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

    Neuronpedia

    INDEX
    Explanations

    code-related terms associated with final variables and types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velle
    -0.15
    gens
    -0.15
    theid
    -0.15
    озна
    -0.15
    ï½ľ
    -0.15
    å¢ĥ
    -0.14
    ament
    -0.14
     Barnett
    -0.14
    eters
    -0.14
    æł
    -0.14
    POSITIVE LOGITS
    ABL
    0.16
    à¸ŀร
    0.15
    opa
    0.15
    abl
    0.14
    ddy
    0.14
    ali
    0.14
    oka
    0.14
    oldown
    0.14
     intrusion
    0.13
    اÙģÛĮ
    0.13
    Act Density 0.012%

    No Known Activations