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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming languages, technological concepts, and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and related grammatical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftime
    -0.72
    izabeth
    -0.68
    amus
    -0.62
    lon
    -0.61
    guyen
    -0.59
    onement
    -0.59
     exha
    -0.58
    itability
    -0.58
     teammate
    -0.58
    legate
    -0.58
    POSITIVE LOGITS
     They
    1.74
    they
    1.65
    They
    1.54
     THEY
    1.43
     they
    1.42
     These
    1.37
     Their
    1.36
    Their
    1.30
    These
    1.27
    their
    1.20
    Act Density 0.609%

    No Known Activations