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

    Neuronpedia

    INDEX
    Explanations

    references to various types of fruits and vegetables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alvar
    -0.83
     Endlich
    -0.77
     Gehen
    -0.76
     Holocene
    -0.75
     myſelf
    -0.74
     Efq
    -0.74
     Monfieur
    -0.73
     Saks
    -0.71
     Burrow
    -0.70
     Brahman
    -0.69
    POSITIVE LOGITS
     fruit
    2.13
     fruits
    2.09
     Fruit
    1.98
     Fruits
    1.89
    Fruit
    1.87
    fruit
    1.84
     FRUIT
    1.83
    fruits
    1.77
    Fruits
    1.72
     fru
    1.31
    Act Density 0.031%

    No Known Activations