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

    Neuronpedia

    INDEX
    Explanations

    numeric age references implying age demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    croft
    -0.15
    nem
    -0.14
    ató
    -0.14
    ensen
    -0.14
    ,
    -0.13
    ERVED
    -0.13
    estone
    -0.13
    advert
    -0.13
    ickey
    -0.13
    alc
    -0.13
    POSITIVE LOGITS
    以ä¸Ĭ
    0.28
    +.
    0.25
    +:
    0.24
     trợ
    0.24
    +)
    0.23
    +,
    0.22
     above
    0.21
    åıĬåħ¶
    0.21
    +)/
    0.21
    +↵
    0.21
    Act Density 0.026%

    No Known Activations