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

    Neuronpedia

    INDEX
    Explanations

    words related to online sources or content posting

    oai_token-act-pair · gpt-3.5-turbo

    special characters or formatting related to web links and paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.75
     Ae
    -0.64
    inctions
    -0.61
    æĪ¦
    -0.61
    irie
    -0.61
    ratulations
    -0.60
    piration
    -0.59
    pire
    -0.58
    çķ
    -0.57
     Nab
    -0.55
    POSITIVE LOGITS
    t
    0.89
    icer
    0.76
    T
    0.72
    TL
    0.70
    TD
    0.67
    ts
    0.64
    ¹
    0.64
    ª
    0.63
    schild
    0.63
    ti
    0.62
    Act Density 0.102%

    No Known Activations