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

    Neuronpedia

    INDEX
    Explanations

    the word "people" as the most significant match

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "people" and their perspectives or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.84
    tnc
    -0.81
    NES
    -0.73
    Accessory
    -0.69
    iary
    -0.69
    inventoryQuantity
    -0.66
    \/\/
    -0.62
    COMPLE
    -0.62
    QL
    -0.62
     Sadd
    -0.61
    POSITIVE LOGITS
     smugglers
    0.94
     who
    0.91
    folk
    0.91
    hood
    0.78
     else
    0.75
     confuse
    0.73
    opausal
    0.73
     perceive
    0.72
     misunderstood
    0.72
     appreciated
    0.72
    Act Density 0.118%

    No Known Activations