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

    Neuronpedia

    INDEX
    Explanations

    phrases related to usage and references to specific individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gangbang
    -0.17
    ScrollIndicator
    -0.16
    azzi
    -0.16
    arella
    -0.15
    .helpers
    -0.15
    zk
    -0.14
    igmat
    -0.14
    ÙĪÛĮÙĩ
    -0.14
    ignet
    -0.14
    ensus
    -0.14
    POSITIVE LOGITS
     Guest
    0.16
    205
    0.15
     guest
    0.14
    èĤī
    0.14
     discrepan
    0.14
     Aggregate
    0.14
     Genuine
    0.14
    eket
    0.14
    ĩ
    0.14
    684
    0.14
    Act Density 0.001%

    No Known Activations