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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Enem
    0.44
     Wrangler
    0.38
     Telegram
    0.38
     Olimp
    0.37
     Gentile
    0.37
     Defensive
    0.36
     Disqus
    0.36
    cente
    0.36
     cholest
    0.36
    杀了
    0.36
    POSITIVE LOGITS
    .’
    0.44
    !"
    0.43
    .}
    0.42
    !’
    0.39
    ."
    0.39
    -|
    0.39
    .'
    0.38
     ones
    0.38
    .**
    0.38
    .!
    0.38
    Act Density 0.000%

    No Known Activations