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

    Neuronpedia

    INDEX
    Explanations

    time-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.93
    ramid
    -0.91
    riad
    -0.84
    uilt
    -0.79
    avorite
    -0.79
    riks
    -0.76
    artisan
    -0.74
    racted
    -0.73
    alach
    -0.73
    erto
    -0.71
    POSITIVE LOGITS
    frames
    1.10
    frame
    0.87
    zone
    0.86
    borne
    0.84
     elapsed
    0.82
    days
    0.80
     consuming
    0.78
    bell
    0.72
     Bucc
    0.72
     msec
    0.71
    Act Density 0.088%

    No Known Activations