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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating cumulative or combined values related to economic or quantitative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ().'/
    -0.15
     acomp
    -0.14
     Svens
    -0.14
    ihan
    -0.14
    arded
    -0.14
    ει
    -0.14
    roud
    -0.14
    ocab
    -0.14
    ess
    -0.14
    etry
    -0.14
    POSITIVE LOGITS
    pz
    0.15
    altar
    0.15
    ToLocal
    0.15
     Berm
    0.14
    pars
    0.14
     Axe
    0.13
    èŃľ
    0.13
    chs
    0.13
    otta
    0.13
    åĽº
    0.13
    Act Density 0.008%

    No Known Activations