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

    Neuronpedia

    INDEX
    Explanations

    paragraphs that include non-English characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    instances of non-word characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     covenant
    -0.78
     treaty
    -0.77
    xual
    -0.77
     scrap
    -0.75
     grop
    -0.75
     describ
    -0.74
     unconditional
    -0.73
     nightly
    -0.71
     frontline
    -0.70
     undocumented
    -0.69
    POSITIVE LOGITS
    Advertisements
    1.22
    âķIJâķIJ
    1.18
    ------------------------
    1.17
    Posts
    1.15
    RAW
    1.15
    Section
    1.13
    Contribut
    1.13
    Synopsis
    1.13
    Topics
    1.11
    Topic
    1.11
    Act Density 0.271%

    No Known Activations