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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating quality or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favors
    -0.23
     Favorite
    -0.22
     neighborhood
    -0.22
     Organizer
    -0.21
    Favorite
    -0.21
     neighborhoods
    -0.21
     neighbors
    -0.21
     favorite
    -0.21
     favorable
    -0.21
     unfavor
    -0.20
    POSITIVE LOGITS
     cracking
    0.25
     adverts
    0.23
     £
    0.23
     programme
    0.23
     postcode
    0.22
     flavours
    0.22
     whilst
    0.22
     organisations
    0.22
     personalised
    0.22
     recognised
    0.22
    Act Density 0.292%

    No Known Activations