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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names, specifically "Rud"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific proper nouns, particularly names and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ago
    -0.72
    ghazi
    -0.67
    uries
    -0.66
    Ø©
    -0.65
     flares
    -0.64
     combust
    -0.64
     ILCS
    -0.63
    tein
    -0.63
     Vietnam
    -0.63
    goers
    -0.63
    POSITIVE LOGITS
    imentary
    1.08
    olf
    1.02
    itionally
    0.92
    der
    0.91
    iom
    0.90
    eness
    0.90
    enthal
    0.88
     Rud
    0.88
    olph
    0.88
    lers
    0.87
    Act Density 0.031%

    No Known Activations