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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "short" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.72
     שוליים
    -0.70
    /*
    -0.66
     InputDecoration
    -0.65
    IsPostBack
    -0.65
    \{\\
    -0.60
     /\.
    -0.59
    calciatore
    -0.57
     Thayer
    -0.57
    Bibliographie
    -0.57
    POSITIVE LOGITS
     short
    1.29
    Short
    1.28
     SHORT
    1.27
     Short
    1.26
    short
    1.15
    SHORT
    1.15
     Shorts
    0.93
    Kurz
    0.88
     shor
    0.85
     shorts
    0.85
    Act Density 0.101%

    No Known Activations