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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eration
    -0.18
    erable
    -0.16
    erator
    -0.16
    erer
    -0.16
    ermann
    -0.15
    erate
    -0.15
    halt
    -0.14
    iversit
    -0.14
    hard
    -0.14
    eki
    -0.14
    POSITIVE LOGITS
    elier
    0.21
    tempts
    0.21
     least
    0.21
    lassian
    0.20
    kinson
    0.19
    temps
    0.19
    -home
    0.18
    /by
    0.18
    rophy
    0.18
    -risk
    0.17
    Act Density 0.336%

    No Known Activations