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

    Neuronpedia

    INDEX
    Explanations

    references to specific years

    oai_token-act-pair · gpt-3.5-turbo

    references to the current year and its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTF
    -0.67
     territ
    -0.67
     sqor
    -0.65
     hemor
    -0.65
     luggage
    -0.64
    inki
    -0.62
    leeve
    -0.61
    ugar
    -0.60
    Phone
    -0.58
    ById
    -0.58
    POSITIVE LOGITS
    cific
    0.79
     æľ
    0.74
    nings
    0.67
     however
    0.66
    eve
    0.65
     Ago
    0.65
     marked
    0.64
     marks
    0.63
    gress
    0.61
     pt
    0.61
    Act Density 0.096%

    No Known Activations