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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ende
    -0.81
    culosis
    -0.76
    çīĪ
    -0.73
    anmar
    -0.72
    ILA
    -0.71
     nomine
    -0.70
    çĶ°
    -0.70
     tremend
    -0.69
    æ©Ł
    -0.69
    ebin
    -0.69
    POSITIVE LOGITS
    ut
    0.76
    olic
    0.68
    essional
    0.67
    nant
    0.65
     ellipt
    0.60
     innocent
    0.60
    zing
    0.60
    ising
    0.58
     Pastebin
    0.57
    isle
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.