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

    Neuronpedia

    INDEX
    Explanations

    phrases related to eating habits and emotional triggers for food cravings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oya
    -0.15
    hurst
    -0.15
    agma
    -0.15
    Luck
    -0.14
     spine
    -0.14
     Suspension
    -0.14
    soup
    -0.13
    imus
    -0.13
     Conserv
    -0.13
    ota
    -0.13
    POSITIVE LOGITS
     calor
    0.26
     carb
    0.24
     grazing
    0.22
     calories
    0.22
     portion
    0.21
     cravings
    0.21
     hunger
    0.21
     temptation
    0.20
    portion
    0.20
     tempt
    0.20
    Act Density 0.112%

    No Known Activations