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

    Neuronpedia

    INDEX
    Explanations

    people or groups associated with specific actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" in different contexts, indicating a focus on identifying people or groups being described

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beet
    -0.72
     Processing
    -0.70
     Cape
    -0.67
     Affordable
    -0.67
     Bound
    -0.66
    Untitled
    -0.66
     Around
    -0.66
     Entertainment
    -0.64
     Anything
    -0.64
     Et
    -0.64
    POSITIVE LOGITS
    soever
    1.10
    oping
    0.91
     resided
    0.91
    upon
    0.88
    umbnails
    0.87
    ever
    0.87
     accompanies
    0.86
     migrated
    0.82
     preceded
    0.81
     oversaw
    0.78
    Act Density 0.169%

    No Known Activations