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

    Neuronpedia

    INDEX
    Explanations

    phrases related to variety and abundance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to groups or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yrights
    -0.55
    NOR
    -0.55
    vertisements
    -0.53
     Malays
    -0.51
    agate
    -0.51
    itters
    -0.51
    istani
    -0.50
    Friend
    -0.49
    dogs
    -0.49
    sylvania
    -0.48
    POSITIVE LOGITS
     of
    1.13
     array
    0.96
     Of
    0.95
     assortment
    0.94
     thereof
    0.92
     consisting
    0.90
     OF
    0.88
     number
    0.86
    Of
    0.85
     comprising
    0.82
    Act Density 0.291%

    No Known Activations