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

    Neuronpedia

    INDEX
    Explanations

    instances where an event or change is about to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply imminent actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Compass
    -0.77
     Explan
    -0.73
     Parables
    -0.71
    didn
    -0.69
     Perspective
    -0.69
     representations
    -0.68
     Howe
    -0.65
    quickShipAvailable
    -0.62
     Likes
    -0.62
     Corpus
    -0.62
    POSITIVE LOGITS
     embark
    1.24
     expire
    1.11
     explode
    0.98
     unleash
    0.96
    NetMessage
    0.94
     become
    0.94
     begin
    0.92
     retire
    0.91
     be
    0.91
     enter
    0.89
    Act Density 0.055%

    No Known Activations