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

    Neuronpedia

    INDEX
    Explanations

    references to freshness in food items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fresh
    -0.23
    Fresh
    -0.21
     Fresh
    -0.21
     fresh
    -0.20
     fres
    -0.20
     freshman
    -0.19
     freshwater
    -0.19
     freshness
    -0.18
    plevel
    -0.17
     freshly
    -0.17
    POSITIVE LOGITS
    ening
    0.38
    ened
    0.36
    -faced
    0.31
    eners
    0.31
    ener
    0.30
    en
    0.27
    -cut
    0.26
    ens
    0.25
    -air
    0.24
    water
    0.23
    Act Density 0.026%

    No Known Activations