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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sensor
    0.51
    Context
    0.50
     Example
    0.49
     Context
    0.49
    نه
    0.48
    Sensor
    0.46
    হ
    0.46
    |_{
    0.45
     Employer
    0.45
     مضبوط
    0.45
    POSITIVE LOGITS
     giggle
    0.48
    んでいた
    0.47
    ]".
    0.46
     gigs
    0.45
     bắn
    0.44
     gig
    0.44
     arranging
    0.43
     으로
    0.43
     այ
    0.43
    ोक
    0.42
    Act Density 0.000%

    No Known Activations