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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    oai_token-act-pair · gpt-3.5-turbo

    references to a significant concept or entity, potentially related to societal or political themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Li
    -0.90
    Putin
    -0.88
    LS
    -0.88
    Linux
    -0.87
    ocks
    -0.86
    ls
    -0.85
    leys
    -0.85
     Jess
    -0.84
    Jess
    -0.84
    Islam
    -0.84
    POSITIVE LOGITS
     Foster
    1.07
     Bride
    1.01
     Berman
    0.99
     Patriot
    0.99
     Gerry
    0.97
     Grail
    0.95
     Herman
    0.93
     Heritage
    0.93
     Frontier
    0.89
     Cantor
    0.88
    Act Density 0.528%

    No Known Activations