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

    Neuronpedia

    INDEX
    Explanations

    parentheses and related punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.17
    лаÑĤи
    -0.15
    俺ãģ¯
    -0.15
    vier
    -0.14
    ÏĢί
    -0.14
    ikhail
    -0.14
    ihad
    -0.14
     ceiling
    -0.14
    DW
    -0.14
    å®Ļ
    -0.14
    POSITIVE LOGITS
    akin
    0.18
    \<^
    0.15
    geois
    0.15
     Sawyer
    0.15
    anship
    0.15
     Mev
    0.15
     repr
    0.14
    2
    0.14
    dbg
    0.14
     vog
    0.14
    Act Density 0.097%

    No Known Activations