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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abbit
    -0.14
    ully
    -0.14
    à¥Īत
    -0.13
    xr
    -0.13
    Spoiler
    -0.13
    si
    -0.13
    ाय
    -0.13
    ê¸Ķ
    -0.13
    nesty
    -0.13
    ley
    -0.12
    POSITIVE LOGITS
     Till
    0.44
     Apart
    0.42
     apart
    0.41
    Apart
    0.41
     Majority
    0.34
     majority
    0.33
     till
    0.32
     Hence
    0.28
     hence
    0.28
    Talking
    0.26
    Act Density 0.304%

    No Known Activations