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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "A lot of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a large quantity or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iphate
    -0.75
    oper
    -0.70
    edin
    -0.69
    berus
    -0.68
    adium
    -0.65
    ooter
    -0.65
    imum
    -0.64
    cum
    -0.64
    omo
    -0.63
    BuyableInstoreAndOnline
    -0.62
    POSITIVE LOGITS
     commenters
    1.07
     commentators
    1.03
     reviewers
    0.88
     observers
    0.87
     analysts
    0.87
     scholars
    0.82
     caveats
    0.82
     biologists
    0.79
     Swed
    0.77
     importantly
    0.77
    Act Density 0.209%

    No Known Activations