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

    Neuronpedia

    INDEX
    Explanations

    elements related to emotional states and expressions

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

    Punctuation followed by adverbs/qualifiers

    np_acts-logits-general · gemini-2.0-flash

    discourse markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fiind
    -0.48
    quele
    -0.42
    mêmes
    -0.42
    ManyToMany
    -0.42
     faveur
    -0.40
    onsored
    -0.40
    hø
    -0.39
    vezető
    -0.39
    ارنة
    -0.39
     Extragalactic
    -0.38
    POSITIVE LOGITS
     btw
    0.94
     BTW
    0.87
     ModelExpression
    0.83
     admittedly
    0.76
     incidentally
    0.72
     kasarigan
    0.71
     according
    0.68
     alas
    0.67
     кстати
    0.67
     ujednoznacz
    0.66
    Act Density 0.163%

    No Known Activations