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 or thanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulhu
    -0.71
     Dare
    -0.70
    ahime
    -0.67
    pos
    -0.67
    ther
    -0.65
    wide
    -0.63
    scape
    -0.63
    dq
    -0.63
    spir
    -0.62
    lo
    -0.62
    POSITIVE LOGITS
     thanking
    1.00
     thanked
    0.97
     thank
    0.77
     applause
    0.77
    imaru
    0.77
     him
    0.75
     forgiveness
    0.75
     sarcast
    0.73
     congratulated
    0.73
    ESCO
    0.72
    Act Density 0.017%

    No Known Activations