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

    Neuronpedia

    INDEX
    Explanations

    references to code or programming-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rung
    -0.17
    urge
    -0.17
    Fallback
    -0.15
     Mr
    -0.14
    nid
    -0.14
    abel
    -0.14
     baj
    -0.14
     nid
    -0.13
    reur
    -0.13
    NIC
    -0.13
    POSITIVE LOGITS
    erli
    0.16
    administrator
    0.15
    ãģĵãĤĵãģ«
    0.14
    .gdx
    0.14
    onn
    0.13
    _fitness
    0.13
     Toolbar
    0.13
    (disposing
    0.13
    fst
    0.13
    maal
    0.13
    Act Density 0.001%

    No Known Activations