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

    Neuronpedia

    INDEX
    Explanations

    references to stacked or layered materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    x
    -0.29
    }}
    -0.29
     och
    -0.28
    Istorija
    -0.28
     fl
    -0.27
     sp
    -0.27
    C
    -0.27
     Blues
    -0.27
    Джерела
    -0.26
     Mick
    -0.26
    POSITIVE LOGITS
     pile
    0.80
     pharmaceutical
    0.78
     pharmacy
    0.77
     Pharma
    0.77
     pharma
    0.77
     Pharmaceutical
    0.76
     piles
    0.74
     pharmacies
    0.74
    Pharma
    0.74
     heap
    0.72
    Act Density 0.190%

    No Known Activations