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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to the concepts of paradise and Eden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sonian
    -0.84
    orno
    -0.82
    intent
    -0.80
    enegger
    -0.79
    weak
    -0.76
    umin
    -0.71
    ener
    -0.71
    ratulations
    -0.70
    ifts
    -0.68
    lass
    -0.68
    POSITIVE LOGITS
     Paradise
    1.22
     paradise
    1.04
     awaits
    0.78
    liness
    0.77
    jar
    0.77
     Scotia
    0.72
     Island
    0.72
     Garage
    0.72
     Bunny
    0.72
    lihood
    0.71
    Act Density 0.015%

    No Known Activations