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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     thicker
    -0.74
     exclusive
    -0.73
     extingu
    -0.65
     warranty
    -0.64
    aii
    -0.62
     flame
    -0.61
     arcane
    -0.61
     vortex
    -0.60
     tutorials
    -0.60
    apist
    -0.59
    POSITIVE LOGITS
    erity
    0.88
    rio
    0.88
    clock
    0.74
     Properties
    0.74
    fm
    0.70
    ogly
    0.69
    ggies
    0.68
    otype
    0.67
    phen
    0.66
     Transit
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.