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

    Neuronpedia

    INDEX
    Explanations

    words related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    present participles or gerunds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.62
     manageable
    -0.61
     streaming
    -0.60
     nour
    -0.59
     buzzing
    -0.59
    pering
    -0.58
     spitting
    -0.57
     SERV
    -0.57
     waiting
    -0.57
     subordinate
    -0.56
    POSITIVE LOGITS
    tons
    1.57
    ham
    1.33
    ton
    1.25
    HAM
    1.14
    haus
    1.13
    redients
    1.13
    hetti
    1.04
    hoff
    1.00
    bird
    0.95
    uez
    0.95
    Act Density 0.116%

    No Known Activations