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

    Neuronpedia

    INDEX
    Explanations

    words related to trends, specifically focusing on directional movements such as upward or downward trends

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trends in directional changes, especially focusing on upward and downward movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DN
    -0.83
    inea
    -0.79
    mberg
    -0.75
    ère
    -0.74
    abase
    -0.68
    nington
    -0.66
    anan
    -0.65
    uala
    -0.65
    BuyableInstoreAndOnline
    -0.64
    ghazi
    -0.64
    POSITIVE LOGITS
     spiral
    1.01
    ly
    1.01
    ward
    1.01
     Spiral
    0.93
     trajectory
    0.93
     traject
    0.92
    wards
    0.91
    bound
    0.88
     causation
    0.87
    most
    0.86
    Act Density 0.069%

    No Known Activations