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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance and related formal attributes or disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     relative
    -0.17
    relative
    -0.16
    rea
    -0.16
    amba
    -0.16
    bie
    -0.15
    rl
    -0.15
    rex
    -0.15
    aj
    -0.15
    ombo
    -0.14
    ione
    -0.14
    POSITIVE LOGITS
    iyat
    0.16
     FORMAT
    0.15
    oise
    0.15
    imat
    0.15
     ÐŀÑģÑĤ
    0.15
    erro
    0.15
    odash
    0.14
    ussy
    0.14
    requency
    0.14
    formats
    0.14
    Act Density 0.013%

    No Known Activations