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

    Neuronpedia

    INDEX
    Explanations

    references to prestigious awards such as the Pulitzer Prize and Nobel Prize

    oai_token-act-pair · gpt-3.5-turbo

    references to prestigious awards and their winners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cry
    -0.74
    ALTH
    -0.71
    fun
    -0.69
    cos
    -0.68
     CY
    -0.66
    versions
    -0.65
    scripts
    -0.65
    ãĤ®
    -0.64
    rome
    -0.63
    nes
    -0.63
    POSITIVE LOGITS
     Prize
    1.07
     awarded
    0.93
     laureate
    0.87
     Winner
    0.84
     Winners
    0.83
    eous
    0.80
    inguished
    0.77
     laure
    0.76
     Award
    0.75
    ributed
    0.73
    Act Density 0.032%

    No Known Activations