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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progressive changes in data, particularly concerning concentrations and trends over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enseits
    -0.65
    alamus
    -0.54
    itola
    -0.53
     Li
    -0.51
    rawDesc
    -0.50
    webElementGuid
    -0.50
    ributor
    -0.50
    ]=="
    -0.50
    wikipedia
    -0.49
    uminazione
    -0.49
    POSITIVE LOGITS
     successive
    0.81
     progressively
    0.79
     stages
    0.77
     progression
    0.76
     successively
    0.74
     stepwise
    0.71
     evolving
    0.70
     Progression
    0.69
     sequentially
    0.67
     evolution
    0.67
    Act Density 0.680%

    No Known Activations