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

    Neuronpedia

    INDEX
    Explanations

    words related to stacking or piling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stacking and layering objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hood
    -0.85
    0100
    -0.78
    context
    -0.76
    lde
    -0.74
    kiss
    -0.71
    cot
    -0.71
    nesota
    -0.70
    cause
    -0.69
    lich
    -0.68
    words
    -0.68
    POSITIVE LOGITS
     stacked
    1.19
     millenn
    1.01
     stacks
    0.95
     adolesc
    0.94
     unbeliev
    0.91
     stacking
    0.91
     shelves
    0.89
     piles
    0.85
     racks
    0.82
     boxes
    0.81
    Act Density 0.009%

    No Known Activations