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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the discovery or confirmation of information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "found" in the context of discoveries or reports, particularly relating to deceased individuals or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tert
    -0.73
    creation
    -0.66
    awk
    -0.66
    yip
    -0.64
    dos
    -0.62
    idium
    -0.61
     expectations
    -0.61
     restriction
    -0.60
    dayName
    -0.59
     compulsion
    -0.59
    POSITIVE LOGITS
    Ô
    0.98
    âĸĪ
    0.81
    Ú
    0.77
    dylib
    0.76
    س
    0.76
    ÙIJ
    0.74
     Tradable
    0.74
     Guilty
    0.73
    ت
    0.73
    د
    0.72
    Act Density 0.028%

    No Known Activations