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

    Neuronpedia

    INDEX
    Explanations

    terms related to artificial intelligence and sentient entities

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

    sentient living intelligent entities

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

    Detects when a text describes an entity (especially non-human or artificial) as sentient, conscious, or otherwise an animate/agent-like being.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     Premium
    -0.39
     ✭✭
    -0.36
    一向
    -0.35
    plik
    -0.35
    Premium
    -0.35
     pince
    -0.35
     encom
    -0.35
     premium
    -0.34
     للمعارف
    -0.34
    slidesPer
    -0.34
    POSITIVE LOGITS
     surla
    0.56
     Administrativna
    0.56
    脚注の使い方
    0.56
    0.54
    principalTable
    0.51
    MLLoader
    0.50
    umman
    0.50
     CreateTagHelper
    0.49
    inSlope
    0.48
     gesteld
    0.48
    Act Density 0.255%

    No Known Activations