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

    Neuronpedia

    INDEX
    Explanations

    terms related to chatbot and information retrieval systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.17
    rett
    -0.15
    å§Ķ
    -0.15
    rips
    -0.15
    çħ
    -0.14
    éĶĢ
    -0.14
     combust
    -0.14
     Relief
    -0.14
    thal
    -0.14
    è¦ĸ
    -0.13
    POSITIVE LOGITS
    BERT
    0.23
    bert
    0.23
     prompt
    0.21
    (prompt
    0.21
    prompt
    0.20
     Prompt
    0.20
     bert
    0.20
     prompts
    0.20
    _prompt
    0.19
     MLM
    0.19
    Act Density 0.020%

    No Known Activations