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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å®ĥ们
    -0.19
    她们
    -0.19
     yourselves
    -0.18
     themselves
    -0.17
     thems
    -0.14
     them
    -0.14
     Yourself
    -0.14
    ết
    -0.13
    erah
    -0.13
     THEM
    -0.13
    POSITIVE LOGITS
     He
    1.07
     His
    1.03
    His
    0.93
    He
    0.86
    .He
    0.69
     Himself
    0.60
     HIS
    0.56
     his
    0.56
     he
    0.54
    ä»ĸçļĦ
    0.53
    Act Density 0.472%

    No Known Activations