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

    Neuronpedia

    INDEX
    Explanations

    phrases related to activities or events happening behind the scenes

    oai_token-act-pair · gpt-3.5-turbo

    references to behind-the-scenes activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odder
    -0.84
    apa
    -0.75
    rill
    -0.75
    ibaba
    -0.74
    alach
    -0.73
    asus
    -0.71
    engu
    -0.71
    ipl
    -0.71
    arcity
    -0.70
    heit
    -0.69
    POSITIVE LOGITS
     scenes
    0.86
    spection
    0.74
    scenes
    0.73
     antics
    0.70
     filming
    0.70
    scene
    0.65
     workings
    0.63
    doors
    0.62
     sporting
    0.61
     whispers
    0.61
    Act Density 0.031%

    No Known Activations