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

    Neuronpedia

    INDEX
    Explanations

    references to nostalgia and memorable experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     diag
    -0.14
    окÑĥ
    -0.14
    Native
    -0.14
     dziew
    -0.14
    inci
    -0.14
    quence
    -0.13
    поÑĢ
    -0.13
     merak
    -0.13
    observeOn
    -0.13
    avern
    -0.13
    POSITIVE LOGITS
     memories
    0.61
     Memories
    0.51
     memory
    0.45
     memoria
    0.40
     fond
    0.39
     Memory
    0.39
     remin
    0.39
    -memory
    0.38
     MEMORY
    0.37
    memory
    0.37
    Act Density 0.267%

    No Known Activations