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

    Neuronpedia

    INDEX
    Explanations

    phrases related to audience engagement and feedback in comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CurrentValue
    -0.14
     Krish
    -0.14
    emey
    -0.14
    appiness
    -0.13
    celik
    -0.13
    åĤ¬
    -0.13
     Cran
    -0.12
    _encoding
    -0.12
    /sdk
    -0.12
     Morr
    -0.12
    POSITIVE LOGITS
     comment
    0.83
     comments
    0.73
     Comment
    0.72
    comment
    0.69
    Comment
    0.65
     Comments
    0.64
    comments
    0.62
     COMMENT
    0.61
    -comment
    0.61
    _comment
    0.60
    Act Density 0.120%

    No Known Activations