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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Berman
    -0.78
    atics
    -0.70
    esh
    -0.64
    atile
    -0.64
    ancy
    -0.61
     Everett
    -0.61
     Curry
    -0.60
    RESULTS
    -0.60
    ivist
    -0.59
     dwar
    -0.58
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    0.73
    atform
    0.72
    place
    0.70
    ffen
    0.70
    ktop
    0.68
     cradle
    0.68
    zac
    0.66
    ^^^^
    0.65
     elig
    0.64
    Tele
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.