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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "nemesis" or related terms that suggest conflict or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _firestore
    -0.18
    p
    -0.17
    incl
    -0.16
    yor
    -0.16
    Wunused
    -0.16
    en
    -0.16
    ych
    -0.15
    y
    -0.15
    ickerView
    -0.15
    geois
    -0.15
    POSITIVE LOGITS
    eyer
    0.28
    perature
    0.25
    peror
    0.25
    eh
    0.23
    pleado
    0.21
    ar
    0.21
    esis
    0.20
    ee
    0.20
    pires
    0.19
    eb
    0.19
    Act Density 0.038%

    No Known Activations