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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political news and events

    oai_token-act-pair · gpt-3.5-turbo

    words associated with military actions or events related to conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oway
    -0.73
    tons
    -0.73
     Nichols
    -0.73
     Michaels
    -0.71
    ross
    -0.71
     Greenberg
    -0.70
     Perkins
    -0.69
     Oaks
    -0.69
    phalt
    -0.68
     Payne
    -0.67
    POSITIVE LOGITS
     CITY
    1.07
    ANK
    1.00
    ANA
    0.88
    EMBER
    0.87
    UTERS
    0.86
    Reuters
    0.85
    IST
    0.83
    WASHINGTON
    0.82
    ANG
    0.81
    ANI
    0.80
    Act Density 0.083%

    No Known Activations