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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "starts" or related terms implying the beginning of a story or process

    oai_token-act-pair · gpt-3.5-turbo

    the beginnings of stories or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mented
    -0.80
    illard
    -0.78
    aths
    -0.76
    ilit
    -0.74
    mens
    -0.73
    luence
    -0.70
    ordinary
    -0.69
    ada
    -0.68
    otropic
    -0.67
    itte
    -0.67
    POSITIVE LOGITS
     anew
    0.92
     airing
    0.82
     raining
    0.77
     BELOW
    0.73
    nings
    0.71
    Ń·
    0.69
     leaking
    0.68
     dusk
    0.68
     abruptly
    0.67
     bothering
    0.66
    Act Density 0.080%

    No Known Activations