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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political goals and scientific aims

    oai_token-act-pair · gemini-2.0-flash

    words related to objectives

    np_token-act-pair-logits · gpt-4o-mini

    goal or purpose

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.75
     Ause
    -0.73
    migrationBuilder
    -0.67
    AccessorTable
    -0.63
    OGND
    -0.62
    yntaxException
    -0.59
    DoubleQuotes
    -0.57
    DataPropertyName
    -0.57
    delwed
    -0.53
     ویکی‌پدیا
    -0.53
    POSITIVE LOGITS
     object
    1.45
     objective
    1.31
     ends
    1.31
     end
    1.25
    object
    1.22
     OBJECT
    1.20
     goal
    1.20
     objects
    1.16
     objectives
    1.14
     goals
    1.11
    Act Density 2.419%

    No Known Activations