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

    Neuronpedia

    INDEX
    Explanations

    references to personal memories and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conto
    -0.15
    олÑĸ
    -0.14
    strstr
    -0.14
     forgiven
    -0.14
    abi
    -0.14
     rond
    -0.14
    еÑģп
    -0.14
    ckpt
    -0.13
    eniable
    -0.13
    Ñģи
    -0.13
    POSITIVE LOGITS
     farewell
    0.33
     goodbye
    0.29
     Fare
    0.28
     leaving
    0.25
     depart
    0.22
     departing
    0.22
     departure
    0.21
     final
    0.21
     Depart
    0.21
     legacy
    0.20
    Act Density 0.181%

    No Known Activations