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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve complexity and clarity in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieber
    -0.17
    adian
    -0.15
    aml
    -0.15
    orton
    -0.14
    ef
    -0.14
    uard
    -0.13
    Anywhere
    -0.13
    ÏĦί
    -0.13
     Casting
    -0.13
    efe
    -0.13
    POSITIVE LOGITS
     technical
    0.42
    technical
    0.37
     complex
    0.35
     complicated
    0.35
     Technical
    0.33
     complexity
    0.31
    complex
    0.30
    Technical
    0.30
     Complex
    0.28
     complexities
    0.28
    Act Density 0.414%

    No Known Activations