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

    Neuronpedia

    INDEX
    Explanations

    references to popular culture or the term "pop" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atre
    -0.19
    esthetic
    -0.17
    atham
    -0.17
    eenth
    -0.16
    arial
    -0.15
    adays
    -0.15
     Destructor
    -0.15
    icari
    -0.15
    äm
    -0.15
    ead
    -0.14
    POSITIVE LOGITS
    ularity
    0.29
    py
    0.28
    lar
    0.22
    ulations
    0.21
    corn
    0.21
    ulares
    0.20
    üler
    0.20
     Mechanics
    0.20
    ulating
    0.19
    ulaire
    0.19
    Act Density 0.010%

    No Known Activations