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

    Neuronpedia

    INDEX
    Explanations

    words associated with emotional connections and significant life events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     benef
    -0.14
     patri
    -0.14
    ::$
    -0.14
    иг
    -0.14
    ween
    -0.13
    ково
    -0.13
    ibo
    -0.13
     tempting
    -0.13
    pora
    -0.13
    ysi
    -0.13
    POSITIVE LOGITS
     memories
    0.56
     memory
    0.47
    memory
    0.42
     Memories
    0.41
     Memory
    0.38
     MEMORY
    0.37
    -memory
    0.36
     moments
    0.35
     memoria
    0.35
    mem
    0.35
    Act Density 0.174%

    No Known Activations