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

    Neuronpedia

    INDEX
    Explanations

    terms related to structured representations in logical frameworks, specifically focusing on attack trees and semantics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     trib
    -0.16
     erg
    -0.16
     discreet
    -0.16
     Cron
    -0.14
    fields
    -0.14
     affection
    -0.14
     conventions
    -0.14
     rh
    -0.14
    acha
    -0.14
    faker
    -0.13
    POSITIVE LOGITS
    lift
    0.19
     witnessing
    0.19
    \<^
    0.18
     folklore
    0.18
    sound
    0.18
    Sound
    0.17
     Sound
    0.17
     Qed
    0.17
     sound
    0.17
     \<^
    0.17
    Act Density 0.031%

    No Known Activations