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

    Neuronpedia

    INDEX
    Explanations

    the word "only" and its modifiers indicating limitation or exclusivity

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

    followed by degree adverbs

    np_acts-logits-general · gemini-2.0-flash

    limited degree or recency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.77
     Wiktionnaire
    -0.67
    definitely
    -0.66
    :✨
    -0.62
    errHandler
    -0.58
     للمعارف
    -0.58
    WritableDatabase
    -0.58
    WriteTagHelper
    -0.58
    </thead>
    -0.56
    出版年
    -0.56
    POSITIVE LOGITS
     marginally
    0.85
     mildly
    0.77
     partial
    0.77
     partially
    0.76
     Partial
    0.69
     slightly
    0.69
    Partial
    0.66
     faintly
    0.64
    partial
    0.62
     hint
    0.62
    Act Density 0.204%

    No Known Activations