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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Have" prompting an action or question

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with "Have" that indicate questions or prompts for engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.62
    peak
    -0.60
    etting
    -0.59
    uit
    -0.59
    atile
    -0.59
    rift
    -0.56
    stration
    -0.56
    laus
    -0.56
    housing
    -0.55
    —-
    -0.54
    POSITIVE LOGITS
     been
    1.21
    been
    1.05
     Been
    1.01
     gotten
    0.98
    gotten
    0.94
     undergone
    0.90
    kell
    0.87
     begun
    0.81
     gone
    0.80
     grown
    0.78
    Act Density 0.088%

    No Known Activations