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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    onies
    -0.78
    sites
    -0.70
     slashed
    -0.68
     pir
    -0.67
     unborn
    -0.66
     sanctuary
    -0.65
     rapist
    -0.65
    ening
    -0.64
     sorcery
    -0.64
     Tup
    -0.62
    POSITIVE LOGITS
     tf
    0.81
    uary
    0.71
     congratulate
    0.70
    è£ħ
    0.68
    ðĿ
    0.68
    FactoryReloaded
    0.66
    çĶ°
    0.66
     outpatient
    0.65
    HL
    0.65
    arching
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.