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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     skillet
    0.89
     driftwood
    0.89
     mesmer
    0.84
     dissidents
    0.84
     trespassing
    0.84
     thermocou
    0.83
     foodie
    0.83
    ],[
    0.82
     havoc
    0.82
     inefficiency
    0.82
    POSITIVE LOGITS
    PER
    0.79
    Pers
    0.73
    uclear
    0.69
    PI
    0.68
    ños
    0.68
    Type
    0.66
    hs
    0.65
    PERS
    0.65
    ENSIONS
    0.65
    esign
    0.64
    Act Density 0.000%

    No Known Activations