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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "originally" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avier
    -0.20
    amines
    -0.17
    al
    -0.17
    eton
    -0.16
    ắp
    -0.14
    Ñĭп
    -0.14
    enia
    -0.14
    ayne
    -0.14
    æ°£
    -0.14
    /site
    -0.14
    POSITIVE LOGITS
    istrat
    0.15
    еÑĢо
    0.15
    reb
    0.15
    umsuz
    0.14
    IKE
    0.14
    .emf
    0.14
     Trang
    0.14
    _TLS
    0.14
    fol
    0.13
    ahr
    0.13
    Act Density 0.018%

    No Known Activations