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

    Neuronpedia

    INDEX
    Explanations

    statements related to philosophical and social concepts

    oai_token-act-pair · gpt-3.5-turbo

    statements and concepts related to religion and morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Downs
    -0.81
     congr
    -0.79
    icago
    -0.77
     throats
    -0.75
    uld
    -0.74
    amins
    -0.73
     Celeb
    -0.73
    ulia
    -0.72
     Turns
    -0.69
    Buzz
    -0.67
    POSITIVE LOGITS
     rooted
    1.34
     characterized
    1.22
     insepar
    1.20
     intimately
    1.17
     conceived
    1.17
     mediated
    1.14
     intrinsically
    1.12
     shaped
    1.11
     embodied
    1.09
     grounded
    1.09
    Act Density 0.283%

    No Known Activations