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

    Neuronpedia

    INDEX
    Explanations

    occurrences of various forms of the verb "to be" and related expressions of state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     erect
    -0.16
     implant
    -0.14
     Michele
    -0.14
    ίÏīν
    -0.14
    Supported
    -0.14
    绾
    -0.13
     Supported
    -0.13
     infr
    -0.13
    hab
    -0.13
    baum
    -0.13
    POSITIVE LOGITS
     persisted
    0.20
     added
    0.19
     written
    0.19
     present
    0.19
     stored
    0.19
     ali
    0.19
     rebound
    0.19
     saved
    0.19
     passed
    0.17
     resent
    0.17
    Act Density 0.277%

    No Known Activations