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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TION
    -0.17
    ahn
    -0.16
    oger
    -0.15
    iyas
    -0.15
    ONTAL
    -0.15
    igar
    -0.14
     Otherwise
    -0.14
    ilon
    -0.14
    ноÑİ
    -0.14
    Otherwise
    -0.14
    POSITIVE LOGITS
    liter
    0.19
     ranging
    0.19
     Gone
    0.18
     Liter
    0.17
     aside
    0.16
     gone
    0.16
    543
    0.15
     literally
    0.15
    alah
    0.14
    Liter
    0.14
    Act Density 0.253%

    No Known Activations