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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lau
    -0.64
    ignty
    -0.58
     Pratt
    -0.56
    tsky
    -0.56
     Feld
    -0.56
     Wonderland
    -0.55
     Paddock
    -0.55
     Mig
    -0.54
     Seah
    -0.54
    pend
    -0.53
    POSITIVE LOGITS
    ा
    0.78
    mbuds
    0.70
     kindly
    0.67
     sir
    0.67
    à¥
    0.66
    à¤
    0.65
    assy
    0.64
    RS
    0.64
    quished
    0.64
    interstitial
    0.63
    Act Density 0.023%

    No Known Activations