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

    Neuronpedia

    INDEX
    Explanations

    elements related to language learning and education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -required
    -0.14
    erea
    -0.13
    Added
    -0.13
    ãģ¨ãģĵãĤį
    -0.13
     Serialized
    -0.13
    ëij¥
    -0.13
    ãĤĪãģĨãģ§ãģĻ
    -0.12
    ά
    -0.12
    lem
    -0.12
     Added
    -0.12
    POSITIVE LOGITS
     consisting
    0.43
     containing
    0.35
     composed
    0.35
     with
    0.33
     that
    0.31
     consists
    0.30
     comprised
    0.30
    composed
    0.30
     featuring
    0.29
     made
    0.29
    Act Density 1.554%

    No Known Activations