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

    Neuronpedia

    INDEX
    Explanations

    words related to growth, progression, and trends

    oai_token-act-pair · gpt-3.5-turbo

    topics related to political movements and societal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Founding
    -0.74
     memorable
    -0.67
     predec
    -0.63
    inctions
    -0.62
    ritical
    -0.61
    akespeare
    -0.60
     ORIG
    -0.59
     1969
    -0.59
     1975
    -0.57
    ented
    -0.57
    POSITIVE LOGITS
     lately
    1.35
     now
    0.97
     tonight
    0.91
     nowadays
    0.90
     today
    0.87
     urgently
    0.84
     furiously
    0.84
     everywhere
    0.81
     NOW
    0.80
     frantically
    0.80
    Act Density 0.780%

    No Known Activations