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

    the letter 'T'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cannabin
    -0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
     actionGroup
    -0.73
    Ĥİ
    -0.71
    EStream
    -0.70
    vernment
    -0.69
    76561
    -0.69
     ment
    -0.67
     fentanyl
    -0.66
     acron
    -0.65
    POSITIVE LOGITS
    ARGET
    1.20
    ractor
    1.14
    ribute
    1.14
    ruck
    1.11
    ract
    1.09
    olkien
    1.09
    unes
    1.07
    aylor
    1.05
    roph
    1.04
    olerance
    1.02
    Act Density 0.033%

    No Known Activations