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

    Neuronpedia

    INDEX
    Explanations

    descriptions of food textures and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Debt
    -0.15
    jure
    -0.15
    uze
    -0.14
    ean
    -0.14
    ugin
    -0.14
     informal
    -0.13
    ispens
    -0.13
    zano
    -0.13
     lä
    -0.13
    .ws
    -0.13
    POSITIVE LOGITS
     wat
    0.26
     taste
    0.25
     gross
    0.23
     rubber
    0.23
    gross
    0.22
     tastes
    0.22
     Wat
    0.21
     tasted
    0.21
     bland
    0.21
     cardboard
    0.20
    Act Density 0.097%

    No Known Activations