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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting nuances within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Įĵ
    -0.16
    elts
    -0.15
    ib
    -0.14
    illes
    -0.14
    rosse
    -0.14
     traces
    -0.13
    exus
    -0.13
    ült
    -0.13
    dbus
    -0.13
    preload
    -0.13
    POSITIVE LOGITS
    gis
    0.17
     Kok
    0.16
    ipop
    0.15
    rames
    0.14
    ola
    0.14
    369
    0.14
     premise
    0.14
    ledi
    0.14
    rength
    0.13
    (...)↵
    0.13
    Act Density 0.001%

    No Known Activations