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

    Neuronpedia

    INDEX
    Explanations

    phrases related to predictions and uncertainties about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regrets
    -0.15
     regret
    -0.15
    prot
    -0.14
    éłĵ
    -0.14
    ved
    -0.14
    ilar
    -0.14
    ÙĩÙĨ
    -0.14
     seizure
    -0.14
    ffen
    -0.14
    BR
    -0.13
    POSITIVE LOGITS
    erken
    0.18
     Ort
    0.15
     Garten
    0.15
    atters
    0.14
    _href
    0.14
     Buk
    0.14
    hung
    0.14
    aea
    0.14
    hte
    0.14
    .Flag
    0.14
    Act Density 0.054%

    No Known Activations