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

    Neuronpedia

    INDEX
    Explanations

    announcements or addresses related to political or social issues

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or announcements related to political or social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Squadron
    -0.64
     Rahman
    -0.61
     Spectrum
    -0.60
    wards
    -0.60
     Exhibition
    -0.58
     cabinets
    -0.56
     Buch
    -0.55
     McF
    -0.55
     nails
    -0.55
     shred
    -0.54
    POSITIVE LOGITS
    WASHINGTON
    0.98
    SAN
    0.75
    TOR
    0.74
    LOS
    0.72
    eport
    0.71
    GREEN
    0.69
    Amid
    0.67
     CONTR
    0.66
    ASHINGTON
    0.66
    ampa
    0.66
    Act Density 0.281%

    No Known Activations