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

    Neuronpedia

    INDEX
    Explanations

    praises and compliments towards someone's abilities or positive qualities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to praise and confidence in others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ozo
    -0.87
    umes
    -0.78
    inian
    -0.72
    channelAvailability
    -0.71
    umn
    -0.70
    aceae
    -0.70
    restricted
    -0.69
    abilia
    -0.67
     Lobby
    -0.67
    onym
    -0.67
    POSITIVE LOGITS
     performance
    1.42
     accuracy
    1.36
     competence
    1.31
     resilience
    1.25
     reliability
    1.23
     effectiveness
    1.21
     responsiveness
    1.20
    worthiness
    1.20
     adequ
    1.19
     efficiency
    1.17
    Act Density 1.303%

    No Known Activations