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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to technology and platforms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various geographic or categorical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hua
    -0.65
    illin
    -0.62
    agra
    -0.60
     Redemption
    -0.60
     Ree
    -0.59
     proof
    -0.58
     Removal
    -0.57
    ="/
    -0.57
     Chronicles
    -0.56
    cknowled
    -0.56
    POSITIVE LOGITS
     imaginable
    0.91
    cale
    0.87
    agos
    0.85
     including
    0.82
    hops
    0.81
     vying
    0.80
     besides
    0.79
     simultaneously
    0.78
    hips
    0.78
     viz
    0.73
    Act Density 0.247%

    No Known Activations