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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acknowledgments or apologies

    oai_token-act-pair · gpt-3.5-turbo

    instances of gratitude or thanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.84
    ":[{"
    -0.68
    foreseen
    -0.64
    .(
    -0.61
    SPONSORED
    -0.61
     ();
    -0.60
     (?,
    -0.60
    BIL
    -0.59
    ablish
    -0.57
    .[
    -0.56
    POSITIVE LOGITS
    ?)
    1.92
    !)
    1.87
    !),
    1.79
    )."
    1.79
    ?).
    1.79
    ?),
    1.79
    !).
    1.74
    *)
    1.72
    )
    1.72
    )"
    1.70
    Act Density 0.617%

    No Known Activations