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

    Neuronpedia

    INDEX
    Explanations

    terms related to color, particularly grey and data handling concepts in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disks
    -0.92
     Theaters
    -0.91
     Rine
    -0.87
     MasterCard
    -0.87
     Shreve
    -0.86
    pnea
    -0.85
     theaters
    -0.83
     Stearns
    -0.83
     boissons
    -0.83
     Stacy
    -0.83
    POSITIVE LOGITS
     enquiries
    1.27
     learnt
    1.20
     artefacts
    1.18
     Enquiries
    1.16
     judgements
    1.15
     licences
    1.10
     enquiry
    1.10
     sceptical
    1.08
     yoghurt
    1.08
     moulds
    1.08
    Act Density 0.325%

    No Known Activations