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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is not complete or finalized yet

    oai_token-act-pair · gpt-3.5-turbo

    the word "yet" indicating something is pending or incomplete

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rities
    -0.79
    rador
    -0.77
    regate
    -0.74
    guy
    -0.74
    ãĤ¦ãĤ¹
    -0.73
    azar
    -0.73
    é¾
    -0.72
    Ĥª
    -0.72
    warts
    -0.71
    APTER
    -0.71
    POSITIVE LOGITS
     anymore
    0.88
     yet
    0.80
     formally
    0.78
     officially
    0.77
    hin
    0.73
     underway
    0.72
     exists
    0.68
     nor
    0.67
     renew
    0.67
     again
    0.66
    Act Density 0.014%

    No Known Activations