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

    Neuronpedia

    INDEX
    Explanations

    unique and specific names and terms from various contexts, such as names of individuals, books, places, and events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or fictional characters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.65
    ãĥĥãĥī
    -0.62
     nor
    -0.61
    ãĤ°
    -0.59
    renheit
    -0.56
    pload
    -0.55
     or
    -0.54
    ãĥ´ãĤ¡
    -0.53
    ij士
    -0.53
    ãĤ¸
    -0.52
    POSITIVE LOGITS
     respectively
    1.49
     alike
    1.29
     collide
    1.03
     are
    1.01
     were
    0.91
     abound
    0.88
     unite
    0.86
     combine
    0.84
     ARE
    0.80
     converge
    0.80
    Act Density 0.555%

    No Known Activations