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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    jri
    -0.97
    ernandez
    -0.72
     spilled
    -0.67
    ickr
    -0.66
     imperson
    -0.66
    isman
    -0.65
    steen
    -0.65
     Franco
    -0.64
    olicy
    -0.63
    avorite
    -0.63
    POSITIVE LOGITS
    oral
    0.73
     Introdu
    0.71
     introduces
    0.68
    Alpha
    0.66
     Receiver
    0.65
     Tasman
    0.62
    ë
    0.61
     Tenn
    0.61
     Sabha
    0.60
    nes
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.