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

    Neuronpedia

    INDEX
    Explanations

    references to time periods, specifically the concept of something happening continuously or repeatedly over a period of time

    oai_token-act-pair · gpt-3.5-turbo

    references to recurring themes or events over multiple years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anooga
    -0.72
    uyomi
    -0.72
     rooft
    -0.70
    CHAT
    -0.68
    ilian
    -0.67
     DISTRICT
    -0.65
    usky
    -0.65
    oxide
    -0.65
    ignant
    -0.63
    atche
    -0.63
    POSITIVE LOGITS
     reckoning
    0.74
    EVA
    0.64
     spent
    0.61
     Asc
    0.61
     touring
    0.60
     bye
    0.60
     graduating
    0.59
    redits
    0.59
     Guinness
    0.59
     Vera
    0.58
    Act Density 0.386%

    No Known Activations