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

    Neuronpedia

    INDEX
    Explanations

    terms related to demographic descriptors or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing demographic majority or predominance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.72
     Apostles
    -0.71
    pper
    -0.69
     Myster
    -0.67
    attr
    -0.66
    Life
    -0.66
    Closure
    -0.66
     fences
    -0.65
     Chaser
    -0.65
    idge
    -0.65
    POSITIVE LOGITS
     predomin
    1.09
     predominantly
    0.94
     comprised
    0.85
     populated
    0.85
     dominated
    0.81
    majority
    0.78
     concentrated
    0.76
     localized
    0.74
     outnumbered
    0.74
     skewed
    0.74
    Act Density 0.004%

    No Known Activations