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

    Neuronpedia

    INDEX
    Explanations

    phrases related to stories claimed to be true or having a sense of authenticity

    oai_token-act-pair · gpt-3.5-turbo

    references to "true" narratives or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acco
    -0.83
    ocene
    -0.76
    Corp
    -0.76
    served
    -0.74
    Pages
    -0.73
    ONES
    -0.73
    uled
    -0.73
    artment
    -0.71
    adish
    -0.71
    azine
    -0.68
    POSITIVE LOGITS
     believer
    1.00
     believers
    0.97
     freshman
    0.77
    stic
    0.77
     positives
    0.74
    terday
    0.71
    ignment
    0.69
     patriot
    0.69
    çĭ
    0.68
     emancipation
    0.67
    Act Density 0.022%

    No Known Activations