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

    Neuronpedia

    INDEX
    Explanations

    words related to terrorist attacks and investigations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    dit
    -0.87
    utical
    -0.73
    Intern
    -0.68
    angel
    -0.66
    API
    -0.66
    ophy
    -0.64
    cean
    -0.63
    fw
    -0.63
     macro
    -0.63
    uchin
    -0.62
    POSITIVE LOGITS
     spree
    1.20
     rampage
    1.02
     perpetrated
    0.98
     massacre
    0.96
     bombings
    0.91
     wounding
    0.86
     Massacre
    0.84
     aftermath
    0.84
     victims
    0.82
     rocked
    0.82
    Act Density 0.145%

    No Known Activations