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

    Neuronpedia

    INDEX
    Explanations

    concepts related to life, death, and existential discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.59
     abus
    -0.56
    Hozzáférés
    -0.53
    setof
    -0.53
    onite
    -0.52
    клопе
    -0.51
    cabul
    -0.48
     schu
    -0.47
    lalom
    -0.47
     schlug
    -0.47
    POSITIVE LOGITS
     death
    2.42
     Death
    2.17
    death
    2.12
    Death
    2.07
     dying
    2.01
     DEATH
    1.96
     Dying
    1.89
     deaths
    1.86
    DEATH
    1.78
    Dying
    1.73
    Act Density 0.729%

    No Known Activations