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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating future events

    oai_token-act-pair · gpt-3.5-turbo

    scheduled events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.92
    checking
    -0.70
    anooga
    -0.67
     Perspective
    -0.66
     ILCS
    -0.65
    Tips
    -0.65
     Checking
    -0.64
    protection
    -0.64
    Apps
    -0.63
    calling
    -0.62
    POSITIVE LOGITS
     expire
    1.56
     arrive
    1.45
     commence
    1.30
     unveil
    1.28
     begin
    1.28
     undergo
    1.27
     embark
    1.20
     depart
    1.13
     coincide
    1.12
     announce
    1.12
    Act Density 0.075%

    No Known Activations