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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names of organizations, schools, and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hindsight
    -0.14
     futures
    -0.14
    ELLOW
    -0.13
     rival
    -0.13
     fals
    -0.13
    venue
    -0.13
    udi
    -0.13
     jeopardy
    -0.13
    veral
    -0.13
    ellow
    -0.13
    POSITIVE LOGITS
     team
    0.26
     portion
    0.26
     experience
    0.25
     story
    0.23
     approach
    0.23
     guys
    0.21
     folks
    0.20
     website
    0.19
     crew
    0.19
     situation
    0.19
    Act Density 0.378%

    No Known Activations