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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "nor" and its variations in negating contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NavParams
    -0.15
    .WinForms
    -0.14
    ursal
    -0.14
    urs
    -0.14
    avl
    -0.14
    ilha
    -0.14
    adget
    -0.14
     trá»ĭ
    -0.14
    isoft
    -0.13
    ERSIST
    -0.13
    POSITIVE LOGITS
    umber
    0.20
    theless
    0.18
    soever
    0.18
    lify
    0.18
    )((((
    0.16
    forth
    0.16
    ĶåĽŀ
    0.15
    ¼åIJĪ
    0.14
    ldb
    0.14
    zb
    0.14
    Act Density 0.023%

    No Known Activations