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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "taken."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ausgest
    -0.55
     Ory
    -0.54
     للمعارف
    -0.52
    ResponseBody
    -0.52
     Rhodes
    -0.51
    ORY
    -0.50
     ory
    -0.50
    merz
    -0.48
    ory
    -0.47
     boasts
    -0.47
    POSITIVE LOGITS
     taken
    2.45
    Taken
    2.21
     Taken
    2.18
    taken
    2.13
     TAKEN
    2.09
     tomadas
    1.24
     diambil
    1.19
     tomada
    1.13
     genomen
    1.12
     taker
    1.09
    Act Density 0.095%

    No Known Activations