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

    Neuronpedia

    INDEX
    Explanations

    words related to exemplifying or embodying ideals or concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to exemplification and embodiment of concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.83
    hand
    -0.78
     wash
    -0.69
     sterile
    -0.67
     hump
    -0.63
     oats
    -0.63
    pora
    -0.62
    hunt
    -0.62
    duct
    -0.62
    plan
    -0.62
    POSITIVE LOGITS
     exempl
    1.28
     embodies
    0.92
    ifies
    0.86
    rities
    0.86
    PLIC
    0.85
    ified
    0.84
    orer
    0.84
    ifiers
    0.82
    ãĤ©
    0.81
    hetical
    0.80
    Act Density 0.006%

    No Known Activations