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

    Neuronpedia

    INDEX
    Explanations

    grammar-related terms, specifically verb forms like participles and genitives

    oai_token-act-pair · gpt-3.5-turbo

    grammatical structures and components related to verbs and participles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.86
    ONSORED
    -0.85
    ramid
    -0.78
    Monitor
    -0.77
    scl
    -0.76
    adr
    -0.75
    NVIDIA
    -0.75
    Sensor
    -0.73
     Ivory
    -0.73
    Premium
    -0.73
    POSITIVE LOGITS
     verbs
    1.18
     suffix
    1.18
     spelling
    1.18
     verb
    1.14
     phrase
    1.13
     pronouns
    1.13
     pronoun
    1.12
     phrases
    1.10
     noun
    1.08
     diction
    1.04
    Act Density 0.161%

    No Known Activations