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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    effective
    -0.07
    🔵
    -0.07
    향
    -0.07
    [selected
    -0.07
    有幸
    -0.07
    暗暗
    -0.07
    (guild
    -0.07
     flakes
    -0.06
     TableName
    -0.06
    ")));↵
    -0.06
    POSITIVE LOGITS
    🂻
    0.07
    刻苦
    0.07
    checkpoint
    0.07
    ObjectName
    0.06
    建筑物
    0.06
    antis
    0.06
    _pos
    0.06
     impossible
    0.06
    .isDirectory
    0.06
    .Diagnostics
    0.06
    Act Density 0.008%

    No Known Activations