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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "subscribe" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wen
    -0.16
    ouz
    -0.15
    wer
    -0.14
    ight
    -0.14
    istically
    -0.14
    aps
    -0.14
    ìŀ¥
    -0.14
    tings
    -0.14
     passport
    -0.14
     Abe
    -0.14
    POSITIVE LOGITS
    .unsubscribe
    0.23
    /un
    0.18
     unsubscribe
    0.18
    unsubscribe
    0.17
    alem
    0.17
    alama
    0.16
     subscribed
    0.16
    tember
    0.16
    ees
    0.15
    intptr
    0.15
    Act Density 0.008%

    No Known Activations