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

    Neuronpedia

    INDEX
    Explanations

    particular special characters or diacritics in text, with a preference for the character "ê" and to some extent "è"

    oai_token-act-pair · gpt-4-turbo

    special characters and non-English characters, with a focus on the character 'ê'

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uctor
    -1.00
    Reviewer
    -0.77
    iaries
    -0.77
     guiActiveUn
    -0.73
    iary
    -0.73
    inarily
    -0.70
    ometimes
    -0.70
    ennial
    -0.69
    emonium
    -0.69
    ativity
    -0.68
    POSITIVE LOGITS
    ²
    1.24
    ¹
    1.21
    °
    1.16
    ¾
    1.14
    1.11
    ¼
    1.08
    ¸
    1.06
    ½
    1.05
    ³
    1.03
    ·
    1.01
    Act Density 0.003%

    No Known Activations