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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal sequence

    oai_token-act-pair · gpt-3.5-turbo

    sequential actions and events in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     currently
    -0.66
     formerly
    -0.61
     prior
    -0.61
     affair
    -0.60
     gorilla
    -0.59
     nowadays
    -0.58
     lately
    -0.57
     Earlier
    -0.56
     unlike
    -0.55
     today
    -0.55
    POSITIVE LOGITS
    EEK
    0.76
    maxwell
    0.73
     proceeded
    0.71
    bered
    0.68
    raq
    0.67
    leep
    0.67
    iphany
    0.67
    GGGG
    0.66
    AAAAAAAA
    0.66
    rosis
    0.66
    Act Density 0.506%

    No Known Activations