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

    Neuronpedia

    INDEX
    Explanations

    instances of death or dying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.55
     houſe
    -0.53
     ſta
    -0.47
     purpoſe
    -0.47
     uſe
    -0.44
     reaſon
    -0.44
     ſtate
    -0.44
     ſte
    -0.43
     ſon
    -0.42
    devServer
    -0.41
    POSITIVE LOGITS
     resulted
    1.24
     survived
    1.16
     died
    1.16
     occurred
    1.14
     disappeared
    1.13
     emerged
    1.13
     remained
    1.10
     ended
    1.09
     appeared
    1.07
    appeared
    1.07
    Act Density 0.217%

    No Known Activations