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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating potential or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isman
    -0.14
     æĵ
    -0.14
    immer
    -0.14
    ason
    -0.14
    讯
    -0.14
    ATS
    -0.14
    446
    -0.13
    eniz
    -0.13
    Extern
    -0.13
    .lu
    -0.13
    POSITIVE LOGITS
    ooks
    0.16
     you
    0.16
    /help
    0.15
    ijo
    0.15
    uta
    0.14
     Nested
    0.14
    биÑĤ
    0.14
    ister
    0.14
    mods
    0.14
    berra
    0.13
    Act Density 0.132%

    No Known Activations