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

    Neuronpedia

    INDEX
    Explanations

    references to gaining knowledge or new information through observation or discovery

    oai_token-act-pair · gpt-3.5-turbo

    references to past events and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -1.00
    "))
    -0.90
    ");
    -0.85
    ").
    -0.81
    !",
    -0.79
    !".
    -0.78
    )",
    -0.78
    "},
    -0.76
    ').
    -0.76
     ',
    -0.76
    POSITIVE LOGITS
     somebody
    1.07
     uh
    1.06
    --
    1.00
     basically
    0.99
    Enlarge
    0.97
     sort
    0.97
    ----
    0.96
     everybody
    0.91
    ——
    0.89
     kind
    0.89
    Act Density 0.865%

    No Known Activations