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

    Neuronpedia

    INDEX
    Explanations

    references to glass items or features

    oai_token-act-pair · gpt-3.5-turbo

    references to glass in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.81
    addr
    -0.75
    nr
    -0.71
     RELE
    -0.70
     Resp
    -0.69
    reon
    -0.68
    rosso
    -0.68
     Sequ
    -0.68
    respond
    -0.67
     Nationals
    -0.67
    POSITIVE LOGITS
     glass
    3.73
    Glass
    2.55
    glass
    2.55
     Glass
    2.44
     glasses
    2.19
     champagne
    1.35
     ceramic
    1.34
     plastic
    1.30
     windshield
    1.29
     bottle
    1.28
    Act Density 0.021%

    No Known Activations