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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation in conversational dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avour
    -0.15
    Dear
    -0.15
     Dear
    -0.15
    ONUS
    -0.14
    typings
    -0.13
    Ñıк
    -0.13
    engkap
    -0.13
    pcf
    -0.13
    lament
    -0.13
     #
    -0.13
    POSITIVE LOGITS
     pleasure
    0.27
     appreciate
    0.23
     joining
    0.21
     welcome
    0.21
     thanks
    0.21
     thank
    0.20
     ladies
    0.20
     Ple
    0.20
     gentlemen
    0.19
     Welcome
    0.18
    Act Density 0.068%

    No Known Activations