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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and their citation details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =yes
    -0.14
    =YES
    -0.14
    ALAR
    -0.14
    :\/\/
    -0.14
    ral
    -0.14
     neighb
    -0.13
    iders
    -0.13
    heets
    -0.13
     reluct
    -0.13
    cepts
    -0.13
    POSITIVE LOGITS
     earlier
    0.20
     Earlier
    0.19
    Earlier
    0.18
    urum
    0.15
    inch
    0.15
    á¾
    0.15
    adders
    0.14
    emann
    0.14
     Branch
    0.13
    assel
    0.13
    Act Density 0.019%

    No Known Activations