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

    Neuronpedia

    INDEX
    Explanations

    references to a specific character or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orre
    -0.16
    yt
    -0.16
    ra
    -0.15
    λα
    -0.15
    ÑĬ
    -0.15
    relude
    -0.15
    arris
    -0.14
    resse
    -0.14
    ingly
    -0.14
    au
    -0.14
    POSITIVE LOGITS
    itage
    0.28
    editary
    0.24
     Majesty
    0.24
    metic
    0.22
    bst
    0.21
    ewith
    0.20
    eto
    0.20
    etical
    0.20
    ders
    0.19
    oku
    0.19
    Act Density 0.035%

    No Known Activations