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

    Neuronpedia

    INDEX
    Explanations

    links that refer to additional content or continuation of the article

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "below" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mut
    -0.63
     restraint
    -0.63
     propri
    -0.60
     pretext
    -0.60
     capacity
    -0.59
     supp
    -0.59
     reincarn
    -0.58
     real
    -0.58
     drive
    -0.57
     priority
    -0.57
    POSITIVE LOGITS
     Below
    3.83
    Below
    2.45
     BELOW
    2.19
    below
    2.06
     Above
    1.99
     below
    1.82
    Above
    1.61
     Here
    1.46
    above
    1.37
     Within
    1.35
    Act Density 0.009%

    No Known Activations