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

    Neuronpedia

    INDEX
    Explanations

    numbers prefixed with "dec"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the word 'dec' followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -1.02
    WAYS
    -0.77
    ĪĴ
    -0.77
    ansas
    -0.74
    sth
    -0.72
    DragonMagazine
    -0.71
    culosis
    -0.70
    eworld
    -0.69
    Interstitial
    -0.68
     Dragonbound
    -0.67
    POSITIVE LOGITS
    rypted
    1.30
    ryption
    1.18
    oded
    1.18
    ried
    1.01
    ently
    1.00
    ibel
    0.96
     dec
    0.89
    arbon
    0.86
    encies
    0.86
    ency
    0.84
    Act Density 0.008%

    No Known Activations