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

    Neuronpedia

    INDEX
    Explanations

    requests for feedback or opinions in comment sections

    oai_token-act-pair · gpt-3.5-turbo

    references to audience engagement and feedback, particularly in comment sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.64
    iour
    -0.63
    ngth
    -0.62
    ographers
    -0.62
    Abstract
    -0.61
    Aid
    -0.61
    sterdam
    -0.60
    Struct
    -0.59
     reluct
    -0.59
    CD
    -0.59
    POSITIVE LOGITS
     comments
    1.33
     Comments
    1.23
     comment
    1.18
     Comment
    1.10
     Forums
    1.04
     forums
    0.99
    comments
    0.99
     commenting
    0.98
    Comment
    0.93
     hashtag
    0.91
    Act Density 0.074%

    No Known Activations