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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.79
    unker
    -0.77
    arse
    -0.73
    aturdays
    -0.69
    inators
    -0.68
     commute
    -0.66
    ilight
    -0.66
    erry
    -0.65
    irtual
    -0.65
    assin
    -0.64
    POSITIVE LOGITS
     floats
    0.66
     DOI
    0.64
     PID
    0.63
    acion
    0.62
     Codes
    0.62
     CODE
    0.61
    ©¶æ¥µ
    0.61
    binding
    0.61
    ãĤ¼ãĤ¦ãĤ¹
    0.60
    uria
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.