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

    Neuronpedia

    INDEX
    Explanations

    words related to time

    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
    ramid
    -0.93
    ortium
    -0.91
    avorite
    -0.80
    riad
    -0.80
    artisan
    -0.77
    alach
    -0.74
    ongyang
    -0.73
    insula
    -0.73
    riks
    -0.72
    racted
    -0.71
    POSITIVE LOGITS
    frames
    1.06
    frame
    0.88
    borne
    0.85
     elapsed
    0.84
    zone
    0.84
    days
    0.80
    ãĥ¼ãĥ³
    0.75
     periods
    0.74
     consuming
    0.73
    bell
    0.73
    Act Density 0.096%

    No Known Activations