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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or recognition

    oai_token-act-pair · gpt-3.5-turbo

    expressions of appreciation and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    infect
    -0.90
    metal
    -0.81
    prep
    -0.81
    buster
    -0.79
    rooms
    -0.73
    Ult
    -0.73
    idem
    -0.72
    smoking
    -0.72
    ridden
    -0.72
    soDeliveryDate
    -0.71
    POSITIVE LOGITS
     appreciation
    0.91
    ĸļ
    0.89
     compliments
    0.75
     gifts
    0.71
    ¿½
    0.71
     how
    0.70
     appreciate
    0.70
     contributions
    0.70
    ably
    0.69
    enance
    0.68
    Act Density 0.034%

    No Known Activations