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

    Neuronpedia

    INDEX
    Explanations

    references to uniqueness and variability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osy
    -0.17
    wit
    -0.16
    awl
    -0.15
    emey
    -0.15
    odel
    -0.15
     âĸ³
    -0.14
    readcr
    -0.14
    uzzer
    -0.14
     ÏĢεÏģι
    -0.14
    vrd
    -0.14
    POSITIVE LOGITS
    istry
    0.17
    stry
    0.17
    ReuseIdentifier
    0.16
    auc
    0.15
    cape
    0.14
    enario
    0.14
    orate
    0.14
    TPL
    0.14
    acci
    0.14
     Grant
    0.13
    Act Density 0.104%

    No Known Activations