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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and affirmations in dialogue

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

    Japanese sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ANEOUS
    -0.39
    RenderAtEndOf
    -0.39
    GTCX
    -0.39
    ToFit
    -0.39
    どうやって
    -0.38
    songwriter
    -0.37
    sätzlich
    -0.36
    inghouse
    -0.35
     Avent
    -0.34
    ）』
    -0.34
    POSITIVE LOGITS
    ണ്
    0.67
     है
    0.65
     છે
    0.59
     ہے
    0.57
     था
    0.55
    ıdır
    0.55
     AssemblyCulture
    0.53
    HasAnnotation
    0.53
    ია
    0.53
     EconPapers
    0.53
    Act Density 0.029%

    No Known Activations