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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     другие
    0.98
    其他
    0.87
    異なる
    0.84
    Compra
    0.82
     अन्य
    0.80
     различные
    0.79
     необходимые
    0.79
    Przyp
    0.79
    ัญ
    0.78
    ඤ
    0.78
    POSITIVE LOGITS
     indulged
    0.76
     indulge
    0.72
     nice
    0.71
     annoyed
    0.71
     it
    0.64
     allowance
    0.63
     merr
    0.63
     injuries
    0.59
     yeah
    0.58
     allowances
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.