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

    Neuronpedia

    INDEX
    Explanations

    themes related to societal structure and oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢана
    -0.16
    ide
    -0.15
     thereby
    -0.15
    æĺ¯ä»Ģä¹Ī
    -0.14
    -valu
    -0.14
    orm
    -0.14
     hvad
    -0.14
     strerror
    -0.14
    etri
    -0.14
    究
    -0.13
    POSITIVE LOGITS
     where
    0.60
    where
    0.46
     où
    0.42
     donde
    0.41
     ÏĮÏĢοÏħ
    0.40
     где
    0.39
    	where
    0.39
    _where
    0.38
     Where
    0.37
     wherein
    0.37
    Act Density 0.592%

    No Known Activations