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

    Neuronpedia

    INDEX
    Explanations

    phrases related to starting points or beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     objs
    -0.83
     Honeywell
    -0.81
     Dolan
    -0.81
     Mercure
    -0.79
    LEncoder
    -0.79
    apollo
    -0.79
     Cowper
    -0.78
    huawei
    -0.78
     Nugent
    -0.78
     navideñas
    -0.77
    POSITIVE LOGITS
     Starting
    1.44
    STARTING
    1.41
     STARTING
    1.37
    Starting
    1.35
     starting
    1.33
    starting
    1.31
    START
    1.26
    getStart
    1.21
     START
    1.17
     start
    1.17
    Act Density 0.090%

    No Known Activations