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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    legation
    -0.07
    .tabPage
    -0.07
     financed
    -0.07
    ,map
    -0.06
    .trade
    -0.06
    伐
    -0.06
     Virgin
    -0.06
    respect
    -0.06
     volunteered
    -0.06
     diesen
    -0.06
    POSITIVE LOGITS
    etti
    0.08
     Inflate
    0.07
    ASI
    0.07
    之人
    0.07
    قه
    0.07
    乐器
    0.07
    摄入
    0.07
    ила
    0.07
    ium
    0.07
     włos
    0.06
    Act Density 0.035%

    No Known Activations