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

    Neuronpedia

    INDEX
    Explanations

    percentage or fraction values indicating a division in two

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference a significant portion of a population or group, specifically those related to the concept of "half."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rav
    -0.71
     Mahar
    -0.63
     therape
    -0.61
     pastoral
    -0.60
     intermedi
    -0.59
     laure
    -0.58
    uli
    -0.58
    Clar
    -0.58
    Broad
    -0.57
     Merchant
    -0.57
    POSITIVE LOGITS
     percent
    0.83
    otine
    0.80
    usk
    0.76
    gage
    0.70
     cents
    0.67
     respondents
    0.66
    azo
    0.66
     thirds
    0.66
     %
    0.65
    pees
    0.64
    Act Density 0.057%

    No Known Activations