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

    Neuronpedia

    INDEX
    Explanations

    phrases related to control and regulation within systems

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

    "... control" or "controlled" following certain words

    np_acts-logits-general · gemini-2.0-flash

    out of control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.60
    AutoField
    -0.52
    enumi
    -0.52
    yntaxException
    -0.51
    ForRow
    -0.50
    ChildIndex
    -0.50
    RegistryLite
    -0.48
    etCode
    -0.47
    ANDUM
    -0.46
    tedrale
    -0.46
    POSITIVE LOGITS
     control
    3.28
     Control
    2.93
    control
    2.92
     CONTROL
    2.76
    Control
    2.73
    CONTROL
    2.58
     controlling
    2.50
     contrôle
    2.46
     controlled
    2.43
     controll
    2.40
    Act Density 0.609%

    No Known Activations