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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related terms and conditional phrases in the context of events or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucs
    -0.16
    Ä©a
    -0.15
    ýš
    -0.15
    ãģĤãĤĬ
    -0.14
    еÑģÑĮ
    -0.14
    Edition
    -0.13
    £½
    -0.13
    hai
    -0.13
    é¡Į
    -0.13
     blow
    -0.13
    POSITIVE LOGITS
     fully
    0.20
     xong
    0.18
     stabil
    0.17
     complete
    0.16
     stabilization
    0.15
     finishes
    0.15
     AFTER
    0.15
    cox
    0.15
     finished
    0.15
    Fully
    0.15
    Act Density 0.230%

    No Known Activations