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

    Neuronpedia

    INDEX
    Explanations

    words related to expressing gratitude and feedback

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to appreciation and soliciting feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illac
    -0.62
     versus
    -0.61
    ories
    -0.61
     barric
    -0.61
    raped
    -0.60
     apartheid
    -0.58
     demol
    -0.57
    otomy
    -0.57
    Guard
    -0.55
    inflamm
    -0.55
    POSITIVE LOGITS
     feedback
    1.12
     donations
    0.98
     YOU
    0.98
    comments
    0.94
     YOUR
    0.92
     contributors
    0.90
     suggestions
    0.90
     Feedback
    0.88
     backers
    0.88
     congr
    0.86
    Act Density 0.212%

    No Known Activations