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

    Neuronpedia

    INDEX
    Explanations

    people, places, or events containing the letters "me"

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and related personal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.83
    paralle
    -0.71
    ernels
    -0.70
    iosity
    -0.70
    olor
    -0.66
    rican
    -0.64
    raviolet
    -0.63
    hips
    -0.63
    keyes
    -0.62
    inyl
    -0.62
    POSITIVE LOGITS
    asure
    1.25
    anwhile
    1.12
    zzo
    1.06
    lda
    1.03
    isters
    0.93
    adow
    0.91
    leon
    0.89
    adows
    0.89
    ister
    0.89
    eting
    0.88
    Act Density 0.016%

    No Known Activations