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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of places

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to naming or being named after someone or something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heric
    -0.84
    ylene
    -0.82
     mediated
    -0.77
    olen
    -0.76
     toget
    -0.74
    alysis
    -0.71
    inson
    -0.69
    iot
    -0.67
    mediated
    -0.67
    mone
    -0.66
    POSITIVE LOGITS
    è£
    0.82
     Revival
    0.76
     Mayo
    0.73
     Haku
    0.73
     Presidents
    0.71
     Bohem
    0.71
    DonaldTrump
    0.71
     Ancients
    0.70
     Lore
    0.70
     Basil
    0.69
    Act Density 0.069%

    No Known Activations