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

    Neuronpedia

    INDEX
    Explanations

    mentions of particular editions or versions of something

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various editions or versions of publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vant
    -0.72
    bors
    -0.69
    apped
    -0.66
    pract
    -0.66
    vati
    -0.65
    amin
    -0.65
    ndra
    -0.65
    hart
    -0.65
    ello
    -0.64
     downed
    -0.63
    POSITIVE LOGITS
     edition
    1.04
     EDITION
    0.88
     Edition
    0.83
    ansion
    0.79
     editions
    0.77
    edition
    0.75
     Dragonbound
    0.74
    iversary
    0.72
    iatus
    0.72
    eers
    0.70
    Act Density 0.006%

    No Known Activations