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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positivity or admiration

    oai_token-act-pair · gpt-3.5-turbo

    positive sentiments related to being able to engage with others and participate joyfully

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olicy
    -0.74
    uria
    -0.73
    urred
    -0.71
    ourse
    -0.69
    mage
    -0.69
    icipated
    -0.68
    cum
    -0.67
    è£
    -0.67
    é¾
    -0.65
    heid
    -0.64
    POSITIVE LOGITS
     tid
    0.80
    noon
    0.70
     ya
    0.68
     remind
    0.67
     symmetry
    0.66
     ðŁĻĤ
    0.66
     buddy
    0.66
     knowing
    0.66
     congr
    0.66
     reminder
    0.66
    Act Density 0.188%

    No Known Activations