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

    Neuronpedia

    INDEX
    Explanations

    references to universities and educational institutions, particularly related to diversity targets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     wedge
    -0.74
     conversion
    -0.66
    creation
    -0.62
     differential
    -0.62
    adden
    -0.62
     cooker
    -0.59
     connector
    -0.59
     buckle
    -0.57
    ering
    -0.57
     threaded
    -0.56
    POSITIVE LOGITS
    ITY
    1.02
    idad
    0.99
    ivers
    0.97
    uador
    0.95
    acion
    0.94
    isitions
    0.93
    ilateral
    0.90
    arium
    0.90
    ITIES
    0.89
    iver
    0.87
    Act Density 0.032%

    No Known Activations