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

    Neuronpedia

    INDEX
    Explanations

    greetings and introductions used in online communication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ificantly
    -0.75
    staking
    -0.68
    VERTISEMENT
    -0.67
    igmat
    -0.62
    conom
    -0.61
    uffer
    -0.60
    atton
    -0.60
    untarily
    -0.59
     deteriorated
    -0.58
     documentaries
    -0.57
    POSITIVE LOGITS
     gentlemen
    1.12
     sir
    1.11
     congratulations
    1.05
     congr
    1.01
     welcome
    0.99
     dear
    0.98
     ladies
    0.96
     thank
    0.95
     hello
    0.88
     please
    0.87
    Act Density 1.309%

    No Known Activations