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

    Neuronpedia

    INDEX
    Explanations

    key concepts and terms related to social sciences and philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikip
    -0.17
    ewe
    -0.15
    elihood
    -0.15
    Fallback
    -0.15
    аниÑĨ
    -0.15
    .FontStyle
    -0.14
    eward
    -0.14
    icter
    -0.14
    æķ¬
    -0.14
    757
    -0.13
    POSITIVE LOGITS
     Gilles
    0.28
     Fou
    0.26
     Lac
    0.22
     Cinema
    0.20
     Ž
    0.20
     thinkers
    0.19
     philosophy
    0.19
     Continental
    0.19
     Michel
    0.19
     cinema
    0.18
    Act Density 0.016%

    No Known Activations