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

    Neuronpedia

    INDEX
    Explanations

    phrases related to memories and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     informée
    -0.49
     solution
    -0.38
     kier
    -0.37
     UPDATE
    -0.35
     update
    -0.35
    çası
    -0.35
    сылкі
    -0.35
     applic
    -0.35
    意料
    -0.34
     veggies
    -0.34
    POSITIVE LOGITS
     memories
    0.92
     memory
    0.91
    memory
    0.79
    memories
    0.76
     Memories
    0.71
    Memories
    0.71
     MEMORY
    0.70
     herinner
    0.69
     forever
    0.68
    Memory
    0.67
    Act Density 0.221%

    No Known Activations