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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns indicating relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citoyen
    -0.33
     botines
    -0.32
     Autres
    -0.31
     bañ
    -0.31
     fijo
    -0.30
     sauvage
    -0.29
     muere
    -0.28
     tatuajes
    -0.28
     colegios
    -0.28
     libremente
    -0.28
    POSITIVE LOGITS
    <unused41>
    1.04
    [@BOS@]
    1.03
    <unused8>
    1.03
    <unused23>
    1.03
    <unused51>
    1.03
    <pad>
    1.03
    <unused3>
    1.03
    <unused16>
    1.03
    <unused52>
    1.03
    <unused14>
    1.03
    Act Density 0.023%

    No Known Activations