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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the importance or value of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of a particular subject or issue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eur
    -0.80
    umin
    -0.76
    Catalog
    -0.76
    dit
    -0.73
    thia
    -0.72
    mur
    -0.71
    KO
    -0.71
    igun
    -0.70
    washer
    -0.70
    ciation
    -0.70
    POSITIVE LOGITS
     incorporating
    1.13
     relying
    1.09
     combining
    1.09
     having
    1.09
     preserving
    1.06
     adopting
    1.06
     maintaining
    1.04
     hindsight
    1.04
     employing
    1.03
     owning
    1.02
    Act Density 0.146%

    No Known Activations