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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endif
    -0.80
     Worse
    -0.77
     blamed
    -0.73
    Qaida
    -0.66
    adj
    -0.59
    EVA
    -0.59
    uries
    -0.58
    ESA
    -0.58
     tallest
    -0.57
    Enlarge
    -0.57
    POSITIVE LOGITS
    ecast
    0.76
    spection
    0.70
     generosity
    0.69
     yourselves
    0.69
     patience
    0.68
     ðŁĻĤ
    0.67
     fruitful
    0.64
     constructive
    0.64
    Thanks
    0.64
     :)
    0.64
    Act Density 0.317%

    No Known Activations