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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to danger and risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.93
    aarrggbb
    -0.84
     barran
    -0.81
     UNIVER
    -0.81
    ︎
    -0.80
    SwingConstants
    -0.80
    antaranya
    -0.79
     &___
    -0.76
     universelle
    -0.74
     résidence
    -0.74
    POSITIVE LOGITS
     Keim
    0.88
     Cassini
    0.79
    mush
    0.73
     Richelieu
    0.73
     Hooks
    0.72
    bacillus
    0.72
     Kendall
    0.70
    mathscr
    0.69
     alms
    0.69
    nals
    0.69
    Act Density 0.584%

    No Known Activations