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

    Neuronpedia

    INDEX
    Explanations

    words ending in '-ted'

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gutenberg
    -0.80
    vernment
    -0.73
     sqor
    -0.64
     cannabin
    -0.63
     preparations
    -0.62
    soDeliveryDate
    -0.60
     largeDownload
    -0.59
    CRIP
    -0.58
     actionGroup
    -0.58
     evaluating
    -0.58
    POSITIVE LOGITS
    ted
    1.38
    ting
    1.25
    geon
    0.98
    mouth
    0.98
    own
    0.92
    bed
    0.92
    ton
    0.91
    kered
    0.87
    pent
    0.85
    rive
    0.85
    Act Density 0.008%

    No Known Activations