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

    Neuronpedia

    INDEX
    Explanations

    phrases related to language use and grammatical accuracy

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

    Language and grammar

    np_acts-logits-general · gemini-2.0-flash

    language structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.60
     DBNull
    -0.60
    Примітки
    -0.53
    Hozzáférés
    -0.53
    getCmp
    -0.53
     estekak
    -0.53
    inheritDoc
    -0.52
    GenerationType
    -0.52
    intang
    -0.51
    rxjs
    -0.50
    POSITIVE LOGITS
     sentences
    0.76
     word
    0.72
     words
    0.72
     sentence
    0.70
     grammatical
    0.69
     Grammar
    0.67
     grammar
    0.67
     language
    0.67
     Language
    0.66
    Words
    0.66
    Act Density 0.377%

    No Known Activations