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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" and its various forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNUSED
    -0.17
     privileged
    -0.16
    acier
    -0.15
    atik
    -0.15
    utely
    -0.14
    acob
    -0.14
    onica
    -0.14
    átka
    -0.14
    erton
    -0.14
     непÑĢи
    -0.14
    POSITIVE LOGITS
     caught
    0.26
     deter
    0.23
     sucked
    0.23
     carried
    0.23
     sw
    0.23
     sed
    0.22
     suck
    0.21
     Caught
    0.21
     sid
    0.21
     lul
    0.21
    Act Density 0.088%

    No Known Activations