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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and measures, particularly related to hazard ratios and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hazard ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.56
    IndentedString
    -0.51
    EDEFAULT
    -0.50
     ujednoznacz
    -0.50
     locu
    -0.44
    //
    -0.44
    AccessFile
    -0.43
    󠁿
    -0.42
    noopener
    -0.42
     AspNetCore
    -0.42
    POSITIVE LOGITS
     Hazardous
    0.81
     hazardous
    0.80
    Hazardous
    0.76
    hazardous
    0.66
     dangerous
    0.65
     hazard
    0.65
     peligros
    0.63
     Hazard
    0.62
    hazard
    0.61
     dangere
    0.60
    Act Density 0.005%

    No Known Activations