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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     BOM
    0.83
     eigenvalue
    0.81
     Jonah
    0.79
    ATTLE
    0.74
     devils
    0.72
     ಬ್ಯಾ
    0.71
     bastard
    0.71
     collinear
    0.70
     newline
    0.70
     larvae
    0.69
    POSITIVE LOGITS
     Instead
    0.96
    Instead
    0.96
     instead
    0.92
     safer
    0.92
     responsibly
    0.89
     safely
    0.89
    安全
    0.89
     respectfully
    0.88
     respectful
    0.86
    安全的
    0.85
    Act Density 3.813%

    No Known Activations