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

    Neuronpedia

    INDEX
    Explanations

    references to confusion or ambiguity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    confusion and ambiguity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.43
    InjectAttribute
    -0.42
    Plane
    -0.38
     jspb
    -0.38
     FetchType
    -0.37
    MigrationBuilder
    -0.37
     paroisse
    -0.36
     représentants
    -0.36
     ledit
    -0.35
    Cyfarwyddwr
    -0.35
    POSITIVE LOGITS
     confusion
    2.08
     Confusion
    1.96
    Confusion
    1.90
    confusion
    1.82
     confusión
    1.53
     confusing
    1.07
     confuse
    0.99
    混乱
    0.98
     confuses
    0.93
     chaos
    0.92
    Act Density 0.002%

    No Known Activations