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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or situations that occurred in the past

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically the term "past" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anguage
    -0.74
    hyde
    -0.73
    zhen
    -0.70
    Software
    -0.68
    NEY
    -0.66
    Repeat
    -0.66
    Girls
    -0.66
    GAN
    -0.65
    BIL
    -0.65
    /#
    -0.65
    POSITIVE LOGITS
    ebin
    1.38
     tense
    0.94
    iche
    0.92
     generations
    0.87
     decade
    0.84
     midnight
    0.74
     week
    0.74
    İ
    0.72
     Fourth
    0.70
     millennium
    0.70
    Act Density 0.027%

    No Known Activations