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 that are past tense or indicate completed actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bies
    -0.63
    thur
    -0.63
    tis
    -0.59
    ansk
    -0.57
    aters
    -0.57
    MAT
    -0.57
     tag
    -0.56
     inscription
    -0.56
    eda
    -0.55
    ¾
    -0.54
    POSITIVE LOGITS
    nesday
    0.80
    dit
    0.77
    ieval
    0.74
    Downloadha
    0.73
    OPE
    0.70
    monton
    0.70
    GGGG
    0.65
    adoes
    0.65
     Pradesh
    0.64
    rome
    0.63
    Act Density 0.150%

    No Known Activations