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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing efficiency or quality of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elight
    -0.16
    à¹ĭ
    -0.15
     Duch
    -0.15
    PURE
    -0.14
     вов
    -0.14
     ê°Ļ
    -0.14
    ViewInit
    -0.14
     ÑĢаб
    -0.13
    obot
    -0.13
     Budd
    -0.13
    POSITIVE LOGITS
    ologically
    0.18
    yo
    0.16
    uluk
    0.16
    ingly
    0.15
    issa
    0.14
    à¹Ĩ
    0.14
    363
    0.14
    ürk
    0.14
    ropp
    0.14
    igh
    0.14
    Act Density 0.188%

    No Known Activations