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

    Neuronpedia

    INDEX
    Explanations

    locations or events related to disasters or tragedies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant locations associated with disasters and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Balt
    -0.81
    obin
    -0.70
    Dub
    -0.70
    Wilson
    -0.66
    writing
    -0.66
     Rockefeller
    -0.65
    DOS
    -0.65
    PATH
    -0.65
    wine
    -0.63
    TOR
    -0.63
    POSITIVE LOGITS
     Massacre
    0.93
    anooga
    0.86
     aftermath
    0.82
     victims
    0.80
     massacre
    0.80
     fallout
    0.78
     survivor
    0.78
     survivors
    0.77
     Dai
    0.73
     charred
    0.73
    Act Density 0.078%

    No Known Activations