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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Lak
    -0.60
    ________________________
    -0.59
     educate
    -0.58
    rees
    -0.58
     ped
    -0.56
     harshly
    -0.56
     ric
    -0.56
     rob
    -0.55
    plant
    -0.55
     Guru
    -0.55
    POSITIVE LOGITS
    Reviewer
    0.80
    incial
    0.70
    OPLE
    0.69
     extraord
    0.67
    inguishable
    0.63
    reme
    0.62
     è£ıè¦ļéĨĴ
    0.62
     Barton
    0.61
     Chr
    0.60
    comings
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.