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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases that provide context or relationships between different concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uss
    -0.15
    usch
    -0.15
    _nat
    -0.14
    entai
    -0.14
    indo
    -0.14
    lay
    -0.13
    quil
    -0.13
    èĵ
    -0.13
    otal
    -0.13
    assy
    -0.13
    POSITIVE LOGITS
     wre
    0.15
    ä¹ĭä¸Ģ
    0.15
     itself
    0.15
    riors
    0.15
     Pitt
    0.15
     many
    0.14
    .cn
    0.14
    ippet
    0.14
    parator
    0.14
    avin
    0.13
    Act Density 0.202%

    No Known Activations