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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kla
    -0.07
    宪
    -0.07
     straightforward
    -0.07
     stakeholders
    -0.07
     Mentor
    -0.07
    ា
    -0.07
    .mo
    -0.07
    交通
    -0.06
    _tests
    -0.06
     Med
    -0.06
    POSITIVE LOGITS
     creepy
    0.07
     disguise
    0.07
    login
    0.07
    :new
    0.07
    ffff
    0.07
     BEFORE
    0.07
    븐
    0.07
    Doing
    0.07
    (space
    0.06
     Gree
    0.06
    Act Density 0.111%

    No Known Activations