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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and welcome in feedback and donation requests

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and requests for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.71
    netflix
    -0.70
    strip
    -0.68
     manufacture
    -0.66
     Mub
    -0.65
     Operation
    -0.60
     Pep
    -0.59
     à¨
    -0.59
     parity
    -0.58
     inconsistency
    -0.57
    POSITIVE LOGITS
     welcome
    1.51
     appreciated
    1.50
     welcomed
    1.40
     grate
    1.33
     gladly
    1.13
     encouraged
    1.12
     greatly
    1.06
     appre
    1.02
     kindly
    1.01
     respectful
    1.00
    Act Density 0.158%

    No Known Activations