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

    Neuronpedia

    INDEX
    Explanations

    specific patterns of common verbs and their grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     themſelves
    -0.40
     auroit
    -0.40
    ByUsername
    -0.40
    uxxxx
    -0.39
     itſelf
    -0.38
     Chwiliwch
    -0.37
    SharedCtor
    -0.35
     mAdapter
    -0.35
     houſe
    -0.35
    AndUpdate
    -0.35
    POSITIVE LOGITS
     belonged
    1.00
     existed
    0.97
     appeared
    0.93
     consisted
    0.92
     resulted
    0.90
     happened
    0.89
     occurred
    0.88
     amounted
    0.87
     originated
    0.87
     belong
    0.86
    Act Density 0.913%

    No Known Activations