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

    Neuronpedia

    INDEX
    Explanations

    expressions of respect and submission in a hierarchical context

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

    bowed before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.45
    CppMethod
    -0.45
    Moder
    -0.44
    戬
    -0.43
    isNameExpr
    -0.42
     berke
    -0.40
     Shakspeare
    -0.40
     blitt
    -0.38
    隔
    -0.38
    WithIdentifier
    -0.38
    POSITIVE LOGITS
     kneel
    0.76
     kneeling
    0.67
     bowing
    0.63
     knelt
    0.63
     bowed
    0.62
     crouching
    0.55
     reverence
    0.50
     squat
    0.50
     crouch
    0.49
     bending
    0.48
    Act Density 0.015%

    No Known Activations