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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating scarcity or difficulty in obtaining something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "come."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tops
    -0.77
    ²¾
    -0.77
    icons
    -0.77
    ettings
    -0.74
    vacc
    -0.74
    asio
    -0.74
    pmwiki
    -0.73
    orthodox
    -0.73
    roller
    -0.72
    cell
    -0.72
    POSITIVE LOGITS
     undone
    1.08
     forth
    0.95
     out
    0.77
     up
    0.75
     closer
    0.73
     WRITE
    0.73
     INTO
    0.72
     ashore
    0.72
     attractions
    0.72
     together
    0.71
    Act Density 0.058%

    No Known Activations