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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated references, particularly focusing on personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clo
    -0.15
    /-
    -0.14
    empt
    -0.14
    sc
    -0.14
    fac
    -0.13
     Kn
    -0.13
    ised
    -0.13
    perm
    -0.13
    ahi
    -0.13
     Memo
    -0.13
    POSITIVE LOGITS
    oret
    0.21
    orem
    0.18
     ayrıca
    0.17
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.16
     ведÑĮ
    0.16
     certainly
    0.15
    커ìĬ¤
    0.14
    aminer
    0.14
     also
    0.14
     फर
    0.14
    Act Density 0.597%

    No Known Activations