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

    Neuronpedia

    INDEX
    Explanations

    descriptive attributes of food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iella
    -0.59
    hoebe
    -0.54
    paj
    -0.48
    gazette
    -0.48
     filtrate
    -0.48
     Finney
    -0.48
     principios
    -0.48
    saraba
    -0.47
    annuation
    -0.47
    MAA
    -0.47
    POSITIVE LOGITS
     boneless
    0.82
     thighs
    0.78
     breasts
    0.77
    abestanden
    0.74
     breast
    0.73
     thigh
    0.68
     drums
    0.65
     chicken
    0.64
     Breast
    0.62
    makeConstraints
    0.61
    Act Density 0.146%

    No Known Activations