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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Ys
    1.04
     POP
    1.02
     RSC
    0.99
    Pop
    0.97
    oy
    0.96
     Pop
    0.96
    roy
    0.96
    Obj
    0.95
     Poc
    0.95
    Dy
    0.95
    POSITIVE LOGITS
     mannit
    0.83
    ----------------
    0.82
     Herman
    0.79
     mannitol
    0.79
     Kran
    0.73
     Cann
    0.72
    katan
    0.72
     Vetter
    0.72
     Rift
    0.70
     Chandler
    0.70
    Act Density 2.043%

    No Known Activations