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

    Neuronpedia

    INDEX
    Explanations

    words related to actions involving physical movements

    oai_token-act-pair · gpt-3.5-turbo

    the presence of indefinite articles and descriptors in contexts depicting various scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     annually
    -0.76
    iments
    -0.74
     endeavors
    -0.70
    Own
    -0.69
    views
    -0.66
    Hon
    -0.66
    Merit
    -0.66
    achu
    -0.65
     Includes
    -0.65
    America
    -0.65
    POSITIVE LOGITS
     couple
    1.10
     handful
    1.07
     few
    1.05
     nearby
    1.00
     bunch
    0.96
     lot
    0.95
     flurry
    0.93
     flashback
    0.93
     friend
    0.88
     bystand
    0.86
    Act Density 0.472%

    No Known Activations