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

    Neuronpedia

    INDEX
    Explanations

    references to the letter 'D' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rick
    -0.22
    ж
    -0.21
    avis
    -0.21
    าว
    -0.21
    ave
    -0.19
    own
    -0.18
    esc
    -0.18
    ice
    -0.18
    ouble
    -0.18
    ocs
    -0.17
    POSITIVE LOGITS
    nip
    0.21
    nie
    0.20
    vů
    0.19
    ey
    0.18
    alia
    0.18
    acic
    0.17
    alamat
    0.17
    iverse
    0.17
    ivers
    0.17
    zer
    0.17
    Act Density 0.055%

    No Known Activations