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

    Neuronpedia

    INDEX
    Explanations

    themes related to exploration and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ·¡
    -0.15
     Levi
    -0.15
    ãĥ¼ãĤ¿
    -0.14
    oga
    -0.14
    strength
    -0.14
    anny
    -0.14
    Initialized
    -0.14
     em
    -0.14
    GRID
    -0.14
     Sne
    -0.14
    POSITIVE LOGITS
     wild
    0.23
     exploration
    0.21
     adventure
    0.20
     exciting
    0.20
     excitement
    0.19
     imagination
    0.18
     Exploration
    0.18
     fun
    0.18
     adventures
    0.18
    wild
    0.17
    Act Density 0.011%

    No Known Activations