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

    Neuronpedia

    INDEX
    Explanations

    formal and structured language, particularly in the context of authority or hierarchy

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

    Following rules, formality, or precision

    np_acts-logits-general · gemini-2.0-flash

    strict, orderly, and formal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.60
    adaptiveStyles
    -0.58
     ErrIntOverflow
    -0.57
     OMITBAD
    -0.50
     freely
    -0.50
     يتيمه
    -0.49
     libremente
    -0.48
    SharedDtor
    -0.46
    Selfer
    -0.46
     FetchType
    -0.46
    POSITIVE LOGITS
     precision
    0.54
     rigid
    0.52
     strict
    0.50
     disciplined
    0.49
     methodical
    0.48
     rigide
    0.47
     orderly
    0.46
     formal
    0.46
     disiplin
    0.45
    Precision
    0.45
    Act Density 0.637%

    No Known Activations