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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.14
     ſtate
    -1.02
     purpoſe
    -0.97
     themſelves
    -0.96
     ſever
    -0.95
     raiſ
    -0.94
     Chriftian
    -0.92
     ſeveral
    -0.91
     ſta
    -0.91
     pleaſure
    -0.90
    POSITIVE LOGITS
     is
    1.26
     là
    1.07
     a
    1.02
     è
    1.00
     be
    0.97
     é
    0.95
     adalah
    0.94
     es
    0.91
     being
    0.89
     merupakan
    0.88
    Act Density 0.016%

    No Known Activations