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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or groups of people within various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to various groups or collective entities, particularly focusing on their characteristics or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thompson
    -0.66
     Sweeney
    -0.65
    llo
    -0.65
     HuffPost
    -0.63
    storm
    -0.61
     Sau
    -0.60
    aneously
    -0.60
    oslav
    -0.57
     Mann
    -0.57
    024
    -0.56
    POSITIVE LOGITS
    hip
    1.34
    ilver
    1.22
    omething
    1.20
    chool
    1.17
    kaya
    1.17
    pite
    1.14
    aurus
    1.14
    mith
    1.13
    erver
    1.13
    ullivan
    1.12
    Act Density 0.559%

    No Known Activations