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

    Neuronpedia

    INDEX
    Explanations

    concepts related to grammatical structure and adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    digest
    -0.15
    onaut
    -0.14
     подÑĢаз
    -0.13
    cheid
    -0.13
    ado
    -0.13
     Pent
    -0.13
    лег
    -0.13
     пÑĢов
    -0.13
     лег
    -0.13
    å¯Ħ
    -0.13
    POSITIVE LOGITS
     possess
    0.32
     animate
    0.30
     masculine
    0.28
     gender
    0.28
     Gender
    0.28
    animate
    0.27
     demonstr
    0.26
     genders
    0.25
     possessed
    0.25
     feminine
    0.25
    Act Density 0.046%

    No Known Activations