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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating that there is not much of something specific

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest a lack of significance or abundance, particularly using the word "much."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.89
    ĪĴ
    -0.76
    izoph
    -0.76
    Ł
    -0.76
    bey
    -0.76
    Ĥİ
    -0.72
    idon
    -0.71
    acia
    -0.68
    ramid
    -0.66
    inx
    -0.65
    POSITIVE LOGITS
     anymore
    1.24
     else
    0.99
     nor
    0.84
     unless
    0.82
     bothered
    0.80
     except
    0.80
    outside
    0.80
     specifics
    0.79
     whatsoever
    0.79
     besides
    0.78
    Act Density 0.156%

    No Known Activations