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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "add" followed by a prepositional phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the act of adding items to lists or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irection
    -0.84
    aji
    -0.67
    actionDate
    -0.66
    avior
    -0.64
    Ê
    -0.62
    asma
    -0.62
    adem
    -0.62
    azard
    -0.60
    Developer
    -0.60
    okemon
    -0.59
    POSITIVE LOGITS
     repertoire
    1.13
     list
    1.04
     mix
    1.00
     existing
    0.96
     pile
    0.94
     arsenal
    0.90
     reperto
    0.90
     fray
    0.87
     coffers
    0.86
     equation
    0.83
    Act Density 0.109%

    No Known Activations