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

    Neuronpedia

    INDEX
    Explanations

    phrases related to American organizations and issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.81
    NB
    -0.75
    orders
    -0.72
    */(
    -0.69
    ijk
    -0.67
    sets
    -0.67
     STATS
    -0.65
    razil
    -0.63
    Prev
    -0.63
    pots
    -0.62
    POSITIVE LOGITS
     Idol
    1.08
    ICAN
    1.07
     Airlines
    1.03
     Samoa
    1.01
     Pie
    0.87
     Express
    0.84
     Dream
    0.84
     Legion
    0.82
     McGee
    0.81
     Psychiatric
    0.80
    Act Density 0.438%

    No Known Activations