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

    Neuronpedia

    INDEX
    Explanations

    adverbs that intensify or qualify statements

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

    intensifiers followed by scale adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.56
     Wikimedijinoj
    -0.55
    󠁣
    -0.54
    الإنجليزية
    -0.52
    ]){
    -0.50
    exists
    -0.50
    GEBURTSDATUM
    -0.49
    homonymie
    -0.49
    SpringBoot
    -0.49
    PMailer
    -0.48
    POSITIVE LOGITS
     high
    0.52
     extensive
    0.47
     large
    0.44
     enormous
    0.43
     massive
    0.42
    RequestParam
    0.41
     designs
    0.39
    Betyg
    0.39
     typelib
    0.38
     descriptions
    0.38
    Act Density 0.052%

    No Known Activations