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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lihood
    -0.88
    phrine
    -0.83
    erb
    -0.80
    gdala
    -0.75
    oft
    -0.74
    haw
    -0.74
    zer
    -0.73
    gew
    -0.72
    heid
    -0.71
    oler
    -0.71
    POSITIVE LOGITS
    ãĤ·ãĥ£
    0.69
     exha
    0.66
     practition
    0.62
     Finance
    0.62
    ãĤ´
    0.61
    Þ
    0.60
     earthqu
    0.58
     racket
    0.58
     ����
    0.58
     accompan
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.