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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _]
    -0.59
    ')['
    -0.54
    arii
    -0.51
    CrossRef
    -0.50
    掙
    -0.50
    ]*(
    -0.50
    ')],
    -0.50
    :].
    -0.49
    >-->
    -0.49
    '},
    -0.49
    POSITIVE LOGITS
     delighted
    0.97
     thrilled
    0.94
     overjoyed
    0.88
     pleased
    0.87
     ecstatic
    0.79
     glad
    0.77
     proud
    0.74
     gratified
    0.74
    joyed
    0.72
     elated
    0.72
    Act Density 0.188%

    No Known Activations