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

    Neuronpedia

    INDEX
    Explanations

    elements related to interpersonal relationships and emotional interactions

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

    Follows third-person pronouns

    np_acts-logits-general · gemini-2.0-flash

    making demands or requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reply
    -0.51
     hear
    -0.50
    Hear
    -0.49
     hears
    -0.49
    hear
    -0.48
    Allow
    -0.47
     Hear
    -0.46
     receives
    -0.45
     response
    -0.45
     Responses
    -0.45
    POSITIVE LOGITS
     demanding
    1.03
    demand
    1.02
     demands
    0.92
     demand
    0.91
     DEMAND
    0.90
     Demands
    0.89
    Demand
    0.88
     Demand
    0.84
     requesting
    0.83
     requests
    0.82
    Act Density 0.576%

    No Known Activations