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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )âĢı
    -0.15
    ipher
    -0.14
     Datum
    -0.14
    SKU
    -0.14
    starter
    -0.14
    оза
    -0.14
    uzzi
    -0.14
    iversit
    -0.13
    алÑĥ
    -0.13
    ÙĪراÙĨ
    -0.13
    POSITIVE LOGITS
    Correction
    0.26
    COR
    0.21
     follow
    0.19
    Follow
    0.18
     correction
    0.17
    (This
    0.16
     Copyright
    0.16
    _correction
    0.16
     Follow
    0.16
    anela
    0.16
    Act Density 0.068%

    No Known Activations