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

    Neuronpedia

    INDEX
    Explanations

    technical vocabulary related to organizational research and classification systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HWND
    -0.13
    idel
    -0.13
    æģ¯
    -0.13
    @nate
    -0.12
    ypass
    -0.12
    asu
    -0.12
    à¹Ģà¸īล
    -0.12
    ynchronously
    -0.12
    .OP
    -0.12
    estroy
    -0.12
    POSITIVE LOGITS
     division
    0.32
     class
    0.29
    åĪĨ
    0.29
     classes
    0.29
     grouping
    0.29
     subdiv
    0.28
    åĪĨç±»
    0.28
     subdivision
    0.28
     categories
    0.28
     subclass
    0.28
    Act Density 0.204%

    No Known Activations