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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ch
    0.43
    stylesheet
    0.40
    mito
    0.40
     feeling
    0.39
    ισε
    0.37
     phrases
    0.37
     definitiv
    0.37
    抜け
    0.37
    aniya
    0.37
     definitely
    0.36
    POSITIVE LOGITS
    тино
    0.44
    踟
    0.43
    tencent
    0.42
    堡
    0.40
     гало
    0.40
    窩
    0.39
    दिक
    0.38
    дай
    0.38
    гай
    0.38
    LAGAB
    0.38
    Act Density 0.002%

    No Known Activations