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

    Neuronpedia

    INDEX
    Explanations

    instances where an action is currently happening or in progress

    oai_token-act-pair · gpt-3.5-turbo

    the word "being" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Relief
    -0.70
     Mobility
    -0.68
     srfAttach
    -0.67
     Taxes
    -0.62
     VIDEOS
    -0.61
     Elements
    -0.61
     Lag
    -0.60
    PsyNetMessage
    -0.59
     Parables
    -0.59
     Wid
    -0.58
    POSITIVE LOGITS
     able
    0.98
     replaced
    0.97
     evaluated
    0.95
     judged
    0.94
     treated
    0.94
     assessed
    0.89
     phased
    0.88
     tested
    0.88
    amed
    0.87
     eaten
    0.86
    Act Density 0.057%

    No Known Activations