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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    т
    0.75
    web
    0.70
    ari
    0.68
    shaus
    0.68
    v
    0.68
    í
    0.68
    ع
    0.68
    ం
    0.67
    та
    0.66
    ęb
    0.66
    POSITIVE LOGITS
     sparked
    0.79
     retirees
    0.78
     turbulence
    0.75
     appointees
    0.75
     tumors
    0.74
     decrees
    0.74
     attacks
    0.74
     instituted
    0.73
     superseded
    0.73
     aggregates
    0.73
    Act Density 0.000%

    No Known Activations