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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the beginning or starting point

    oai_token-act-pair · gpt-3.5-turbo

    references to beginnings or starting points in events or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aliation
    -0.70
    rored
    -0.68
    oother
    -0.68
    Els
    -0.66
    WA
    -0.63
     awa
    -0.61
    mun
    -0.59
    rian
    -0.59
    Steel
    -0.59
    ÙĴ
    -0.59
    POSITIVE LOGITS
     standpoint
    1.24
     perspective
    1.09
     onwards
    1.06
     perspectives
    0.98
     vantage
    0.91
     viewpoint
    0.85
    outer
    0.84
     sources
    0.80
     backgrounds
    0.77
    ratch
    0.77
    Act Density 0.191%

    No Known Activations