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

    Neuronpedia

    INDEX
    Explanations

    people counting or numbers related to counts in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical counts or tallies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Harbor
    -0.69
    ovie
    -0.62
    ARP
    -0.60
     Directorate
    -0.60
     Eden
    -0.59
    perty
    -0.59
    agall
    -0.59
     inflamm
    -0.59
     Loft
    -0.59
    OPLE
    -0.57
    POSITIVE LOGITS
    enance
    1.73
    downs
    1.27
    ess
    1.04
    esses
    1.03
    down
    0.99
    DOWN
    0.91
    ere
    0.89
    ries
    0.88
    sheets
    0.86
    ener
    0.86
    Act Density 0.031%

    No Known Activations