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

    Neuronpedia

    INDEX
    Explanations

    words related to generosity and generation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to generational categories and the concept of "generation."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĺħ
    -0.83
    mare
    -0.80
    yer
    -0.73
    gerald
    -0.68
    eneg
    -0.67
     Sandwich
    -0.67
    EEP
    -0.67
    wal
    -0.66
    olicy
    -0.65
     McKay
    -0.64
    POSITIVE LOGITS
    icity
    1.15
    osity
    1.13
    ational
    1.01
    ously
    1.00
    ically
    0.98
    ators
    0.94
    ics
    0.87
    ical
    0.86
    ator
    0.86
    ative
    0.81
    Act Density 0.043%

    No Known Activations