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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    !
    1.26
    ,
    1.09
    ?
    0.95
     were
    0.94
     grossly
    0.89
    графии
    0.89
    .
    0.89
     averted
    0.88
    --
    0.88
     Tens
    0.88
    POSITIVE LOGITS
    ти
    1.10
    または
    1.09
    isable
    1.04
    ಾ
    1.04
    те
    1.03
    en
    1.02
    扂
    0.98
    el
    0.96
    isée
    0.96
    ন্দ
    0.96
    Act Density 0.004%

    No Known Activations