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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alus
    -0.16
    bab
    -0.15
    Sys
    -0.14
    nP
    -0.14
    onaut
    -0.14
    prite
    -0.13
     culpa
    -0.13
    uckle
    -0.13
    kop
    -0.13
    vet
    -0.13
    POSITIVE LOGITS
    SenderId
    0.16
    axter
    0.15
    isl
    0.14
    /welcome
    0.14
    706
    0.14
     лиÑĪ
    0.13
    lava
    0.13
     кад
    0.13
    atest
    0.13
    ã
    0.13
    Act Density 0.123%

    No Known Activations