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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Mult
    0.80
     paese
    0.79
     passione
    0.75
     ada
    0.75
     pasión
    0.75
     Ihrem
    0.74
     país
    0.73
    Mult
    0.73
    爱
    0.72
     gaat
    0.72
    POSITIVE LOGITS
     thereby
    1.21
     Then
    1.17
     Thereby
    1.13
    Then
    1.11
     thus
    1.10
     Thus
    1.09
     then
    1.08
    从而
    1.06
    thus
    1.05
    Thus
    1.01
    Act Density 1.183%

    No Known Activations