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

    Neuronpedia

    INDEX
    Explanations

    references to data values or metrics related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithFormat
    -0.75
     '{@
    -0.74
    ρε
    -0.71
     Процитовано
    -0.71
    ::::::::
    -0.69
     >=",
    -0.67
     πά
    -0.67
    +:+
    -0.67
    complexType
    -0.67
    *)&
    -0.66
    POSITIVE LOGITS
    1
    0.96
    st
    0.80
    ilets
    0.70
     Eleventh
    0.65
     XI
    0.63
    FileUtil
    0.63
    ⁄
    0.62
     chives
    0.61
     referenties
    0.61
     Achille
    0.60
    Act Density 0.863%

    No Known Activations