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

    Neuronpedia

    INDEX
    Explanations

    terms related to death and mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ništ
    -0.71
    icksburg
    -0.64
    iddler
    -0.58
    Allo
    -0.57
    +:+
    -0.57
    adpleegd
    -0.56
    hearsal
    -0.56
     Salisbury
    -0.56
     Formulation
    -0.55
     nini
    -0.55
    POSITIVE LOGITS
     död
    0.57
    ly
    0.56
     DEATH
    0.54
     Death
    0.51
     care
    0.50
    waite
    0.50
    حياتها
    0.50
    yness
    0.49
    cares
    0.49
    Birth
    0.49
    Act Density 0.153%

    No Known Activations