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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ango
    -0.16
    erot
    -0.15
    atori
    -0.15
    ILE
    -0.14
    ilet
    -0.14
    Shared
    -0.14
    ean
    -0.14
    arend
    -0.14
    ãģĩ
    -0.14
     Pearson
    -0.13
    POSITIVE LOGITS
    otal
    0.18
    lamaz
    0.16
    ContentSize
    0.15
    ool
    0.14
     Interr
    0.14
    kaz
    0.14
    semb
    0.14
    mpl
    0.14
    .Dispatch
    0.14
    tha
    0.14
    Act Density 0.011%

    No Known Activations