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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to death and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.61
     transfieras
    -0.60
     Infórmanos
    -0.60
     unknownFields
    -0.59
     kaarangay
    -0.54
     للمعارف
    -0.52
    astéro
    -0.52
     Italijanski
    -0.52
     חיצוניים
    -0.51
     autorytatywna
    -0.50
    POSITIVE LOGITS
    isDead
    0.49
     death
    0.48
     Death
    0.44
    Death
    0.44
     mort
    0.43
     premat
    0.43
     💀
    0.41
     auctor
    0.41
    didSet
    0.41
    death
    0.40
    Act Density 0.491%

    No Known Activations