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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    annels
    0.66
    దన
    0.66
    ussels
    0.66
    Threat
    0.66
    пози
    0.64
    יוחד
    0.64
    cyon
    0.64
    ppins
    0.62
    Leftrightarrow
    0.62
    ޗ
    0.62
    POSITIVE LOGITS
     mistakes
    3.82
     mistake
    3.63
     Mistakes
    3.15
     errors
    3.07
     mistakenly
    2.96
     mis
    2.84
     mistaken
    2.83
     error
    2.81
     errores
    2.71
     blunder
    2.71
    Act Density 1.072%

    No Known Activations