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
    arp
    -0.16
     пов
    -0.15
    uti
    -0.14
    avic
    -0.14
    lak
    -0.14
    izzy
    -0.14
    den
    -0.14
    ç¿Ķ
    -0.14
    la
    -0.14
    lus
    -0.14
    POSITIVE LOGITS
    ably
    0.25
    iable
    0.20
    ately
    0.18
    iative
    0.17
    iado
    0.16
    ance
    0.16
     appreciate
    0.16
    -value
    0.15
    iez
    0.15
    INDER
    0.15
    Act Density 0.015%

    No Known Activations