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

    Neuronpedia

    INDEX
    Explanations

    references and occurrences of numerical values and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ward
    -0.20
     numbered
    -0.19
    eward
    -0.18
    utin
    -0.17
    umber
    -0.17
    WARD
    -0.16
    roads
    -0.15
    igo
    -0.15
    adaÅŁ
    -0.15
     numbering
    -0.15
    POSITIVE LOGITS
    eral
    0.23
    erable
    0.23
    çłģ
    0.21
     pháºŃn
    0.21
    ical
    0.21
    ered
    0.20
    erals
    0.19
    ake
    0.19
    wang
    0.19
     liá»ĩu
    0.19
    Act Density 0.081%

    No Known Activations