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

    Neuronpedia

    INDEX
    Explanations

    references to the subjective experience of understanding and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    areth
    -0.15
    unken
    -0.15
    eur
    -0.14
    essim
    -0.14
    agger
    -0.13
    ety
    -0.13
    olle
    -0.13
    ear
    -0.13
     rub
    -0.13
    uil
    -0.13
    POSITIVE LOGITS
    /cal
    0.17
    StartPosition
    0.16
    оÑģÑĮ
    0.16
    tol
    0.16
    arius
    0.15
    ¤¤
    0.15
    qui
    0.14
    cho
    0.14
     Äiju
    0.14
     جع
    0.13
    Act Density 0.170%

    No Known Activations