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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotions or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to feelings and emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.70
    tainment
    -0.64
    adra
    -0.63
    sites
    -0.62
    dds
    -0.60
    advertising
    -0.60
     Discussion
    -0.60
    ulton
    -0.59
    Cod
    -0.59
    config
    -0.59
    POSITIVE LOGITS
     urge
    1.19
     compulsion
    1.08
     kins
    1.07
     warmth
    1.03
     acutely
    1.00
     pressure
    0.96
     obligation
    0.94
     Bern
    0.94
     compelled
    0.93
     pinch
    0.93
    Act Density 0.120%

    No Known Activations