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

    Neuronpedia

    INDEX
    Explanations

    phrases related to trends, especially directional trends like upward or downward movements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to trends in movement, both upward and downward, particularly in financial or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ère
    -0.79
    DN
    -0.74
    abase
    -0.72
    inea
    -0.70
    ATURE
    -0.69
    ulhu
    -0.68
    GER
    -0.67
     Maker
    -0.67
    ombie
    -0.66
    TOP
    -0.66
    POSITIVE LOGITS
     mobility
    1.04
     pressure
    1.00
     trajectory
    0.99
     spiral
    0.97
    ly
    0.97
     slope
    0.94
    pressure
    0.92
     traject
    0.91
     redistribution
    0.87
     Spiral
    0.86
    Act Density 0.032%

    No Known Activations