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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    er
    1.44
    in
    1.16
     vigorous
    1.08
    с
    1.08
     exuberant
    1.06
    ার
    1.02
     abruptly
    1.02
    ు
    1.01
    capped
    1.00
     sass
    0.97
    POSITIVE LOGITS
    ты
    1.41
     motivos
    1.30
    री
    1.28
     существу
    1.21
     그래서
    1.20
    殳
    1.20
    ない
    1.20
    uestra
    1.20
     vocês
    1.19
    ní
    1.18
    Act Density 0.410%

    No Known Activations