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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "adopt" followed by a verb or noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "adopt."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isal
    -0.65
     Kah
    -0.63
    TPS
    -0.62
    selves
    -0.61
    wer
    -0.59
     Brun
    -0.57
    affer
    -0.57
     9000
    -0.57
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.57
     Dish
    -0.57
    POSITIVE LOGITS
     adopt
    1.18
     adoption
    1.04
     adopted
    1.04
     adopting
    0.91
    soDeliveryDate
    0.86
    opted
    0.80
    alogy
    0.79
    iors
    0.78
    ions
    0.78
     adop
    0.77
    Act Density 0.011%

    No Known Activations