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

    Neuronpedia

    INDEX
    Explanations

    phrases ending with a form of the word "of"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or projects, particularly in relation to their characteristics or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Niet
    -0.80
     Petraeus
    -0.65
     Kissinger
    -0.61
     Saban
    -0.59
     Luthor
    -0.58
     Kahn
    -0.57
     Angus
    -0.55
     Bernstein
    -0.55
     sag
    -0.54
     Highlander
    -0.53
    POSITIVE LOGITS
    taboola
    0.66
    ategory
    0.65
    zona
    0.64
    ^{
    0.64
    ysical
    0.63
    arge
    0.63
    avis
    0.62
    arthed
    0.60
    ï¸ı
    0.60
    soDeliveryDate
    0.60
    Act Density 0.782%

    No Known Activations