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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social progress and historical ideology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omor
    -0.15
    ALSE
    -0.15
    kü
    -0.15
    ubat
    -0.15
    avax
    -0.15
    ÏħÏĩ
    -0.14
     mặt
    -0.14
    оÑĢоÑĤ
    -0.14
    elm
    -0.14
     democrat
    -0.14
    POSITIVE LOGITS
     Locke
    0.29
     Hob
    0.28
    Lock
    0.28
     Lock
    0.24
     Bent
    0.23
     Burke
    0.22
    .Lock
    0.21
     Adam
    0.21
     Raw
    0.20
     Mill
    0.20
    Act Density 0.095%

    No Known Activations