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

    Neuronpedia

    INDEX
    Explanations

    names of famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals, particularly those named Michel or Jacques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conservancy
    -0.73
     Alaska
    -0.71
     Hawaii
    -0.68
     Honolulu
    -0.68
    ndra
    -0.68
     Anchorage
    -0.67
     Hawaiian
    -0.66
     Mariners
    -0.66
     dispensary
    -0.65
    thritis
    -0.64
    POSITIVE LOGITS
    angelo
    1.38
     Fou
    1.01
     Michel
    1.01
    sonian
    0.89
    hetti
    0.89
    hou
    0.88
     Coul
    0.85
    otti
    0.84
     Kafka
    0.83
    insk
    0.82
    Act Density 0.021%

    No Known Activations