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

    Neuronpedia

    INDEX
    Explanations

    affirmations and responses in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyim
    -0.17
    istrov
    -0.15
    swick
    -0.14
     Dense
    -0.14
    metatable
    -0.14
     íĮĮìĿ¼ì²¨ë¶Ģ
    -0.14
    trie
    -0.13
    åĹ
    -0.13
    æ½
    -0.13
    uru
    -0.13
    POSITIVE LOGITS
    olla
    0.16
    -ing
    0.15
    dden
    0.15
    ÂĿ
    0.15
    series
    0.14
    pollo
    0.14
    plusplus
    0.14
    enant
    0.14
    æ£Ĵ
    0.14
    ilia
    0.13
    Act Density 0.097%

    No Known Activations