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

    Neuronpedia

    INDEX
    Explanations

    proper nouns like names such as "Conan" and "Joan"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly 'Conan' and 'Joan'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achev
    -0.86
    ertodd
    -0.85
    atoon
    -0.74
    oby
    -0.71
    achu
    -0.71
    acca
    -0.70
    ramid
    -0.70
    ettel
    -0.69
    ached
    -0.68
    ystem
    -0.66
    POSITIVE LOGITS
    tons
    1.04
    uin
    0.87
    ãĥĥãĥĪ
    0.80
    Nap
    0.79
    ality
    0.73
    ahime
    0.72
    AAF
    0.70
    ts
    0.67
    ileen
    0.67
    iste
    0.66
    Act Density 0.029%

    No Known Activations