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

    Neuronpedia

    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numeric dates or references related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yang
    -0.76
    udeb
    -0.71
    dyl
    -0.65
    kas
    -0.63
    within
    -0.63
    esan
    -0.61
    laus
    -0.61
     intercepted
    -0.61
    agna
    -0.61
     whipped
    -0.59
    POSITIVE LOGITS
    mber
    0.73
    ths
    0.69
    raq
    0.66
    PF
    0.66
     Atlantis
    0.66
    tenance
    0.66
     Veil
    0.65
    Dear
    0.62
    essage
    0.62
    jured
    0.62
    Act Density 0.057%

    No Known Activations