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

    Neuronpedia

    INDEX
    Explanations

    instances of numbers representing weights or measurements

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values, especially those related to weights or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eve
    -0.68
    otin
    -0.67
     Uni
    -0.66
     Ou
    -0.64
    vell
    -0.63
    Du
    -0.63
    git
    -0.62
     bund
    -0.61
    catentry
    -0.61
    wcsstore
    -0.61
    POSITIVE LOGITS
     140
    2.88
    140
    2.00
     139
    1.94
     141
    1.92
     138
    1.91
     135
    1.87
     142
    1.84
     137
    1.82
     136
    1.76
     143
    1.70
    Act Density 0.030%

    No Known Activations