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

    Neuronpedia

    INDEX
    Explanations

    terms related to limitations or constraints

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

    restriction, restricted, restrict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aub
    -0.51
    QMetaType
    -0.49
    One
    -0.49
    ViewInit
    -0.48
    newVal
    -0.48
    Johns
    -0.45
    + 
    -0.45
     + 
    -0.45
    Oleh
    -0.45
     Aub
    -0.45
    POSITIVE LOGITS
     restriction
    1.02
     restrict
    0.96
     restric
    0.96
     restricted
    0.94
     restrictions
    0.94
     Restriction
    0.90
    restriction
    0.90
     RESTRICT
    0.88
    restricted
    0.85
     Restrictions
    0.82
    Act Density 0.009%

    No Known Activations