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

    Neuronpedia

    INDEX
    Explanations

    time-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anium
    -0.80
    ãĥİ
    -0.73
    udeb
    -0.72
    acceptable
    -0.71
    conservancy
    -0.71
    ums
    -0.70
    arching
    -0.70
    cheat
    -0.67
    ĸļ
    -0.66
    particularly
    -0.64
    POSITIVE LOGITS
    ,
    0.97
     he
    0.81
     they
    0.79
     however
    0.77
     she
    0.74
     thereafter
    0.72
     another
    0.72
     we
    0.69
    ,.
    0.69
     someone
    0.69
    Act Density 0.226%

    No Known Activations