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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a large quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing the quantity and effort associated with tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iley
    -0.80
    getic
    -0.74
    uyomi
    -0.67
    advertising
    -0.65
    ebin
    -0.64
    achable
    -0.64
    iphate
    -0.62
    ifiable
    -0.61
    iasis
    -0.61
    ensis
    -0.61
    POSITIVE LOGITS
    body
    0.74
    etheless
    0.71
     sprang
    0.70
     NCT
    0.69
     Swed
    0.67
     âĶľ
    0.65
    nir
    0.63
     people
    0.62
     arose
    0.62
    ItemThumbnailImage
    0.61
    Act Density 0.209%

    No Known Activations