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

    Neuronpedia

    INDEX
    Explanations

    mentions of someone or something also doing or having been part of an activity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "also" indicating additional information or participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     moreover
    -0.65
     even
    -0.63
     EVEN
    -0.62
    #$
    -0.60
    é¾įå¥ij士
    -0.60
    only
    -0.60
    assic
    -0.60
     ONLY
    -0.60
     comprehension
    -0.59
     ANY
    -0.58
    POSITIVE LOGITS
     benefited
    0.89
     participated
    0.89
     weighed
    0.83
     implicated
    0.82
     contributed
    0.82
     included
    0.77
     affected
    0.76
     impacted
    0.74
     fared
    0.72
     underwent
    0.71
    Act Density 0.119%

    No Known Activations