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

    Neuronpedia

    INDEX
    Explanations

    words related to surveys and data collection

    oai_token-act-pair · gpt-3.5-turbo

    research-related activities and participant interactions in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.71
     lately
    -0.70
    sorry
    -0.70
    âĿ
    -0.66
    ren
    -0.63
    gotten
    -0.62
    GV
    -0.62
     docs
    -0.61
    even
    -0.61
    uck
    -0.60
    POSITIVE LOGITS
     fictitious
    1.07
     predetermined
    1.06
     simulated
    1.01
     varying
    1.01
     hypothetical
    0.99
     fictional
    0.96
     randomly
    0.90
     stereotypical
    0.87
     various
    0.87
     scenarios
    0.86
    Act Density 0.494%

    No Known Activations