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

    Neuronpedia

    INDEX
    Explanations

    keywords relating to rules or guidelines

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thirds
    -0.81
     Hasan
    -0.68
    FORE
    -0.67
     Lans
    -0.63
    butt
    -0.61
     Teresa
    -0.59
     Haram
    -0.57
     Cyrus
    -0.57
     Pound
    -0.57
     ashore
    -0.57
    POSITIVE LOGITS
    ions
    2.02
    ive
    2.01
    ively
    1.95
    ives
    1.90
    ivity
    1.76
    ors
    1.67
    iveness
    1.67
    ibles
    1.64
    ivist
    1.63
    ional
    1.62
    Act Density 0.216%

    No Known Activations