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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to accidents, injuries, and disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Threat
    -0.17
     Interr
    -0.15
    urga
    -0.14
    threat
    -0.14
    enis
    -0.14
     kê
    -0.14
    repos
    -0.14
     عص
    -0.14
     steal
    -0.13
     Assault
    -0.13
    POSITIVE LOGITS
     tragedy
    0.29
     deadliest
    0.26
     disaster
    0.25
     deaths
    0.24
     accident
    0.23
     fatalities
    0.23
     infer
    0.22
     deadly
    0.22
     survivors
    0.21
     stamp
    0.21
    Act Density 0.092%

    No Known Activations