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

    Neuronpedia

    INDEX
    Explanations

    information related to disasters and casualties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     airports
    -0.16
     Threat
    -0.15
     Interr
    -0.15
    alom
    -0.15
    iyel
    -0.14
    æľºåľº
    -0.14
    threat
    -0.14
    andalone
    -0.14
     misunder
    -0.14
    //{{
    -0.14
    POSITIVE LOGITS
     survivors
    0.26
     deadliest
    0.24
     survivor
    0.23
     tragedy
    0.23
     infer
    0.23
     disaster
    0.22
     deadly
    0.22
     stamp
    0.20
     crush
    0.19
     Survivor
    0.19
    Act Density 0.043%

    No Known Activations