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

    Neuronpedia

    INDEX
    Explanations

    dates related to significant historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events related to September 11 attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bred
    -0.75
    reau
    -0.74
    ships
    -0.70
     carrot
    -0.68
    SPA
    -0.67
    SHIP
    -0.63
    BIL
    -0.63
     contrad
    -0.63
     royalties
    -0.61
    english
    -0.60
    POSITIVE LOGITS
    ghazi
    1.06
     Attacks
    1.00
     2001
    0.93
    arnaev
    0.93
     attacks
    0.91
     Massacre
    0.86
     bombings
    0.85
     bombing
    0.84
    attacks
    0.84
    ocaust
    0.84
    Act Density 0.119%

    No Known Activations