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

    Neuronpedia

    INDEX
    Explanations

    mentions or abbreviations related to news sources or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to national security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fare
    -0.73
    Äĩ
    -0.72
    ======
    -0.65
    zona
    -0.62
    thumbnails
    -0.62
    verages
    -0.61
     mats
    -0.60
    ments
    -0.60
     otherwise
    -0.60
    ça
    -0.59
    POSITIVE LOGITS
    FW
    1.26
    fw
    1.12
    ertodd
    1.01
    ettings
    0.85
    erve
    0.82
    lé
    0.82
    erver
    0.81
    daq
    0.81
    ensitive
    0.81
    ession
    0.80
    Act Density 0.018%

    No Known Activations