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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions related to emotional reactions or sounds

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

    expressions of frustration or exasperation

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

    mathematical expressions or notations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.77
     stället
    -0.60
    లాలు
    -0.59
    Kesimpulan
    -0.59
    drawSprites
    -0.58
    μως
    -0.58
    virons
    -0.58
     stanovnika
    -0.58
     coûte
    -0.58
     Réponses
    -0.57
    POSITIVE LOGITS
    insert
    0.82
    Insert
    0.72
     inserts
    0.70
     giggles
    0.67
     sarcasm
    0.67
     glances
    0.66
     grins
    0.65
     laughs
    0.63
     hugs
    0.63
     wipes
    0.63
    Act Density 0.053%

    No Known Activations