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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically the surname "Roberts"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Roberts"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥŁ
    -0.76
    bernatorial
    -0.76
    indu
    -0.71
     Manit
    -0.69
    itably
    -0.68
    liest
    -0.67
    igun
    -0.66
    ++++++++++++++++
    -0.66
    agn
    -0.64
    cond
    -0.63
    POSITIVE LOGITS
     Roberts
    1.27
    haw
    1.07
    ullivan
    0.89
    aunders
    0.88
    lett
    0.87
    Roberts
    0.87
    boa
    0.82
    icum
    0.78
    eteenth
    0.77
    sey
    0.77
    Act Density 0.006%

    No Known Activations