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

    Neuronpedia

    INDEX
    Explanations

    references to historical events or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific historical locations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lime
    -0.77
     turtles
    -0.76
    Native
    -0.74
     coral
    -0.73
     coconut
    -0.71
    Jay
    -0.68
     snake
    -0.68
     snakes
    -0.68
     peas
    -0.68
     Native
    -0.66
    POSITIVE LOGITS
    heit
    1.31
     Mü
    1.30
    ÃŁ
    1.30
    hof
    1.26
     Dortmund
    1.26
    ü
    1.19
     Munich
    1.19
     Bundes
    1.18
     Gö
    1.18
    stein
    1.17
    Act Density 0.367%

    No Known Activations