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

    Neuronpedia

    INDEX
    Explanations

    quotes and punctuation marks that indicate speech or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anske
    -0.15
    ekl
    -0.15
    enko
    -0.15
    feeds
    -0.15
    æĸĹ
    -0.14
    (optional
    -0.14
    irl
    -0.14
     jig
    -0.14
    GenerationStrategy
    -0.14
    iete
    -0.14
    POSITIVE LOGITS
     s
    0.17
     ab
    0.15
    uber
    0.15
     sh
    0.15
     segment
    0.15
    pure
    0.15
    ustr
    0.15
     pure
    0.14
    thing
    0.14
     segments
    0.14
    Act Density 0.082%

    No Known Activations