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

    Neuronpedia

    INDEX
    Explanations

    terms related to hierarchy and subservience

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

    subordinate, subordination, subjugation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.39
     Biôgrafia
    -0.35
     sprawd
    -0.34
    Vá
    -0.34
    Happ
    -0.34
    Exam
    -0.33
    checks
    -0.33
     Betracht
    -0.33
    exam
    -0.32
    Checks
    -0.32
    POSITIVE LOGITS
     subordinate
    1.99
     subordinated
    1.71
     subordinates
    1.49
     subordin
    1.49
     subordination
    1.45
     подчи
    1.00
    ordinate
    0.89
    inferior
    0.87
    ordinates
    0.82
     subserv
    0.81
    Act Density 0.005%

    No Known Activations