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

    Neuronpedia

    INDEX
    Explanations

    Japanese characters and words

    oai_token-act-pair · gpt-3.5-turbo

    special characters and specific letter combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.86
    ifications
    -0.80
    vana
    -0.70
     externalToEVAOnly
    -0.69
    inates
    -0.68
    adder
    -0.68
     Siren
    -0.67
    nesday
    -0.67
     Tid
    -0.67
    istically
    -0.66
    POSITIVE LOGITS
    ´
    1.26
    1.18
    ķ
    1.18
    ¼
    1.17
    ĥ
    1.14
    ²
    1.14
    ĵĺ
    1.10
    á
    1.10
    ½
    1.07
    ¾
    1.07
    Act Density 0.002%

    No Known Activations