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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs ending in 'ed'

    oai_token-act-pair · gpt-3.5-turbo

    words with certain verb endings, particularly those that suggest a completed action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lauder
    -0.72
    ITNESS
    -0.71
    VERTISEMENT
    -0.66
    OSP
    -0.65
    abet
    -0.62
    Afee
    -0.60
     Restaur
    -0.58
    itans
    -0.57
    ORY
    -0.57
    OTOS
    -0.56
    POSITIVE LOGITS
    addle
    0.96
     away
    0.85
    ucket
    0.85
     out
    0.83
     forth
    0.81
    down
    0.81
    away
    0.81
     Away
    0.80
     down
    0.79
    tips
    0.79
    Act Density 0.148%

    No Known Activations