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

    Neuronpedia

    INDEX
    Explanations

    sentences that provide instructions or guidelines, particularly regarding social behavior and etiquette

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

    words of caution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.56
     nahilalakip
    -0.55
    StoreMessageInfo
    -0.50
    曖昧さ回避
    -0.47
    Искәрмәләр
    -0.46
    Xna
    -0.43
    ScopeManager
    -0.43
    stateProvider
    -0.43
    RTGC
    -0.43
    Pranala
    -0.42
    POSITIVE LOGITS
     warning
    0.65
     warnings
    0.59
    Warning
    0.57
    warning
    0.56
     cautions
    0.54
     warns
    0.54
     Warning
    0.54
     admon
    0.53
     warned
    0.52
     caution
    0.52
    Act Density 0.148%

    No Known Activations