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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude directed towards the reader or audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -0.66
    iculty
    -0.65
    picture
    -0.64
    olson
    -0.64
    dimension
    -0.63
    é¾
    -0.63
    Mount
    -0.63
     Hurricanes
    -0.62
    ingu
    -0.62
    apo
    -0.61
    POSITIVE LOGITS
     sir
    0.99
     guys
    0.98
     kindly
    0.95
     gentlemen
    0.77
    're
    0.76
     gracious
    0.75
    tub
    0.73
     welcome
    0.72
    ा
    0.71
     diligence
    0.70
    Act Density 0.031%

    No Known Activations