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

    Neuronpedia

    INDEX
    Explanations

    references to naming and features in the context of identity and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roz
    -0.15
    yg
    -0.15
    assen
    -0.15
    icensed
    -0.14
     UNION
    -0.14
    964
    -0.14
    URAL
    -0.13
    ural
    -0.13
    mess
    -0.13
    engin
    -0.13
    POSITIVE LOGITS
     name
    0.55
    åIJį称
    0.44
     Name
    0.42
    .name
    0.39
    -name
    0.39
    åIJįåŃĹ
    0.39
    	name
    0.38
    åIJį稱
    0.38
     название
    0.38
     NAME
    0.38
    Act Density 0.248%

    No Known Activations