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

    Neuronpedia

    INDEX
    Explanations

    repetitive patterns and mentions of the term "Re."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geology
    -0.69
    tagHelperRunner
    -0.62
    fören
    -0.61
    Assemblée
    -0.61
     relu
    -0.61
     Latimer
    -0.60
     replay
    -0.60
    îné
    -0.59
    WithIdentifier
    -0.59
     оригіналу
    -0.59
    POSITIVE LOGITS
     Re
    0.96
    re
    0.86
    Re
    0.71
     referred
    0.67
     recipient
    0.58
    addEventListener
    0.57
    де
    0.56
    referred
    0.56
     able
    0.56
    Viited
    0.55
    Act Density 0.079%

    No Known Activations