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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    nants
    -0.78
    enaries
    -0.76
    odder
    -0.74
     detach
    -0.73
    ottage
    -0.72
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
     fragmentation
    -0.68
    aceae
    -0.68
    ledged
    -0.66
     partitions
    -0.66
    POSITIVE LOGITS
     Alert
    0.80
     Mog
    0.77
     Saying
    0.74
     Hond
    0.71
    stanbul
    0.71
     Reyes
    0.68
     Dise
    0.67
     Reporting
    0.66
     hust
    0.66
     Tec
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.