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

    Neuronpedia

    INDEX
    Explanations

    strong affirmatives and emphatic expressions of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     realmente
    -0.24
     really
    -0.18
     simply
    -0.17
     gerçekten
    -0.17
     actually
    -0.17
     einfach
    -0.16
     simplement
    -0.16
     wirklich
    -0.16
    actually
    -0.15
    really
    -0.15
    POSITIVE LOGITS
    ãģªãģĮãĤī
    0.18
     NOT
    0.17
     not
    0.17
     worth
    0.16
    leck
    0.15
    /random
    0.15
    iswa
    0.15
     wouldn
    0.15
     something
    0.14
    ;y
    0.14
    Act Density 0.064%

    No Known Activations