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

    Neuronpedia

    INDEX
    Explanations

    names of characters and entities from a narrative context

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

    dialogue sounds and tones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.65
     enjoyment
    -0.64
     fun
    -0.60
     ENJOY
    -0.59
     весе
    -0.57
     JOY
    -0.54
    enjoy
    -0.53
     happiness
    -0.52
     enjoyed
    -0.52
     Enjoy
    -0.52
    POSITIVE LOGITS
    лтемелер
    0.48
     leyendas
    0.43
     reputación
    0.41
     OMITBAD
    0.41
     colère
    0.40
    tizado
    0.40
     disgusted
    0.40
     doInBackground
    0.40
     almofada
    0.39
     Fiscalía
    0.39
    Act Density 0.109%

    No Known Activations