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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a large quantity or group of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating large quantities or counts of entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     majesty
    -0.71
     Brief
    -0.70
     Dull
    -0.61
     nearest
    -0.61
    icut
    -0.60
     Channel
    -0.60
    inelli
    -0.60
     lil
    -0.59
     Buster
    -0.58
     Puzz
    -0.58
    POSITIVE LOGITS
     (>
    1.05
     of
    0.88
    UID
    0.79
    bang
    0.76
     (~
    0.73
    custom
    0.71
     (<
    0.69
    aux
    0.66
    ourced
    0.65
    metry
    0.65
    Act Density 0.126%

    No Known Activations