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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce or highlight specific examples, lists, or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llum
    -0.16
    еÑĨÑĤ
    -0.15
    สล
    -0.15
    ftware
    -0.15
    hua
    -0.15
    atters
    -0.14
     Commentary
    -0.14
    ingles
    -0.14
    orum
    -0.14
     pornstar
    -0.14
    POSITIVE LOGITS
     example
    0.23
     exemple
    0.20
    example
    0.19
     examples
    0.17
     list
    0.17
     heads
    0.17
     Example
    0.17
     exemp
    0.16
     tip
    0.16
     hint
    0.16
    Act Density 0.055%

    No Known Activations