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

    Neuronpedia

    INDEX
    Explanations

    conversational expressions and interjections that indicate a response or transition in dialogue

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

    conversational interjections and fillers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kuj
    -0.53
     otomatig
    -0.52
    twimg
    -0.50
    agrid
    -0.50
    ésultat
    -0.48
     fallu
    -0.47
    EndContext
    -0.47
    ndose
    -0.46
    ✭✭
    -0.45
     snippetHide
    -0.45
    POSITIVE LOGITS
     createState
    0.43
    Chham
    0.37
    setObjectName
    0.36
     punishable
    0.35
     baskılı
    0.34
    InlineData
    0.34
    antası
    0.33
     propOrder
    0.33
     zelve
    0.33
     dezelve
    0.33
    Act Density 0.073%

    No Known Activations