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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and emergency preparedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.16
     Len
    -0.15
    935
    -0.15
     garn
    -0.15
    edio
    -0.15
    ãĥ¬ãĥ³
    -0.15
     escal
    -0.14
    неÑģÑĤи
    -0.14
    iotic
    -0.14
    Jvm
    -0.14
    POSITIVE LOGITS
     life
    0.30
     inflation
    0.28
     throwable
    0.28
     flotation
    0.27
     Life
    0.26
     buoy
    0.25
     Throwable
    0.25
     lifes
    0.24
    Life
    0.23
     float
    0.23
    Act Density 0.037%

    No Known Activations