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

    Neuronpedia

    INDEX
    Explanations

    interviews and reviews

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to media and entertainment content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.90
    sic
    -0.76
    maximum
    -0.72
    olson
    -0.71
    hap
    -0.69
    orthy
    -0.68
    fortunately
    -0.68
     lowly
    -0.68
    omever
    -0.68
    perature
    -0.68
    POSITIVE LOGITS
     Scenes
    0.97
     Manager
    0.96
     Tracker
    0.94
     Dates
    0.93
     Rankings
    0.92
     Tracks
    0.92
     Plans
    0.92
     Crimes
    0.91
     Reviews
    0.90
     Theme
    0.90
    Act Density 0.335%

    No Known Activations