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

    Neuronpedia

    INDEX
    Explanations

    programming language-related words or terms

    oai_token-act-pair · gpt-3.5-turbo

    the end of a document or text block

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULTS
    -0.68
     Haram
    -0.67
    Downloadha
    -0.66
     Scotia
    -0.62
     quo
    -0.60
     obscene
    -0.60
     bout
    -0.60
     exha
    -0.60
    ETHOD
    -0.59
     gymn
    -0.59
    POSITIVE LOGITS
    ed
    2.15
    ing
    1.81
    edly
    1.48
    ers
    1.44
    er
    1.43
    ership
    1.40
    s
    1.38
    edIn
    1.31
    edin
    1.26
    ered
    1.25
    Act Density 0.192%

    No Known Activations