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

    Neuronpedia

    INDEX
    Explanations

    footage related to surveillance or capturing events

    oai_token-act-pair · gpt-3.5-turbo

    references to surveillance or recorded video footage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inence
    -0.73
    ccoli
    -0.69
    osi
    -0.69
    isse
    -0.66
    gently
    -0.66
     dement
    -0.65
    女
    -0.64
     Schwarz
    -0.63
    oslav
    -0.63
    sole
    -0.62
    POSITIVE LOGITS
     footage
    1.19
     filmed
    1.03
     depicting
    1.00
     cameras
    1.00
     clips
    0.99
     camera
    0.97
     recordings
    0.94
     recorder
    0.91
     tape
    0.88
     tapes
    0.88
    Act Density 0.060%

    No Known Activations