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

    Neuronpedia

    INDEX
    Explanations

    references to electrical device operation and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lic
    -0.17
     Crowley
    -0.15
    alien
    -0.14
    æ½
    -0.13
     modular
    -0.13
     lic
    -0.13
    strup
    -0.13
    ÏĥÏĥ
    -0.13
     alien
    -0.13
    aliz
    -0.13
    POSITIVE LOGITS
     mode
    0.50
     modes
    0.42
     Mode
    0.42
    mode
    0.39
    Mode
    0.38
    -mode
    0.38
     Modes
    0.38
    _mode
    0.36
    模å¼ı
    0.34
    .mode
    0.33
    Act Density 0.188%

    No Known Activations