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

    Neuronpedia

    INDEX
    Explanations

    keywords and terminology related to technology and product features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dw
    -0.16
    Lifecycle
    -0.16
    utow
    -0.16
    (cr
    -0.14
    ç¯ĩ
    -0.14
    µ
    -0.14
     atd
    -0.13
    nez
    -0.13
    _SIGNATURE
    -0.13
     ç¾
    -0.13
    POSITIVE LOGITS
    llen
    0.17
     chest
    0.14
    orest
    0.14
    leys
    0.14
    TPL
    0.14
     kn
    0.14
    بÙĪر
    0.14
    loub
    0.14
    ockets
    0.14
    -Ф
    0.14
    Act Density 0.047%

    No Known Activations