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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     frequ
    -0.69
     burst
    -0.68
     sexually
    -0.63
     avg
    -0.63
    fully
    -0.63
     tremend
    -0.62
    fur
    -0.61
     smoker
    -0.61
     cruise
    -0.61
     auction
    -0.60
    POSITIVE LOGITS
    ãĥīãĥ©
    0.73
    umbs
    0.71
    itches
    0.67
     Gate
    0.67
    okemon
    0.66
    ramids
    0.65
     Chronicles
    0.65
    RECT
    0.65
    osure
    0.64
    OUN
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.