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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing the concept of enjoyment or having a good time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize enjoyment or a sense of abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endas
    -0.81
    ghazi
    -0.68
    ctors
    -0.65
    ettings
    -0.64
     Ending
    -0.63
    rities
    -0.63
    alks
    -0.63
    illions
    -0.63
    =#
    -0.62
    mares
    -0.62
    POSITIVE LOGITS
     worth
    0.81
     coincidence
    0.75
     fun
    0.75
     understatement
    0.70
     hassle
    0.68
     akin
    0.68
     preferable
    0.68
     harb
    0.66
     tempered
    0.66
     alright
    0.66
    Act Density 0.190%

    No Known Activations