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

    Neuronpedia

    INDEX
    Explanations

    technical terms and phrases related to systems failures, legal agreements, and governance structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nun
    -0.17
    hor
    -0.15
     Hlav
    -0.15
    AllowAnonymous
    -0.14
    tru
    -0.14
    roz
    -0.14
    ses
    -0.14
     Horror
    -0.14
    nar
    -0.14
    adel
    -0.14
    POSITIVE LOGITS
    Ĥ
    0.17
    .CurrentCulture
    0.15
    .jackson
    0.15
    ellas
    0.14
    etty
    0.14
    ckpt
    0.14
    iken
    0.13
    uell
    0.13
    ÏĥÏĥ
    0.13
    êm
    0.13
    Act Density 0.037%

    No Known Activations