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

    Neuronpedia

    INDEX
    Explanations

    references to job roles and promotions within an organizational context

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

    preceding job titles or positions

    np_acts-logits-general · gemini-2.0-flash

    job titles and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MethodManager
    -0.57
     PyTuple
    -0.53
    BufferException
    -0.52
    Persistence
    -0.50
    GIVEREF
    -0.50
     isNameExpr
    -0.49
    NgModule
    -0.49
    LayoutConstraint
    -0.49
     ſever
    -0.49
    MessageDigest
    -0.48
    POSITIVE LOGITS
     position
    2.40
     role
    2.35
     Position
    1.90
    role
    1.84
    position
    1.81
     roles
    1.79
     positions
    1.79
     POSITION
    1.74
     Role
    1.72
    Position
    1.68
    Act Density 0.399%

    No Known Activations