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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to weekly events and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sprites
    -0.15
     equalTo
    -0.15
    ilver
    -0.14
     subsequ
    -0.14
    /***/
    -0.13
    ä¸īå¹´
    -0.13
    ä¸Ģå¹´
    -0.13
    Months
    -0.13
     memcmp
    -0.13
    utes
    -0.13
    POSITIVE LOGITS
     edition
    0.25
    links
    0.20
     links
    0.20
     headlines
    0.20
     roundup
    0.20
     wrap
    0.20
     Weekly
    0.19
     Edition
    0.19
     weekly
    0.19
    Links
    0.19
    Act Density 0.171%

    No Known Activations