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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    stv
    0.71
    anst
    0.59
     Stage
    0.59
     Fern
    0.55
     stage
    0.54
    Guard
    0.53
     filmmaker
    0.52
     hosp
    0.52
    观
    0.52
     supervisor
    0.51
    POSITIVE LOGITS
    IFT
    1.22
     LEWIS
    1.17
     Leasing
    1.15
    Miles
    1.11
     Lacy
    1.09
     Lena
    1.09
     mocha
    1.08
    Winters
    1.07
     twenties
    1.06
     Lewis
    1.06
    Act Density 2.276%

    No Known Activations