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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to brands, companies, or specific individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vengeance
    -0.69
    perty
    -0.66
     cruelty
    -0.61
    ß
    -0.61
     horizont
    -0.60
     antit
    -0.60
    MJ
    -0.59
     streng
    -0.58
    Þ
    -0.58
     sovere
    -0.56
    POSITIVE LOGITS
    baugh
    0.92
    kamp
    0.82
    DragonMagazine
    0.81
    ukong
    0.80
    EStream
    0.74
    borough
    0.71
    ãĤ¤ãĥĪ
    0.71
    furt
    0.70
     IMAGES
    0.70
    pedia
    0.68
    Act Density 0.193%

    No Known Activations