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

    Neuronpedia

    INDEX
    Explanations

    references to plans and planning activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .gdx
    -0.17
    achi
    -0.16
    angelo
    -0.16
    خاÙĨÙĩ
    -0.16
    achs
    -0.15
    725
    -0.15
    halb
    -0.15
    cul
    -0.15
    gow
    -0.14
    compan
    -0.14
    POSITIVE LOGITS
    enberg
    0.18
    ayout
    0.17
    etary
    0.17
    -ahead
    0.17
    ings
    0.16
    ritch
    0.15
    ishing
    0.15
    isphere
    0.15
    ck
    0.15
    ter
    0.15
    Act Density 0.059%

    No Known Activations