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

    Neuronpedia

    INDEX
    Explanations

    references to question and answer structures in chatbot systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alphabet
    -0.17
    435
    -0.15
    mür
    -0.15
     LETTER
    -0.15
     alphabet
    -0.14
    eten
    -0.14
    аÑĩ
    -0.13
     رس
    -0.13
    rending
    -0.13
    765
    -0.13
    POSITIVE LOGITS
     utter
    0.22
     paraph
    0.21
     Ground
    0.21
     span
    0.20
     ground
    0.20
     gold
    0.20
    utter
    0.19
     spans
    0.19
    utt
    0.19
     grounding
    0.19
    Act Density 0.011%

    No Known Activations