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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical data and references to quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     numbered
    -0.19
    IED
    -0.18
    utin
    -0.17
    ward
    -0.15
    roads
    -0.15
    _utf
    -0.15
    eward
    -0.15
    ear
    -0.15
    rid
    -0.15
    avin
    -0.14
    POSITIVE LOGITS
     crunch
    0.28
    ical
    0.26
     Crunch
    0.23
    plate
    0.22
    -cr
    0.22
    ered
    0.21
    erable
    0.21
    icator
    0.21
    wang
    0.21
     liá»ĩu
    0.20
    Act Density 0.060%

    No Known Activations