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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Skydragon
    -0.85
    entimes
    -0.77
     toget
    -0.74
     liqu
    -0.71
     0004
    -0.70
    bia
    -0.69
     Petro
    -0.67
    ipedia
    -0.66
    yip
    -0.65
    )</
    -0.64
    POSITIVE LOGITS
     iteration
    0.69
     Gould
    0.68
     Bun
    0.61
    steps
    0.61
     Pt
    0.61
     Grassley
    0.60
     closest
    0.59
    later
    0.59
    wal
    0.58
     :=
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.