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

    Neuronpedia

    INDEX
    Explanations

    references to memory loss or impairment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igest
    -0.19
    imat
    -0.16
    ummies
    -0.15
    getMock
    -0.15
    arti
    -0.14
    ssi
    -0.13
     generations
    -0.13
    üf
    -0.13
     Counter
    -0.13
     counter
    -0.13
    POSITIVE LOGITS
     memory
    0.50
     remembers
    0.44
    memory
    0.44
     Memory
    0.43
     memories
    0.43
     remember
    0.42
    Memory
    0.42
    -memory
    0.40
     remembering
    0.40
    remember
    0.39
    Act Density 0.155%

    No Known Activations