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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "being."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nødvendig
    -0.86
     Francine
    -0.83
     Patti
    -0.83
     dafs
    -0.81
     Schott
    -0.80
     Conley
    -0.78
    сторія
    -0.77
     faw
    -0.77
     Nagasaki
    -0.77
     Palatine
    -0.76
    POSITIVE LOGITS
     being
    1.45
     BEING
    1.30
    Being
    1.24
     Being
    1.24
    being
    1.21
     be
    0.96
     étant
    0.91
     être
    0.89
     bein
    0.88
     Be
    0.85
    Act Density 0.067%

    No Known Activations