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

    Neuronpedia

    INDEX
    Explanations

    the use of the word "more."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REA
    -0.16
     Äijáng
    -0.15
    enet
    -0.15
    ÃŃch
    -0.15
    zm
    -0.14
    enta
    -0.14
    roz
    -0.14
    GMEM
    -0.14
    _sdk
    -0.14
    ạnh
    -0.14
    POSITIVE LOGITS
     recent
    0.28
     es
    0.25
     involved
    0.23
     recently
    0.23
     general
    0.21
     traditional
    0.20
     advanced
    0.20
    recent
    0.20
    Recent
    0.19
    general
    0.19
    Act Density 0.096%

    No Known Activations