0.66
    instance
    -0.65
    orph
    -0.65
     preferably
    -0.65
    entric
    -0.64
    align
    -0.64
    plement
    -0.63
    POSITIVE LOGITS
    mare
    0.75
    lot
    0.71
     Mald
    0.69
    ICE
    0.63
     Maid
    0.63
    uel
    0.62
     Browne
    0.61
     prelim
    0.61
     Trafford
    0.61
     coll
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.