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

    Neuronpedia

    INDEX
    Explanations

    keywords related to numerical data and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ramsey
    -0.14
     spre
    -0.13
    ODY
    -0.13
     rec
    -0.13
    aura
    -0.13
     applied
    -0.13
    248
    -0.13
    orent
    -0.13
    ipop
    -0.13
    ipple
    -0.13
    POSITIVE LOGITS
     prompts
    0.30
    (prompt
    0.28
     prompt
    0.28
    prompt
    0.27
     userInput
    0.26
     prompting
    0.26
     input
    0.26
    .prompt
    0.26
     prompted
    0.25
     Prompt
    0.25
    Act Density 0.114%

    No Known Activations