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

    Neuronpedia

    INDEX
    Explanations

    keywords related to code interfaces and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thon
    -0.17
    ubat
    -0.16
    NSE
    -0.15
    .wordpress
    -0.15
    eri
    -0.15
    ÑĪÑĤ
    -0.14
    lane
    -0.14
    Ïģκ
    -0.14
    ught
    -0.14
    dy
    -0.14
    POSITIVE LOGITS
    udd
    0.15
     &);↵
    0.15
    ilm
    0.14
     assortment
    0.14
     worlds
    0.14
    utting
    0.14
     LTD
    0.14
    ese
    0.14
    887
    0.14
    شر
    0.14
    Act Density 0.000%

    No Known Activations