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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to death and loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    횟
    -0.57
    ########.
    -0.56
     pairs
    -0.55
     magasiner
    -0.54
    новништво
    -0.53
     pair
    -0.51
    pless
    -0.50
     فريبيس
    -0.49
    InlineData
    -0.49
     automate
    -0.48
    POSITIVE LOGITS
     died
    0.84
     deceased
    0.81
     décédé
    0.75
     falleció
    0.72
     meninggal
    0.69
     Died
    0.67
     Deceased
    0.66
    deceased
    0.64
    KURZBESCHREIBUNG
    0.64
     zmar
    0.63
    Act Density 0.409%

    No Known Activations