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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to product features and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighborhood
    -0.24
     neighborhoods
    -0.23
     flavor
    -0.23
     flavorful
    -0.23
     rumor
    -0.22
     Neighborhood
    -0.22
     honorable
    -0.21
     behaviors
    -0.21
     colorful
    -0.21
     flavors
    -0.20
    POSITIVE LOGITS
     timber
    0.24
     UK
    0.22
     whilst
    0.21
    GRP
    0.21
     specialist
    0.20
     bespoke
    0.20
     ‘
    0.20
     £
    0.20
     fixing
    0.20
     Pers
    0.19
    Act Density 0.329%

    No Known Activations