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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffin
    -0.14
    869
    -0.14
    719
    -0.14
     Fasc
    -0.14
     Titanic
    -0.14
    -0.13
    763
    -0.13
    keypress
    -0.13
    selectAll
    -0.13
    arker
    -0.12
    POSITIVE LOGITS
    ulus
    0.17
    icio
    0.14
    legates
    0.14
    G
    0.14
    Ch
    0.14
    St
    0.13
    ffen
    0.13
    H
    0.13
    vice
    0.13
    oves
    0.13
    Act Density 0.369%

    No Known Activations