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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ynet
    -0.16
    аÑĤков
    -0.15
    okrat
    -0.15
    ãĤ©
    -0.15
     Kok
    -0.14
    λια
    -0.14
    asers
    -0.14
    clare
    -0.14
    yna
    -0.14
    pty
    -0.14
    POSITIVE LOGITS
    inen
    0.16
    chang
    0.15
    asc
    0.14
    cker
    0.14
    wa
    0.14
    ered
    0.14
     Lambert
    0.14
    ings
    0.14
    axter
    0.13
    ader
    0.13
    Act Density 0.064%

    No Known Activations