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

    Neuronpedia

    INDEX
    Explanations

    instances where something is collecting or bringing together multiple elements or data points

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aggregation and data collection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stroke
    -0.71
    bird
    -0.70
    foot
    -0.68
    vous
    -0.66
    warm
    -0.65
    ne
    -0.64
    pher
    -0.64
     Helic
    -0.62
    ney
    -0.62
     Mouth
    -0.61
    POSITIVE LOGITS
     aggreg
    1.08
     aggregation
    1.04
     aggregate
    0.97
    regate
    0.96
    aucuses
    0.77
    ãĥ¼ãĥĨãĤ£
    0.76
    ulates
    0.74
    ample
    0.72
    amation
    0.70
    iband
    0.70
    Act Density 0.009%

    No Known Activations