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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings or political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Roberts" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.92
    alities
    -0.77
    lihood
    -0.74
    ascar
    -0.71
    riots
    -0.69
    mble
    -0.69
     Beir
    -0.69
    uate
    -0.66
    uated
    -0.66
    ality
    -0.65
    POSITIVE LOGITS
    haw
    1.08
    ullivan
    0.87
    eln
    0.86
    onian
    0.85
    otle
    0.82
    burgh
    0.79
    dale
    0.77
    ç·
    0.76
    DOM
    0.75
    eye
    0.75
    Act Density 0.054%

    No Known Activations