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

    Neuronpedia

    INDEX
    Explanations

    elements related to health and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лев
    -0.15
     [âĢ¦
    -0.14
    sec
    -0.14
     colorWithRed
    -0.14
     camp
    -0.13
     sec
    -0.13
     forg
    -0.13
     Camp
    -0.13
    /Form
    -0.13
     Restricted
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥª
    0.19
    ackets
    0.15
    ascade
    0.15
    urst
    0.15
    ija
    0.14
    eteria
    0.14
    ervlet
    0.14
    pak
    0.14
    porter
    0.14
     Zur
    0.14
    Act Density 0.772%

    No Known Activations