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

    Neuronpedia

    INDEX
    Explanations

    references to popular media franchises and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ath
    -0.16
    lauf
    -0.15
     åĮĹ京
    -0.15
     Bottom
    -0.14
    esium
    -0.14
    .native
    -0.14
    -export
    -0.14
     æ¢
    -0.14
    enzhen
    -0.14
     Ath
    -0.14
    POSITIVE LOGITS
     Naruto
    0.26
    nar
    0.17
     Oro
    0.16
     Sas
    0.16
     Marco
    0.15
     Kag
    0.15
     Hin
    0.15
    engan
    0.15
     Sage
    0.15
    Marco
    0.15
    Act Density 0.004%

    No Known Activations