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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     erst
    -0.08
     suff
    -0.08
    .bluetooth
    -0.07
    管网
    -0.07
    icket
    -0.07
     wind
    -0.06
     passage
    -0.06
     coupled
    -0.06
    صلة
    -0.06
    _tar
    -0.06
    POSITIVE LOGITS
    arbonate
    0.08
     tomatoes
    0.08
    עשייה
    0.07
    ículo
    0.07
    📗
    0.07
    什么样
    0.07
    𝕋
    0.07
    ]});↵
    0.07
    verts
    0.07
     shortcomings
    0.07
    Act Density 0.024%

    No Known Activations