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

    Neuronpedia

    INDEX
    Explanations

    punctuations and conjunctions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    שְׁ
    -0.62
    bigoplus
    -0.61
    ią
    -0.61
    𝙫
    -0.59
    Tur
    -0.58
    krist
    -0.57
     يتيمه
    -0.57
    おきます
    -0.56
    δες
    -0.55
    べき
    -0.54
    POSITIVE LOGITS
    ,-,
    1.36
    .$,
    1.26
    ′,
    1.23
    °,
    1.22
     }}$,
    1.20
    €,
    1.17
    ​,
    1.16
    ,:),
    1.15
     \%$,
    1.14
    %,
    1.14
    Act Density 2.658%

    No Known Activations