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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly surnames and first names

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to prominent individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.75
    pmwiki
    -0.61
    Cola
    -0.58
    afety
    -0.56
     Nieto
    -0.55
     Alto
    -0.54
    ça
    -0.53
    taboola
    -0.53
    issance
    -0.51
     ACTIONS
    -0.51
    POSITIVE LOGITS
    apes
    0.51
    ratulations
    0.50
    ansom
    0.47
    uchi
    0.47
     sled
    0.47
     ransom
    0.46
     mobs
    0.46
    brid
    0.46
    nir
    0.46
    amaz
    0.46
    Act Density 1.271%

    No Known Activations