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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "heard" and its related forms, indicating discussions or reports about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    姿
    -0.15
    uji
    -0.15
    udden
    -0.15
     Pics
    -0.14
    ito
    -0.14
    exels
    -0.14
    iç
    -0.13
    -looking
    -0.13
     scene
    -0.13
     اÙĦظ
    -0.13
    POSITIVE LOGITS
    /read
    0.30
     about
    0.26
    kening
    0.23
    /watch
    0.21
     stories
    0.20
    about
    0.19
    _about
    0.18
    rum
    0.18
     tales
    0.18
    stories
    0.17
    Act Density 0.047%

    No Known Activations