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

    Neuronpedia

    INDEX
    Explanations

    phrases related to incidents or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to incidents involving aircraft and safety alerts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.86
    soDeliveryDate
    -0.69
     "$
    -0.69
     endif
    -0.68
    toggle
    -0.67
     Wonders
    -0.67
    Pg
    -0.65
     economists
    -0.64
     addicts
    -0.64
     clout
    -0.64
    POSITIVE LOGITS
     ..."
    1.11
    %"
    1.06
     âĢ¦"
    1.03
     [
    1.02
    )",
    0.99
    ),"
    0.99
     Plaintiff
    0.98
    ,'"
    0.96
     Defendant
    0.93
    )"
    0.92
    Act Density 0.831%

    No Known Activations