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

    Neuronpedia

    INDEX
    Explanations

    references to a specific group or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concess
    -0.68
    ournal
    -0.62
    èª
    -0.62
    cale
    -0.61
     dagger
    -0.57
     vap
    -0.56
     Plate
    -0.56
    ा
    -0.56
    iak
    -0.56
     sulph
    -0.56
    POSITIVE LOGITS
    members
    1.14
    think
    1.08
    mates
    1.01
    leader
    1.01
     members
    0.99
     disbanded
    0.95
    leaders
    0.92
    ings
    0.90
    ages
    0.88
    affiliated
    0.86
    Act Density 0.040%

    No Known Activations