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

    Neuronpedia

    INDEX
    Explanations

    phrases related to visual fixation or intense gaze

    oai_token-act-pair · gpt-3.5-turbo

    actions related to looking or observing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.78
    ctr
    -0.71
    interstitial
    -0.69
    notes
    -0.67
    rosse
    -0.67
    ERN
    -0.66
    actionDate
    -0.65
    icult
    -0.64
    akuya
    -0.62
    STRUCT
    -0.61
    POSITIVE LOGITS
     dag
    0.95
     gaze
    0.94
     stares
    0.93
     stare
    0.91
     staring
    0.89
     blank
    0.89
     stared
    0.80
    creen
    0.75
     gazing
    0.75
     unfocused
    0.74
    Act Density 0.024%

    No Known Activations