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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases or tokens and their importance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gens
    -0.20
    rome
    -0.18
    à¥įयव
    -0.16
    åŃĺäºİ
    -0.16
    ati
    -0.16
    indr
    -0.15
    .getBean
    -0.15
    irit
    -0.15
    illis
    -0.15
    iron
    -0.15
    POSITIVE LOGITS
     coast
    0.16
    //*[
    0.15
    yle
    0.14
    mlink
    0.14
    Ñģки
    0.14
    nesia
    0.14
    ШÐIJ
    0.14
     Giant
    0.13
    жа
    0.13
    aoke
    0.13
    Act Density 0.004%

    No Known Activations