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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    .validation
    -0.07
    (touch
    -0.07
     Silent
    -0.07
    备用
    -0.07
    .byte
    -0.07
    (Auth
    -0.07
     Cơ
    -0.07
     CallingConvention
    -0.07
     divul
    -0.07
    ]\\
    -0.07
    POSITIVE LOGITS
    ädchen
    0.08
     הכי
    0.07
    𬭎
    0.06
    ≾
    0.06
    公司
    0.06
    瓻
    0.06
     optimism
    0.06
    �
    0.06
     gy
    0.06
    𬟽
    0.06
    Act Density 0.114%

    No Known Activations