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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    olatile
    -0.07
    Joseph
    -0.07
     Florida
    -0.07
    China
    -0.07
     Belfast
    -0.07
     Mind
    -0.07
    <Component
    -0.06
     CFR
    -0.06
    Н
    -0.06
     figure
    -0.06
    POSITIVE LOGITS
    骶
    0.08
     agendas
    0.07
    🖇
    0.07
    סבי
    0.07
    销量
    0.07
    捺
    0.07
     pami
    0.07
    𬤝
    0.07
    业务
    0.07
     gramm
    0.07
    Act Density 0.017%

    No Known Activations