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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "by" indicating an action's performer or source

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utical
    -0.83
    soType
    -0.81
    bard
    -0.80
    enth
    -0.78
    NES
    -0.77
    velt
    -0.77
    dayName
    -0.77
    paren
    -0.76
    chio
    -0.76
    tti
    -0.76
    POSITIVE LOGITS
     gunfire
    1.15
     gunshot
    1.09
     gunmen
    0.99
     snipers
    0.96
     extremists
    0.92
     virtue
    0.90
     terrorists
    0.90
     gunshots
    0.90
     stray
    0.89
     suicide
    0.88
    Act Density 0.045%

    No Known Activations