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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jadx
    -0.18
    bakan
    -0.15
    ipple
    -0.14
    ipples
    -0.14
    hatt
    -0.14
    ác
    -0.14
    iode
    -0.14
    (Of
    -0.14
    iminal
    -0.14
    frage
    -0.13
    POSITIVE LOGITS
     talking
    0.28
     Talking
    0.27
    Talking
    0.23
     similarly
    0.20
    CAP
    0.19
     apart
    0.19
     talks
    0.18
     Sources
    0.18
     sources
    0.18
    Caption
    0.18
    Act Density 0.008%

    No Known Activations