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

    Neuronpedia

    INDEX
    Explanations

    people looking into each other's eyes

    oai_token-act-pair · gpt-3.5-turbo

    instances of looking at or making eye contact with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥİ
    -0.69
    atra
    -0.67
     ASC
    -0.65
    avier
    -0.65
    ¬¼
    -0.64
    olo
    -0.63
    Fact
    -0.62
    eno
    -0.61
     orchestr
    -0.60
    ulo
    -0.60
    POSITIVE LOGITS
     blank
    1.06
     curiously
    1.01
     disappro
    1.00
     puzzled
    0.98
     horrified
    0.94
     stares
    0.94
     quizz
    0.92
     eyes
    0.90
     frown
    0.90
     suspicious
    0.89
    Act Density 0.152%

    No Known Activations