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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical stability and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     agré
    -0.33
     cres
    -0.31
     gre
    -0.31
    श्न
    -0.28
    ThroughAttribute
    -0.28
    stdafx
    -0.27
     Conform
    -0.27
     iconLine
    -0.27
    Conform
    -0.26
    "){
    -0.26
    POSITIVE LOGITS
    QMetaType
    0.68
     nakalista
    0.66
     ambulatory
    0.63
     mishap
    0.57
     AssemblyCulture
    0.56
     clumsy
    0.54
     EconPapers
    0.54
     Höhe
    0.54
     ACCIDENT
    0.53
    Tembelea
    0.53
    Act Density 0.264%

    No Known Activations