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

    Neuronpedia

    INDEX
    Explanations

    mentions of references or citations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uts
    -0.21
    istr
    -0.18
    ows
    -0.18
    sville
    -0.17
    la
    -0.17
    ern
    -0.17
    ish
    -0.16
    de
    -0.16
    ifter
    -0.15
    agn
    -0.15
    POSITIVE LOGITS
    ential
    0.25
    rence
    0.23
    able
    0.21
    resher
    0.20
    /reference
    0.20
    point
    0.18
    -point
    0.17
    æĸĩçĮ®
    0.17
    actoring
    0.17
    entially
    0.17
    Act Density 0.028%

    No Known Activations