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

    Neuronpedia

    INDEX
    Explanations

    proper nouns ending in 'ag'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ag" and its variations in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     starters
    -0.62
     entitlement
    -0.60
     Perse
    -0.59
     outnumbered
    -0.59
     itch
    -0.57
    Msg
    -0.56
    WHERE
    -0.56
     vandalism
    -0.56
     Agenda
    -0.55
    DonaldTrump
    -0.54
    POSITIVE LOGITS
    lia
    1.25
    arten
    1.22
    rosso
    1.19
    lass
    1.17
    omez
    1.17
    lio
    1.17
    uez
    1.16
    uese
    1.15
    roups
    1.14
    allery
    1.13
    Act Density 0.085%

    No Known Activations