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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions happening in front of a specific audience or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases focused on events happening in front of an audience or crowd

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bach
    -0.68
    pring
    -0.68
    among
    -0.67
    bush
    -0.65
    ierra
    -0.63
    isure
    -0.63
     Levels
    -0.62
    berman
    -0.62
    nell
    -0.61
    oba
    -0.61
    POSITIVE LOGITS
     cameras
    1.11
     camera
    1.04
     onlook
    0.87
     audiences
    0.87
    camera
    0.86
     Camera
    0.84
     horrified
    0.84
     fireplace
    0.84
     crowds
    0.83
     cheering
    0.83
    Act Density 0.061%

    No Known Activations