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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or desire, particularly with a focus on gratitude and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    to thank or acknowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arma
    -0.49
     estekak
    -0.43
     turb
    -0.42
     typelib
    -0.41
    gatsby
    -0.41
    numerusform
    -0.41
    󠁢
    -0.41
     HttpNotFound
    -0.41
    miyorum
    -0.40
    Tembelea
    -0.40
    POSITIVE LOGITS
     thank
    0.67
     thanked
    0.63
     reiterate
    0.59
     thanking
    0.56
     congratulate
    0.56
     apologised
    0.54
     emphasise
    0.54
     express
    0.53
     emphasised
    0.50
     apologise
    0.50
    Act Density 0.020%

    No Known Activations