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

    Neuronpedia

    INDEX
    Explanations

    references to sources or citations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uts
    -0.19
    ows
    -0.18
    sville
    -0.17
    istr
    -0.17
    la
    -0.16
    wish
    -0.16
    ifter
    -0.15
    ستر
    -0.15
    de
    -0.15
    ish
    -0.15
    POSITIVE LOGITS
    ential
    0.25
    rence
    0.23
    able
    0.23
    resher
    0.22
    point
    0.21
     point
    0.20
    -point
    0.20
     points
    0.19
    æĸĩçĮ®
    0.18
    actoring
    0.17
    Act Density 0.026%

    No Known Activations