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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting characters used in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acht
    -0.18
    ayo
    -0.16
    antz
    -0.16
     lesb
    -0.16
    onga
    -0.15
    den
    -0.15
    olas
    -0.14
    anzi
    -0.14
    rag
    -0.14
    riday
    -0.14
    POSITIVE LOGITS
     next
    0.15
    ello
    0.15
    lifetime
    0.15
     tomorrow
    0.14
    .amazonaws
    0.14
    Îļα
    0.14
    Tomorrow
    0.14
     Her
    0.14
     guy
    0.14
    ilage
    0.13
    Act Density 0.001%

    No Known Activations