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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    0
    0.94
    a
    0.88
    e
    0.76
    big
    0.75
    ↵↵
    0.73
    9
    0.73
    ی
    0.73
    2
    0.71
    hop
    0.71
     had
    0.68
    POSITIVE LOGITS
     pyrolysis
    0.88
     trivalent
    0.88
     electrop
    0.84
     aldehyde
    0.81
    ctree
    0.80
    ینګ
    0.79
     supremacist
    0.79
     erythemat
    0.79
     اسرائی
    0.78
     ഇവിടെ
    0.78
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.