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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "only" and its surrounding context indicating restrictions or singularities

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

    Comes after the word "only"

    np_acts-logits-general · gemini-2.0-flash

    only + adjective/adverb/verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.63
    \{\\
    -0.61
    UnusedPrivate
    -0.58
     nevertheless
    -0.54
    λέον
    -0.52
    still
    -0.49
     trotzdem
    -0.48
     dennoch
    -0.48
    anything
    -0.47
     już
    -0.46
    POSITIVE LOGITS
     nahilalakip
    0.87
     للاسماء
    0.80
    NameInMap
    0.73
    SourceChecksum
    0.73
     marginally
    0.72
    DockStyle
    0.71
    Lähteet
    0.70
     partial
    0.69
     one
    0.69
    CppMethod
    0.69
    Act Density 0.223%

    No Known Activations