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

    Neuronpedia

    INDEX
    Explanations

    the word "be" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "be" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Harlem
    -0.64
    ablishment
    -0.62
     guarantee
    -0.60
    ision
    -0.60
     Elise
    -0.59
     Mund
    -0.58
     Stain
    -0.58
    orer
    -0.58
    shall
    -0.57
     Must
    -0.57
    POSITIVE LOGITS
     forgiven
    1.03
     able
    0.94
     mistaken
    0.91
    acons
    0.90
     construed
    0.87
     tempted
    0.83
    heading
    0.79
     considered
    0.79
     regarded
    0.78
     underestimated
    0.77
    Act Density 0.148%

    No Known Activations