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

    Neuronpedia

    INDEX
    Explanations

    references to controversial events and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceptive
    -0.18
    estre
    -0.14
    .getApp
    -0.14
    ä¸Ī
    -0.14
    λια
    -0.13
    emplates
    -0.13
    fty
    -0.13
    лиÑı
    -0.13
    curring
    -0.13
    个
    -0.13
    POSITIVE LOGITS
     timeline
    0.19
     evidence
    0.17
    timeline
    0.17
    imeline
    0.16
    DCF
    0.16
     timelines
    0.15
    Claims
    0.15
    sources
    0.15
     allegations
    0.15
    iani
    0.15
    Act Density 0.380%

    No Known Activations