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

    Neuronpedia

    INDEX
    Explanations

    references to food items and their preparation methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cigaret
    -0.16
     frying
    -0.16
     cooker
    -0.15
    Insets
    -0.15
     securities
    -0.15
    _usec
    -0.15
    bread
    -0.15
     Vine
    -0.15
     cooking
    -0.14
     ÅŁar
    -0.14
    POSITIVE LOGITS
     ice
    0.45
     scoop
    0.38
     Ice
    0.37
    ice
    0.36
     sco
    0.34
     cone
    0.33
    Ice
    0.33
     cones
    0.32
     ICE
    0.31
     frozen
    0.31
    Act Density 0.035%

    No Known Activations