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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     evade
    -0.15
     closest
    -0.14
     Tort
    -0.14
     associate
    -0.14
     statist
    -0.14
     áp
    -0.14
    onet
    -0.14
     personalities
    -0.13
     eldre
    -0.13
     thresh
    -0.13
    POSITIVE LOGITS
     Insight
    0.16
     scores
    0.15
     cons
    0.14
    ãģĭãģĦ
    0.14
    کاÙĨ
    0.14
    |{↵
    0.14
    одо
    0.14
    ç
    0.14
    ãģĭãģĹ
    0.14
    wap
    0.13
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.