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

    Neuronpedia

    INDEX
    Explanations

    phrases related to continuity or persistence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĹ©
    -0.19
     earliest
    -0.19
     immediately
    -0.18
     early
    -0.18
     instantly
    -0.18
    uez
    -0.17
    early
    -0.15
     prematurely
    -0.15
     quickly
    -0.15
     ÙĤبÙĦ
    -0.15
    POSITIVE LOGITS
     longer
    0.34
     throughout
    0.30
     indefinitely
    0.27
     longest
    0.27
     Longer
    0.27
    ä¸ĭåİ»
    0.26
     till
    0.25
     until
    0.25
     Throughout
    0.24
    until
    0.22
    Act Density 0.260%

    No Known Activations