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

    Neuronpedia

    INDEX
    Explanations

    references to eating and food-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bloem
    -0.51
     arşivlendi
    -0.49
     skall
    -0.48
    CascadeType
    -0.47
     Barrera
    -0.46
     Giugno
    -0.46
    Jegyzetek
    -0.45
    rolid
    -0.45
    BeforeAll
    -0.45
     lavanda
    -0.45
    POSITIVE LOGITS
     eat
    4.06
     eats
    3.49
     Eat
    3.46
     eaten
    3.41
     eating
    3.34
    Eat
    3.31
    eat
    3.25
     ate
    3.24
     Eating
    2.95
     EAT
    2.92
    Act Density 0.071%

    No Known Activations