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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     EVENT
    -0.07
    --------------
    -0.07
    下面就
    -0.07
    风雨
    -0.07
     UPPER
    -0.07
    曦
    -0.07
    🅘
    -0.07
    ,',
    -0.07
     --------------------
    -0.07
    .NoArgsConstructor
    -0.06
    POSITIVE LOGITS
     engaging
    0.08
     safeguard
    0.07
    㙘
    0.06
    壕
    0.06
    篇文章
    0.06
     ellos
    0.06
    ◭
    0.06
    ⊗
    0.06
    arlo
    0.06
     cattle
    0.06
    Act Density 0.001%

    No Known Activations