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

    expressions of gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.66
     Modes
    -0.61
     expectancy
    -0.61
     {:
    -0.59
     batter
    -0.58
    lihood
    -0.57
    nings
    -0.55
     Conc
    -0.55
     Prosecut
    -0.55
    Constructed
    -0.54
    POSITIVE LOGITS
    ooo
    1.16
    bered
    1.15
    oooo
    1.14
    othe
    1.08
    oner
    1.07
    othes
    1.00
    oths
    1.00
    apy
    0.99
    arin
    0.97
    aps
    0.96
    Act Density 0.105%

    No Known Activations