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

    Neuronpedia

    INDEX
    Explanations

    instances of the pronoun "we"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quia
    -0.16
    mia
    -0.15
     italia
    -0.15
    _IA
    -0.15
    íĥĿ
    -0.15
    оба
    -0.15
    657
    -0.15
    ieten
    -0.15
    lia
    -0.14
    enties
    -0.14
    POSITIVE LOGITS
     learn
    0.27
     meet
    0.25
     flash
    0.24
     fast
    0.23
     learns
    0.23
     learned
    0.20
     Meet
    0.20
    learn
    0.19
     find
    0.19
     Learn
    0.19
    Act Density 0.054%

    No Known Activations