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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "unique" indicating special or distinctive qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thew
    -0.16
    anten
    -0.14
    argin
    -0.14
    thought
    -0.13
    anda
    -0.13
    dech
    -0.13
    erton
    -0.13
    camp
    -0.13
     antis
    -0.13
    .GetChild
    -0.13
    POSITIVE LOGITS
    hey
    0.16
    857
    0.15
    iox
    0.15
    orks
    0.15
    897
    0.14
    Msp
    0.14
    ynn
    0.14
    ois
    0.14
    WP
    0.14
    (unique
    0.14
    Act Density 0.018%

    No Known Activations