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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives for intelligence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "smarter" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eda
    -0.76
     Gazette
    -0.68
     Secret
    -0.68
    Area
    -0.67
    Demon
    -0.67
    ANA
    -0.66
    Jer
    -0.61
     Divinity
    -0.61
    aints
    -0.61
    ACA
    -0.61
    POSITIVE LOGITS
     intellig
    0.95
    elligent
    0.89
    sonian
    0.86
     smarter
    0.85
     intelligent
    0.82
     behavi
    0.79
     smartest
    0.79
     optim
    0.77
     alloc
    0.76
     execut
    0.74
    Act Density 0.008%

    No Known Activations