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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating numerical quantities or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.85
    /**
    -0.72
    belline
    -0.70
    Xna
    -0.68
    thenia
    -0.64
     саны
    -0.64
    EndProject
    -0.64
     AssemblyTitle
    -0.62
    izophrenia
    -0.61
     oubli
    -0.60
    POSITIVE LOGITS
     amount
    0.76
     total
    0.72
     noqa
    0.68
     time
    0.66
     additional
    0.62
     money
    0.61
    بوابة
    0.61
    amount
    0.60
    awtextra
    0.59
    Total
    0.58
    Act Density 0.224%

    No Known Activations