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

    Neuronpedia

    INDEX
    Explanations

    numerical or quantitative references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĤº
    -0.17
    nothrow
    -0.16
    ãĥ³ãĥĹ
    -0.15
    enz
    -0.15
    alfa
    -0.15
    dre
    -0.14
    WND
    -0.14
    dete
    -0.14
    ivel
    -0.13
     Noel
    -0.13
    POSITIVE LOGITS
    alion
    0.16
    uba
    0.16
    urat
    0.16
    ottage
    0.15
    antanamo
    0.15
     conv
    0.15
    parator
    0.15
    isky
    0.14
    essen
    0.14
    forced
    0.14
    Act Density 0.004%

    No Known Activations