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

    Neuronpedia

    INDEX
    Explanations

    phrases related to trends and fluctuations over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to trends and patterns in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Honest
    -0.72
     Clever
    -0.69
     Choose
    -0.68
     CCTV
    -0.66
    quartered
    -0.65
     Loaded
    -0.65
     Ingredients
    -0.64
     Donation
    -0.64
     voic
    -0.64
    umbn
    -0.62
    POSITIVE LOGITS
     plateau
    1.49
     peaks
    1.35
     peaked
    1.31
     lows
    1.27
     downward
    1.20
     stagnation
    1.20
     dips
    1.15
     declines
    1.15
     downwards
    1.13
     decreasing
    1.10
    Act Density 0.500%

    No Known Activations