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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     subsets
    1.24
    ‍♂
    1.21
     inescap
    1.20
     hangout
    1.20
     peeps
    1.16
     legit
    1.15
     hm
    1.15
     angenommen
    1.14
     reu
    1.13
     speculated
    1.12
    POSITIVE LOGITS
    },
    1.16
    olone
    1.09
    ../
    1.07
    walker
    1.05
    ল
    1.05
    arsi
    1.05
     ці
    1.03
    されている
    1.02
    ಸ್ತ
    1.00
    বিধান
    1.00
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.