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

    Neuronpedia

    INDEX
    Explanations

    mentions of societal concepts and structures

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of society and its impact on various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urations
    -0.84
    Pad
    -0.76
    ruction
    -0.73
    word
    -0.70
    orney
    -0.67
    ocular
    -0.66
    iverse
    -0.66
    orescence
    -0.65
    rav
    -0.64
    etsk
    -0.63
    POSITIVE LOGITS
    wide
    1.04
    folk
    0.81
    liness
    0.80
    ically
    0.74
    eers
    0.71
    fare
    0.70
     indo
    0.70
    geist
    0.68
     deems
    0.66
     evolves
    0.66
    Act Density 0.024%

    No Known Activations