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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     justice
    -0.08
    审计
    -0.08
    鞠
    -0.07
    利润
    -0.07
     harmony
    -0.07
    防守
    -0.07
     Zen
    -0.07
     women
    -0.07
     phishing
    -0.07
    充满
    -0.07
    POSITIVE LOGITS
    ?!
    0.08
     IUser
    0.08
    .has
    0.07
     tyr
    0.07
    Cheers
    0.06
    …and
    0.06
    _rsa
    0.06
    -powered
    0.06
    怆
    0.06
    _objs
    0.06
    Act Density 0.092%

    No Known Activations