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

    Neuronpedia

    INDEX
    Explanations

    punctuation and structure in text, particularly focusing on various forms of leading spaces and sentence delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     habet
    -0.64
     ſtand
    -0.61
     juſt
    -0.59
     becauſe
    -0.59
     étoit
    -0.57
     auroit
    -0.56
     pouvoit
    -0.56
     femmin
    -0.56
     épar
    -0.55
     ſtate
    -0.55
    POSITIVE LOGITS
     ?>>
    0.74
    }>
    0.67
    --}}
    0.60
    hésite
    0.59
     propOrder
    0.59
    ')}}">
    0.59
    >--}}
    0.57
     }}">
    0.56
    PositiveButton
    0.56
    '">
    0.54
    Act Density 0.218%

    No Known Activations