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

    Neuronpedia

    INDEX
    Explanations

    references to survival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sou
    -0.56
     id
    -0.56
     str
    -0.52
     ri
    -0.49
    lek
    -0.49
    kar
    -0.49
    ‌
    -0.49
    za
    -0.48
    -
    -0.48
     main
    -0.48
    POSITIVE LOGITS
     survived
    3.82
     survives
    3.23
     survive
    3.17
    survi
    3.10
     Survi
    2.99
     surviving
    2.84
     survivor
    2.77
     survivors
    2.72
    Surviving
    2.71
     survi
    2.66
    Act Density 0.068%

    No Known Activations