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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    place
    -0.80
    dq
    -0.70
    wide
    -0.68
     indo
    -0.68
     Osc
    -0.63
     Construct
    -0.61
    conserv
    -0.60
    abad
    -0.60
    scan
    -0.58
    FO
    -0.58
    POSITIVE LOGITS
    giving
    1.00
    fulness
    0.91
     thank
    0.84
    ESCO
    0.77
     acknowled
    0.76
    imaru
    0.75
    gements
    0.75
     thanking
    0.75
    fully
    0.74
    FUL
    0.71
    Act Density 0.018%

    No Known Activations