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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    references to personal opinions or subjective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Keynes
    -0.62
     Mechdragon
    -0.59
     Directory
    -0.57
     annexation
    -0.56
     Lyons
    -0.55
     Mobil
    -0.55
     Kabul
    -0.55
     aerobic
    -0.55
     Tours
    -0.55
     antid
    -0.55
    POSITIVE LOGITS
    _.
    1.10
    [/
    1.09
     thats
    1.08
    ,,,,
    1.05
    YOU
    0.99
    sorry
    0.97
     haha
    0.97
    _-
    0.96
    THIS
    0.94
    cause
    0.93
    Act Density 0.878%

    No Known Activations