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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-interest and social issues

    oai_token-act-pair · gpt-3.5-turbo

    complex concepts related to self-interest and interdependence in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tours
    -0.84
     braces
    -0.82
     packs
    -0.80
     ambassadors
    -0.80
     racks
    -0.79
     cleaners
    -0.79
     tourists
    -0.79
     rentals
    -0.78
     trailers
    -0.77
     interns
    -0.75
    POSITIVE LOGITS
    existing
    1.38
    intuitive
    1.25
    rational
    1.23
    dimensional
    1.22
    linear
    1.19
    context
    1.18
    defined
    1.16
    ministic
    1.14
    functional
    1.13
    hist
    1.12
    Act Density 0.255%

    No Known Activations