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

    Neuronpedia

    INDEX
    Explanations

    quotations and excerpts

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ont
    -0.79
     infinity
    -0.70
    atural
    -0.68
    poke
    -0.67
    rings
    -0.64
    ictional
    -0.64
    isable
    -0.64
    edi
    -0.62
    retion
    -0.62
    erent
    -0.62
    POSITIVE LOGITS
    anwhile
    1.08
    SPONSORED
    0.89
     Cosponsors
    0.89
    enegger
    0.89
    kefeller
    0.87
     NAACP
    0.77
    ¥ŀ
    0.77
     boycot
    0.73
     assassinated
    0.73
     moderates
    0.72
    Act Density 4.306%

    No Known Activations