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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ones
    -0.16
    ampo
    -0.15
    agna
    -0.14
    PPER
    -0.14
    .isSelected
    -0.14
    .scalablytyped
    -0.14
    ｡
    -0.14
    inish
    -0.14
    unist
    -0.13
    regor
    -0.13
    POSITIVE LOGITS
     whose
    0.35
    whose
    0.28
     which
    0.27
     another
    0.23
     whom
    0.19
     where
    0.19
    which
    0.19
     اÙĦØ°ÙĬ
    0.17
     itself
    0.17
     cui
    0.17
    Act Density 0.207%

    No Known Activations