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

    Neuronpedia

    INDEX
    Explanations

    structures quantifying divisions or classifications within data points or parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    
    -0.67
     Divide
    -0.60
     divided
    -0.59
    huk
    -0.58
     divis
    -0.57
     divide
    -0.57
     Divided
    -0.57
    OMB
    -0.55
     divides
    -0.54
     divisions
    -0.54
    POSITIVE LOGITS
     تضيفلها
    0.88
    Personensuche
    0.75
    tanleria
    0.69
    bewerken
    0.63
     betweenstory
    0.62
    🔈
    0.62
     financières
    0.60
     judiciaire
    0.58
     îna
    0.56
     dobrý
    0.56
    Act Density 0.023%

    No Known Activations