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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mosqu
    -0.88
    ãĥĩãĤ£
    -0.83
     destro
    -0.82
     exting
    -0.79
    ãĤ´
    -0.76
     raft
    -0.75
     livest
    -0.75
    ©¶æ
    -0.74
     rul
    -0.73
    ãĥķãĤ¡
    -0.73
    POSITIVE LOGITS
    '
    0.95
    '-
    0.75
    '.
    0.74
    .'"
    0.73
    ',
    0.69
    ,'
    0.69
    '"
    0.69
    osures
    0.69
     Captain
    0.68
    eries
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.