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

    Neuronpedia

    INDEX
    Explanations

    mentions or descriptions of graves

    oai_token-act-pair · gpt-3.5-turbo

    references to graves and associated concepts of death or burial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivity
    -0.71
    é¾
    -0.70
     Ack
    -0.69
    ILA
    -0.68
    BuyableInstoreAndOnline
    -0.66
    encer
    -0.66
    uana
    -0.62
     pir
    -0.62
     warr
    -0.61
    erker
    -0.60
    POSITIVE LOGITS
    lly
    1.23
    grave
    1.01
    stones
    0.99
     robbing
    0.86
    stone
    0.86
     grave
    0.84
    locked
    0.79
    cover
    0.78
    lain
    0.77
    faced
    0.76
    Act Density 0.029%

    No Known Activations