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

    Neuronpedia

    INDEX
    Explanations

    mentions of a verb followed by "Has" or "has"

    oai_token-act-pair · gpt-3.5-turbo

    questions beginning with "Has" or variations of "has"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interested
    -0.74
    weights
    -0.63
    ances
    -0.63
    atically
    -0.62
    QB
    -0.61
     behold
    -0.59
     Communists
    -0.55
     clicks
    -0.55
     glove
    -0.54
     transmitting
    -0.54
    POSITIVE LOGITS
     been
    1.30
    kell
    1.20
     undergone
    1.17
    been
    1.13
     Been
    1.11
    hed
    1.06
     emerged
    1.01
     become
    1.01
     arisen
    0.99
     risen
    0.97
    Act Density 0.136%

    No Known Activations