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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, instructions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and phrases related to requirements or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     watching
    -0.91
    watching
    -0.83
     Watching
    -0.82
    checking
    -0.82
     mindful
    -0.79
     overseeing
    -0.79
    thinking
    -0.75
     reviewing
    -0.75
    forcing
    -0.75
     debating
    -0.74
    POSITIVE LOGITS
     contain
    1.52
     undergo
    1.33
     withstand
    1.25
     belong
    1.25
     survive
    1.22
     originate
    1.22
     emit
    1.20
     conform
    1.20
     behave
    1.18
     exist
    1.16
    Act Density 0.435%

    No Known Activations