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

    Neuronpedia

    INDEX
    Explanations

    phrases related to recognition or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating recognition or acknowledgment of past contributions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (?,
    -0.55
    ourning
    -0.52
     nutshell
    -0.52
    iaries
    -0.51
    resa
    -0.51
    venants
    -0.51
    onomy
    -0.51
    xiety
    -0.50
     intrigue
    -0.49
    Published
    -0.49
    POSITIVE LOGITS
    !).
    0.86
    ?).
    0.79
     incidentally
    0.73
    ).[
    0.73
    %).
    0.70
    76561
    0.70
    }}}
    0.63
     ).
    0.61
    ).
    0.60
    )."
    0.60
    Act Density 1.188%

    No Known Activations