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

    Neuronpedia

    INDEX
    Explanations

    terms indicating quantities or measurements of comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unhappy
    -0.49
     Happy
    -0.48
     HAPPY
    -0.47
     चुनें
    -0.44
     délic
    -0.44
    wurf
    -0.44
    ceğini
    -0.43
     feliz
    -0.43
     happy
    -0.42
    zi
    -0.42
    POSITIVE LOGITS
     amount
    0.87
     quantity
    0.85
    NUMX
    0.82
    AddHtmlAttribute
    0.78
     amounts
    0.78
     flexibility
    0.78
     quantities
    0.78
    rungsseite
    0.77
     accuracy
    0.75
    astéroïdes
    0.72
    Act Density 0.561%

    No Known Activations