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

    Neuronpedia

    INDEX
    Explanations

    references to funding and support for educational and research initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ãłu
    -0.16
    SystemService
    -0.15
    ONGL
    -0.14
    ↵↵
    -0.14
    ÑijÑĢ
    -0.14
    ivil
    -0.14
     sometimes
    -0.14
    untu
    -0.14
    langs
    -0.13
    eniz
    -0.13
    POSITIVE LOGITS
    oti
    0.15
     finish
    0.15
    ande
    0.14
    zew
    0.14
     continued
    0.13
     continue
    0.13
    uge
    0.13
    èĶ
    0.13
    urb
    0.13
    ampa
    0.13
    Act Density 0.005%

    No Known Activations