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
    oader
    -0.18
    ernel
    -0.17
     spo
    -0.15
    chet
    -0.15
    opher
    -0.15
    ermo
    -0.14
    ald
    -0.14
     Newtown
    -0.14
    unfinished
    -0.14
    aldo
    -0.14
    POSITIVE LOGITS
    .Networking
    0.16
    fak
    0.15
    elli
    0.15
    eworld
    0.14
     bail
    0.14
    izr
    0.13
    adro
    0.13
    äº
    0.13
    iasi
    0.13
    ãģĵãĤĵãģª
    0.13
    Act Density 0.118%

    No Known Activations