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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and politeness

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

    Responses to words indicating gratitude or acknowledgement

    np_acts-logits-general · gemini-2.0-flash

    no problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SceneManagement
    -0.49
    ⓘ
    -0.46
    langkah
    -0.45
     Injectable
    -0.44
    ftagPool
    -0.44
    ieke
    -0.44
    /*",
    -0.44
     createSlice
    -0.43
    -0.42
    ふと
    -0.42
    POSITIVE LOGITS
     Paglinawan
    1.00
    Glad
    0.81
     glad
    0.79
     Glad
    0.77
    glad
    0.77
    addGap
    0.75
     CreateTagHelper
    0.72
     pleaſure
    0.71
    UnusedPrivate
    0.69
    thank
    0.64
    Act Density 0.110%

    No Known Activations