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

    Neuronpedia

    INDEX
    Explanations

    instances of negation and uncertainty in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isol
    -0.15
    åºĨ
    -0.15
    lian
    -0.15
    543
    -0.15
    лÑİ
    -0.14
    .sul
    -0.14
    agar
    -0.14
    ÑĸлÑĸ
    -0.14
    intColor
    -0.14
    ilyn
    -0.13
    POSITIVE LOGITS
     ÙĪÙĦد
    0.15
     ëĤĺ
    0.14
     Ph
    0.14
    eden
    0.14
     always
    0.14
     Nut
    0.14
     Commons
    0.14
    _PTR
    0.14
    .shtml
    0.14
    rolled
    0.13
    Act Density 0.150%

    No Known Activations