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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ’in
    -0.07
    份
    -0.06
     face
    -0.06
     onData
    -0.06
    aked
    -0.06
    lke
    -0.06
     Land
    -0.06
     hype
    -0.06
    🎬
    -0.06
     fame
    -0.06
    POSITIVE LOGITS
    asInstanceOf
    0.07
     Scala
    0.07
     наличии
    0.07
     origins
    0.07
     découvert
    0.07
    ochen
    0.07
    兼任
    0.07
     DPR
    0.07
    厦门市
    0.07
    ∴
    0.06
    Act Density 0.004%

    No Known Activations