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

    Neuronpedia

    INDEX
    Explanations

    instances of comments or annotations in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oste
    -0.16
    ovich
    -0.15
    ches
    -0.15
    _none
    -0.15
    steen
    -0.15
     âĨĴ↵↵
    -0.14
    _picker
    -0.14
    鸣
    -0.14
    ç´¹
    -0.14
    ħį
    -0.14
    POSITIVE LOGITS
    ominator
    0.16
     Friendship
    0.14
    inger
    0.14
     Clifford
    0.14
    onym
    0.14
    bao
    0.14
    erville
    0.14
    omial
    0.14
     Assistant
    0.14
     Chow
    0.13
    Act Density 0.016%

    No Known Activations