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

    Neuronpedia

    INDEX
    Explanations

    references to uncertainty and its various implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utt
    -0.16
    atoi
    -0.15
    dish
    -0.15
    enta
    -0.15
    ourd
    -0.14
    oya
    -0.14
    dry
    -0.14
    à¥ģह
    -0.14
    çİĩ
    -0.14
    몰
    -0.14
    POSITIVE LOGITS
    unc
    0.16
    ]={↵
    0.16
     sat
    0.16
    imed
    0.15
     Unc
    0.15
     пÑĢоÑĢ
    0.15
    eza
    0.15
     Hop
    0.14
    wchar
    0.14
    aguay
    0.14
    Act Density 0.037%

    No Known Activations