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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    brance
    -0.90
     sacrific
    -0.77
     tremend
    -0.72
    ,—
    -0.70
     favor
    -0.69
     answ
    -0.68
     practise
    -0.68
     challeng
    -0.67
     favour
    -0.67
     enrich
    -0.66
    POSITIVE LOGITS
     Hancock
    0.76
     Recon
    0.75
     Chow
    0.75
     Sah
    0.73
    States
    0.73
    anus
    0.71
    hold
    0.71
    zee
    0.68
    Nut
    0.68
    Whe
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.