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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    increase
    -0.08
     возраст
    -0.08
     bunny
    -0.07
    -tra
    -0.07
    lernen
    -0.07
    马桶
    -0.07
    ぬ
    -0.07
    つく
    -0.07
    ivities
    -0.07
    tank
    -0.07
    POSITIVE LOGITS
    Pub
    0.07
    Found
    0.07
     cupid
    0.07
    -caret
    0.07
     lecture
    0.07
    侥幸
    0.06
    tokenId
    0.06
    .setAuto
    0.06
     tempered
    0.06
     katılı
    0.06
    Act Density 0.008%

    No Known Activations