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

    Neuronpedia

    INDEX
    Explanations

    references to perspective and points of view in narratives

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

    dialogue and divine conversation

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects expressions that mark viewpoint or perspective (phrases like "from X's point of view", "the perspective of", "role of", "in the ...").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.52
    ânsito
    -0.50
     onResponse
    -0.47
    EDEFAULT
    -0.47
    RenderAtEndOf
    -0.44
    Rüyada
    -0.43
     gynhyrchwyd
    -0.43
     Sobald
    -0.42
     typelib
    -0.41
     referrerpolicy
    -0.41
    POSITIVE LOGITS
    новниш
    0.50
    essional
    0.41
    的角度
    0.41
    optionalTypeArgs
    0.41
     dialogue
    0.40
    dialogue
    0.38
    Descriere
    0.38
    cerpt
    0.37
     Carrasco
    0.37
     tearDown
    0.37
    Act Density 0.051%

    No Known Activations