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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    703
    -0.15
    ç®
    -0.15
     cruc
    -0.15
    683
    -0.15
    183
    -0.14
     Leonard
    -0.14
    307
    -0.14
     ong
    -0.14
     part
    -0.14
    ariant
    -0.14
    POSITIVE LOGITS
    234
    0.18
    456
    0.18
     sdf
    0.17
    hg
    0.17
    567
    0.16
     fds
    0.16
    123
    0.15
    ads
    0.15
    678
    0.15
    345
    0.15
    Act Density 0.063%

    No Known Activations