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

    Neuronpedia

    INDEX
    Explanations

    references to food and meal suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erken
    -0.18
    rish
    -0.15
    loys
    -0.15
    aoke
    -0.15
     cinnamon
    -0.15
    phant
    -0.15
    odom
    -0.15
    isoft
    -0.15
    ghost
    -0.14
    -cookie
    -0.14
    POSITIVE LOGITS
     dressing
    0.44
     Dress
    0.38
     salad
    0.38
     dress
    0.37
     Salad
    0.35
     salads
    0.34
    sal
    0.33
     dressed
    0.33
    Sal
    0.32
    dress
    0.32
    Act Density 0.043%

    No Known Activations