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

    Neuronpedia

    INDEX
    Explanations

    discussions related to efforts made to ensure safety and protect individuals' rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BorderFactory
    -0.72
     eventdata
    -0.62
     HasFactory
    -0.61
    ГЛА
    -0.61
    bufio
    -0.60
     useHistory
    -0.60
    Xna
    -0.60
    writeFieldEnd
    -0.57
    новниш
    -0.56
    windowFixed
    -0.56
    POSITIVE LOGITS
     efforts
    1.19
     Efforts
    1.14
     effort
    1.03
    efforts
    1.02
     measures
    1.02
     upaya
    0.98
     steps
    0.93
    steps
    0.92
    Measures
    0.91
     Steps
    0.91
    Act Density 0.285%

    No Known Activations