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

    Neuronpedia

    INDEX
    Explanations

    references to authors or creators of works, particularly in a literary or artistic context

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

    song titles by authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kysy
    -0.37
     officielles
    -0.36
     publiques
    -0.36
     Económica
    -0.35
     whatever
    -0.34
     blanches
    -0.34
    ellum
    -0.34
     réguli
    -0.33
     privées
    -0.33
     quite
    -0.33
    POSITIVE LOGITS
    rungsseite
    0.95
     betweenstory
    0.93
     disambiguazione
    0.71
     EconPapers
    0.69
    endpush
    0.68
     ujednoznacz
    0.67
     Италијани
    0.60
    endphp
    0.59
    ThroughAttribute
    0.59
     queſta
    0.59
    Act Density 0.071%

    No Known Activations