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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    article usage, particularly the word "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATURES
    -0.79
    allion
    -0.70
    loads
    -0.68
     inspiration
    -0.68
    ours
    -0.66
    iversary
    -0.65
    oola
    -0.65
    onis
    -0.65
    ontent
    -0.65
    aints
    -0.64
    POSITIVE LOGITS
     nutshell
    1.32
     hurry
    1.30
     manner
    1.25
     timely
    1.06
     heartbeat
    1.03
     phased
    1.01
     bid
    0.97
     vacuum
    0.95
     crowded
    0.95
     pinch
    0.89
    Act Density 0.131%

    No Known Activations