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

    Neuronpedia

    INDEX
    Explanations

    questions and themes surrounding understanding, belief, and moral implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icker
    -0.17
    icks
    -0.17
    abb
    -0.17
    antity
    -0.16
    uxe
    -0.14
    145
    -0.14
    erman
    -0.14
    åļ
    -0.14
    çŃ
    -0.14
    riter
    -0.14
    POSITIVE LOGITS
    adele
    0.16
    usz
    0.15
    KNOWN
    0.14
    arb
    0.14
    ãĤıãģĽ
    0.14
    UCT
    0.14
    aths
    0.14
    owitz
    0.14
    esium
    0.13
    emoc
    0.13
    Act Density 0.088%

    No Known Activations