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

    Neuronpedia

    INDEX
    Explanations

    terms indicating something unique or noteworthy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yntaxException
    -0.58
    któ
    -0.56
     professionali
    -0.56
     alimentaire
    -0.56
    InjectAttribute
    -0.55
     prosecute
    -0.55
    ahnya
    -0.53
     république
    -0.53
     tendenza
    -0.53
     llamo
    -0.53
    POSITIVE LOGITS
     special
    3.97
     Special
    3.53
    special
    3.48
    Special
    3.44
    SPECIAL
    2.90
     SPECIAL
    2.89
     speciale
    2.56
     specials
    2.24
    特殊
    2.17
     especial
    2.17
    Act Density 0.066%

    No Known Activations