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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "mention" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -confidence
    -0.15
    å»ł
    -0.15
    ids
    -0.14
    idend
    -0.14
    oons
    -0.13
    co
    -0.13
    zan
    -0.13
    ialis
    -0.13
    баÑĩ
    -0.13
    ogram
    -0.13
    POSITIVE LOGITS
     how
    0.23
    ioned
    0.22
    ned
    0.22
    how
    0.18
    -worthy
    0.17
    aire
    0.17
    oft
    0.16
    aires
    0.16
     prominently
    0.16
    ning
    0.16
    Act Density 0.063%

    No Known Activations