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

    Neuronpedia

    INDEX
    Explanations

    complex descriptions and discussions about societal systems and human behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     homogeneous
    -0.13
     VIP
    -0.13
     mainstream
    -0.13
    702
    -0.13
    incip
    -0.13
    çªģ
    -0.12
     Validates
    -0.12
     Virgin
    -0.12
    423
    -0.12
     stark
    -0.12
    POSITIVE LOGITS
     complex
    0.75
     Complex
    0.68
    complex
    0.68
    Complex
    0.64
     complicated
    0.64
     complexity
    0.61
    _complex
    0.57
     complexities
    0.55
     Complexity
    0.54
     komplex
    0.53
    Act Density 0.315%

    No Known Activations