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

    Neuronpedia

    INDEX
    Explanations

    references to different editions of publications or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undi
    -0.17
    ãģªãĤĭ
    -0.16
    ans
    -0.16
    eron
    -0.15
    er
    -0.15
    upp
    -0.15
     popcorn
    -0.14
     Stellar
    -0.14
    idden
    -0.14
    fit
    -0.14
    POSITIVE LOGITS
    holm
    0.18
    icated
    0.17
    redient
    0.16
    brief
    0.16
    ÛĮزÛĮ
    0.16
    .gdx
    0.16
    icio
    0.15
    veloper
    0.15
    ration
    0.15
    tl
    0.15
    Act Density 0.018%

    No Known Activations