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

    Neuronpedia

    INDEX
    Explanations

    phrases or contexts indicating collaboration or interaction between different entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \CMS
    -0.13
     [âĢ¦]↵
    -0.13
     [âĢ¦]
    -0.12
     [âĢ¦
    -0.12
    phies
    -0.11
    ationToken
    -0.11
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.11
    âĢļ
    -0.11
    -0.11
     (...)
    -0.11
    POSITIVE LOGITS
    ãģĵãģ¡ãĤī
    0.13
     Uncategorized
    0.13
     EXEMPLARY
    0.12
     jinak
    0.12
    here
    0.12
    ê¸Ķ
    0.12
    bett
    0.12
    ä¹ĭä¸Ģ
    0.11
    ìĿ¸ì§Ģ
    0.11
    .gdx
    0.11
    Act Density 0.005%

    No Known Activations