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

    Neuronpedia

    INDEX
    Explanations

    references to memory and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ؤلاء
    -0.97
    ⓧ
    -0.92
     betweenstory
    -0.90
     kasarigan
    -0.88
    theless
    -0.88
     pouvoit
    -0.87
    लिए
    -0.86
     høre
    -0.85
     calyx
    -0.85
     canst
    -0.85
    POSITIVE LOGITS
     memory
    1.51
     Memory
    1.40
     memories
    1.26
     Memories
    1.23
    memory
    1.22
    Memory
    1.22
     MEMORY
    1.22
     MEM
    1.20
    Memories
    1.15
     mem
    1.12
    Act Density 0.066%

    No Known Activations