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

    Neuronpedia

    INDEX
    Explanations

    references to survival and near-death experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    narrowly escaped death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StatelessWidget
    -0.52
    Sucesor
    -0.51
     kasarigan
    -0.45
     surla
    -0.43
     مشين
    -0.42
    Atsauces
    -0.38
    Leider
    -0.36
    Véxase
    -0.36
    LabelTagHelper
    -0.36
    省市镇
    -0.35
    POSITIVE LOGITS
     narrowly
    1.08
     lucky
    0.99
     escaped
    0.94
     luckily
    0.89
     survived
    0.89
     dodged
    0.88
    Lucky
    0.84
    lucky
    0.84
     Lucky
    0.83
     luck
    0.81
    Act Density 0.033%

    No Known Activations