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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     training
    0.54
     vyn
    0.49
     air
    0.49
    ید
    0.48
    ס
    0.45
     TABLE
    0.45
     participation
    0.44
    지
    0.44
    트
    0.44
     classical
    0.43
    POSITIVE LOGITS
    nič
    0.52
    köz
    0.51
    不变
    0.45
    Cober
    0.44
    ጵ
    0.43
    ását
    0.43
     മാറ
    0.43
    msqrt
    0.43
    <0x9A>
    0.42
    góc
    0.42
    Act Density 0.000%

    No Known Activations