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

    Neuronpedia

    INDEX
    Explanations

    mentions of violent incidents or accidents

    oai_token-act-pair · gpt-3.5-turbo

    reports on violent incidents and official statements regarding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Founders
    -0.81
    constitutional
    -0.75
    BILL
    -0.72
     Founding
    -0.70
     infringing
    -0.70
    TPP
    -0.69
    */(
    -0.69
    bill
    -0.69
     ALEC
    -0.69
     Plaintiff
    -0.68
    POSITIVE LOGITS
     blamed
    1.13
     evacuated
    1.05
     estimates
    1.03
     helicopters
    1.02
     spokesman
    1.02
     casualty
    0.99
     eyewitness
    0.99
     evacuate
    0.95
     mourn
    0.95
     officials
    0.92
    Act Density 0.517%

    No Known Activations