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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    u
    1.66
    e
    1.40
    i
    1.30
    evening
    1.27
    en
    1.27
    ate
    1.25
    ead
    1.24
    vr
    1.21
    an
    1.20
    д
    1.19
    POSITIVE LOGITS
     stencil
    1.21
     shields
    1.06
     bootcamp
    1.03
     shelters
    1.00
    सील
    0.98
     reluct
    0.97
     molde
    0.97
     gosh
    0.96
    ansky
    0.95
     scaler
    0.95
    Act Density 0.000%

    No Known Activations