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

    Neuronpedia

    INDEX
    Explanations

    references to control and regulations related to systems or processes

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

    "control" and its variations

    np_acts-logits-general · gemini-2.0-flash

    act of control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {~
    -0.58
     rump
    -0.52
    onas
    -0.51
    布団
    -0.51
     Jennings
    -0.50
     ago
    -0.50
     Ayers
    -0.49
     Bens
    -0.48
    ης
    -0.48
    TIMES
    -0.47
    POSITIVE LOGITS
     control
    1.43
     controls
    1.42
     Controls
    1.42
     CONTROL
    1.41
     Control
    1.38
     Controlling
    1.33
    Controlling
    1.32
    control
    1.28
    Control
    1.26
    CONTROL
    1.25
    Act Density 0.151%

    No Known Activations