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

    Neuronpedia

    INDEX
    Explanations

    terms related to clarification and explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADVERTISEMENT
    -0.16
     Valent
    -0.16
    olet
    -0.16
    andas
    -0.15
    ylan
    -0.14
    aggi
    -0.14
    má
    -0.14
    elson
    -0.14
    ù
    -0.14
    esen
    -0.14
    POSITIVE LOGITS
    oup
    0.16
    æĺ¯æĪij
    0.15
    ithe
    0.15
    205
    0.15
    ãĤ¤ãĥĪ
    0.14
    ith
    0.13
     Cougar
    0.13
    degree
    0.13
    -cut
    0.13
    ibrate
    0.13
    Act Density 0.006%

    No Known Activations