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

    Neuronpedia

    INDEX
    Explanations

    direct eye contact and interaction between individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions that indicate attention or scrutiny between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Claim
    -0.67
    Fact
    -0.65
     orchestr
    -0.64
     ASC
    -0.64
     preached
    -0.63
    ¬¼
    -0.62
    theless
    -0.62
    Course
    -0.61
    Skill
    -0.60
    Ep
    -0.59
    POSITIVE LOGITS
     blank
    0.92
     gaze
    0.89
     stare
    0.88
     eyes
    0.85
     stares
    0.84
     faces
    0.83
    screen
    0.82
     wink
    0.80
     smir
    0.80
     retina
    0.79
    Act Density 0.275%

    No Known Activations