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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the initiation or beginning of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fieldName
    -0.91
     itemprop
    -0.90
     contextLoads
    -0.89
     Honeywell
    -0.87
     Nugent
    -0.82
     Cowper
    -0.82
     Dolan
    -0.82
    LEncoder
    -0.81
     objs
    -0.80
    ضان
    -0.80
    POSITIVE LOGITS
     starting
    1.53
     Starting
    1.52
     start
    1.52
    START
    1.48
    Starting
    1.48
     Starts
    1.47
    STARTING
    1.46
     START
    1.45
    starting
    1.45
     STARTING
    1.44
    Act Density 0.064%

    No Known Activations