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

    Neuronpedia

    INDEX
    Explanations

    references to scattered materials or physical fragments, particularly in contexts like accidents or damage

    oai_token-act-pair · gpt-3.5-turbo

    references to destructed materials and debris

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pis
    -0.80
    zee
    -0.74
    vern
    -0.70
     Freem
    -0.68
    osexual
    -0.68
    pher
    -0.66
    ebus
    -0.66
    kers
    -0.65
    ishops
    -0.64
    Polit
    -0.64
    POSITIVE LOGITS
     debris
    1.15
    shed
    1.06
     piles
    0.92
     fragments
    0.92
    collection
    0.84
     particles
    0.81
     remnants
    0.80
     wreckage
    0.80
     heap
    0.78
     litter
    0.77
    Act Density 0.018%

    No Known Activations