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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the introduction or launch of products, services, or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the introduction or launch of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucci
    -0.81
     ancest
    -0.67
    eno
    -0.65
     portrayal
    -0.64
    onge
    -0.63
    rouse
    -0.61
    acci
    -0.60
    é¾įåĸļ士
    -0.60
     condu
    -0.59
    Catalog
    -0.59
    POSITIVE LOGITS
     hostilities
    0.74
    glas
    0.67
    xit
    0.61
     these
    0.61
     Moves
    0.58
     Innocent
    0.57
     fresh
    0.57
    leased
    0.57
    ammad
    0.56
    lished
    0.55
    Act Density 0.157%

    No Known Activations