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

    Neuronpedia

    INDEX
    Explanations

    references to events or categories related to death or mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -1.04
     in
    -0.98
     et
    -0.97
     to
    -0.96
     -
    -0.92
     y
    -0.90
     se
    -0.90
     de
    -0.89
     di
    -0.89
     ha
    -0.88
    POSITIVE LOGITS
     itſelf
    2.25
    ſelves
    2.05
     myſelf
    2.01
     Jefus
    1.99
    ſelf
    1.98
     pleaſure
    1.98
     Monfieur
    1.96
     Reſ
    1.93
     raiſ
    1.92
     Anſ
    1.91
    Act Density 0.512%

    No Known Activations