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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting commands related to underlining

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cess
    -0.71
    lys
    -0.71
    …
    -0.71
     …
    -0.67
     Brande
    -0.67
     Firestone
    -0.65
    ovací
    -0.65
     Dha
    -0.64
    bolt
    -0.64
     Games
    -0.64
    POSITIVE LOGITS
    <u>
    1.09
    </u>
    1.08
    期刊论文
    0.95
    ❤❤
    0.93
    ····
    0.91
    .​
    0.89
     referenties
    0.87
    LEncoder
    0.86
     chré
    0.85
     againſt
    0.83
    Act Density 0.095%

    No Known Activations