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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating quality or manner of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    096
    -0.15
    ol
    -0.15
     Dre
    -0.15
    607
    -0.15
    406
    -0.15
     mood
    -0.14
    gov
    -0.14
    deen
    -0.14
    adir
    -0.14
    517
    -0.14
    POSITIVE LOGITS
    esch
    0.16
    vrier
    0.15
    lef
    0.14
    ief
    0.14
    ãĥ¼ãĥ«ãĥī
    0.14
     Zus
    0.14
    ÑĨик
    0.14
    ĸī
    0.14
    Apollo
    0.14
    ãĥ¼ãĥª
    0.13
    Act Density 0.233%

    No Known Activations